Rebuilding Trust in our Doctors: An Option for our Broken System


This week’s impeachment hearings show what a crisis of trust we live in today.  69% of Americans believe the government withholds information from the public, according to recent findings by Pew Research Center.  Just 41 % of Americans trust news organizations.  We even distrust our own health care providers: Only 34% of Americans say they deeply trust their doctor.

One important way doctors can regrow that trust is to become educated about the types of medicine their patients want, including alternative therapies. 

People are seeking new ways to care for their health. For instance, the percentage of U.S. adults doing yoga and mediating—while still a minority– rose dramatically between 2012 and 2017, according to the CDC’s National Center for Health Statistics.  Likewise, the number of Americans taking dietary supplements including vitamins, minerals and natural therapies like turmeric, increased ten percentage points, to 75% in the past decade, according to the Council for Responsible Nutrition.  As Americans increasingly seek out non-pharmaceutical ways to address wellness, they need doctors who can talk to them about such alternatives. 

Unfortunately, this is rare.  As a provider of an holistic approach to health called Ayurvedic Medicine, I often see people who tell me their physician dismissed them when they asked about treatments they’d read about on the internet.  In many cases, clients tell me their doctor has actually chastised them for entertaining an alternative approach to their existing illness.  This leaves them disempowered. They wanted to make choices to improve their own health, but found they were not acknowledged, supported or even understood by the doctor.  

Furthermore, when doctors aren’t familiar with alternative treatments, they can’t advise their patients about interactions with conventional medicines.  With 75% of Americans taking some sort of supplement, all doctors should at least be able to offer guidance on contraindicated medications. 

With all this, it’s not surprising that only 30% of my patients report having a primary care physician they are happy with.

It doesn’t have to be this way. Physicians should receive mandatory training in integrative medicine, allowing them to consider both prevention and intervention in promoting health and wellbeing.  I’m not saying M.D.s must become experts in  alternative forms of medicine;. That would require years of rigorous training and hundreds of hours of clinical experience. I certainly do not want to see doctors prescribing an Ayurvedic remedy without understanding the underlying cause and pathology. That could simply replace pharmaceuticals with herbs, rather than working with the individual as a whole.  

Instead, I am proposing that conventionally trained physicians do what I do.  When I believe my clients would benefit from conventional medical treatment protocols instead of, or in addition to natural therapies, I offer an educated and empirically based explanation as to why, and respectfully refer out to the appropriate professional.   But conventional physicians rarely do the same. 

To give patients a full, informed range of options, doctors should be required to demonstrate familiarity with the various non-conventional systems of medicine, like traditional Chinese medicine, ayurvedic medicine and naturopathy, so they can have an educated conversation with patients who ask.  At that point, doctors could refer those cases elsewhere, or further their education to encompass a deeper understanding of the discipline. Either way, the patient has been acknowledged and supported by the system.

A few leading medical schools are already doing this. In Arizona, the Dr. Andrew Weil Center for Integrative medicine, where I have taught,  paved the way in 1994, followed by George Washington University and the University of Wisconsin, to name a few.

This divide between conventional and alternative medicine is particularly important at this moment in time. The current healthcare system has turned patients into healthcare consumers who must make their own choices, and who are  more and more empowered to take control of their own health. In many ways, this is a good thing.  As we do so, patients deserve doctors who understand the full range of choices that consumers face. 

If more physicians are trained and educated in medical school to think with an integrative approach to medicine, we can change the broken system, and docs will benefit too. The system is not set up to support them either. By creating an overwhelming demand, ordinary people can advocate for large health care hospitals, clinics and institution to provide compassion and implement integrative models for better quality of care. . It is in our hands to rebuild the trust of the now unhappy, and skeptical patient. Because without a trust in the healer, how can the healing begin?

Amita Nathwani is a professor of Ayurvedic Medicine and an adjunct faculty member with the Family Medicine Integrative Medicine Fellowship at Banner Health, University of Arizona.

The post Rebuilding Trust in our Doctors: An Option for our Broken System appeared first on The Health Care Blog.

from The Health Care Blog

The Dilemma of the Black Patient


Last week a nurse posted a video of
herself on Twitter
 mocking patients with the caption “We know when y’all are
faking” followed by laughing emojis. Twitter responded with the hashtag #patientsarenotfaking,
created by Imani Barbarin, and
a slew of testimonials of negligent medical care. While the nurse’s video was
not explicitly racialized, plenty in the black community felt a particular
sting: there is clear evidence that this attitude contributes to the problem of
black patients receiving substandard care, and that negative behavioral traits like faking or exaggerating symptoms are more likely
to be attributed to black patients. The problem is so bad that it turns
out racial bias is built right into an algorithm widely used by
hospitals to determine patient need. 

Since we can’t rely on the system or
algorithms, many health organizations and the popular media encourage patients to
advocate for
themselves and their loved ones by, for example, asking questions, asking for second (or more) opinions, “trusting [their] guts,”
and not being afraid to speak up for themselves or their loved ones. But this
ubiquitous advice to “be your own advocate” doesn’t take into account that not
all “advocacy” is interpreted in the same way—especially when the advocacy
comes from a black person. Sometimes a patient’s self-advocacy is dismissed as
“faking;” sometimes it is regarded as anger or hostility.

Black male faces showing neutral expressions are more likely than white faces to be interpreted as angry, violent, or hostile, while black women are often perceived as ill-tempered and angry. These stereotypes can have a chilling effect on a person’s decision to advocate for themselves, or it can prompt violent reaction.       

This past August, LeeAnn Bienaime delivered her firstborn child, with the assistance of her husband, in the couple’s bathtub. No, the couple had not planned a home birth. Instead, they were turned away from Naval Medical Center in Portsmouth, VA even though Bienaime was in active labor. Thankfully, she and her baby were healthy. In discussing her ordeal, Ms. Bienaime said, “In hindsight I would have stood my ground and not left.” 

Consider what happened to Barbara Dawson when she stood her ground. Ms. Dawson was having trouble breathing and went to Calhoun Liberty Hospital in Blountstown, Florida. The emergency room docs determined that she was stable and discharged her. However, Ms. Dawson, knowing that something was not right with her body, refused to leave and pled to be examined further. Hospital staff responded by calling the police, who promptly arrested her for trespassing and disorderly conduct. Even after she collapsed outside of the arresting officer’s patrol vehicle, the officer assumed she was faking and can be heard on the dashcam video telling an unresponsive Dawson, “Falling down like this, laying down, that’s not going to stop you from going to jail.” Within hours, Ms. Dawson was dead from a pulmonary embolism, a blood clot in her lungs.

It’s an open secret in US hospitals
that some patients and families are “good” and others are labeled “difficult.”
“Good” patients and families are (or are perceived to be) compliant: they
refrain from complaining or pushing back against medical advice or evaluations
and abide by social norms of manners and politeness. “Difficult” patients and
families challenge hospital staff.They may not easily
acquiesce to hospital directives, they may ask questions, or they may have

But many patients and families who
are regarded as “difficult” are merely trying to understand and advocate for
themselves or their loved ones the best way they know how. Patients who speak
up tend to be more satisfied with their medical encounter and gain better
information about their medical conditions. Additionally, patient self-advocacy
is thought to be on element in the prevention of medical mistakes. As Dr. Louise Aronson writes in
defense of difficult patients in The New England Journal of Medicine,
“There will always be patients and families who are considered high
maintenance, challenging, or both by health care providers. Among them are a
few with evident mental illness, but most are simply trying their best to
understand and manage their own or their loved ones’ illness.” Dr. Aronson
found herself reluctant to speak up for her father, who was a hospital patient,
out of worry of being labeled “difficult” by the hospital staff. She spoke up
anyway and likely saved her father’s life.   

For black patients, the consequence of being “difficult” can be as deadly as any disease, injury, or illness, while the consequence of notstanding firmly for oneself can also be dangerous. It has been well-documented that black patients don’t get adequate pain relief: a 2016 study of 418 medical students and residents found that approximately 50 percent believed that black patients have “thicker skin,”and are, therefore, unable to feel pain to the extent that white patients do. Black women are three times more likely to die during and shortly after pregnancy than white women—research has connected this disparity directly to institutional racism. Even wealthy, high-profile pregnant black women, like Beyoncé Knowles-Carter and Serena Williams, had their symptoms minimized or ignored, leading to critical complications. 

So what is a black patient to do?  Despite medical personnel’s insistence that she was simply “confused” as a result of her pain medications, Serena Williams could afford to not back down. Not everyone can. And the consequences can linger long past the medical encounter. Black patients who find themselves with biased providers tend to have shorter medical encounters. And those who pick up on a physician’s bias tend to have greater difficulty recalling the treatment plan, further contributing to worsened health outcomes.         

Medical personnel do not leave their biases at the door when they enter healthcare spaces and don their scrubs. In fact, data show that medical professionals exhibit similar levels of implicit bias as the general population, and that these biases seem to have at least some effect on treatment and care decisions.

There is some recognition that it is not black patients’
responsibility to effectively respond to bias. In September, the California
State Legislature passed
a bill
 that would require implicit bias training for
healthcare workers. Ideally, such training would make healthcare workers
cognizant of the racialized dynamics that can shape the medical encounter,
including whether patients advocate for themselves and how their advocacy is
perceived. While not a panacea and at minimum requires a long-term
commitment to change
, more states should take this first step. It could save

Willson, PhD, is currently a fellow at the National Humanities Center and an
Encore Public Voices fellow with the OpEd Project.

The post The Dilemma of the Black Patient appeared first on The Health Care Blog.

from The Health Care Blog

Artificial Intelligence vs. Tuberculosis, Part 1


Slumdog TB

No one knows who gave Rahul Roy
tuberculosis. Roy’s charmed life as a successful trader involved traveling in his
Mercedes C class between his apartment on the plush Nepean Sea Road in South
Mumbai and offices in Bombay Stock Exchange. He cared little for Mumbai’s weather.
He seldom rolled down his car windows – his ambient atmosphere, optimized for
his comfort, rarely changed.

Historically TB, or
“consumption” as it was known, was a Bohemian malady; the chronic suffering produced
a rhapsody which produced fine art. TB was fashionable in Victorian Britain, in
part, because consumption, like aristocracy, was thought to be hereditary. Even
after Robert Koch discovered that the cause of TB was a rod-shaped bacterium –
Mycobacterium Tuberculosis (MTB), TB had a special status denied to its immoral
peer, Syphilis, and unaesthetic cousin, leprosy.

TB became egalitarian in the early twentieth
century but retained an aristocratic noblesse oblige. George Orwell may have
contracted TB when he voluntarily lived with miners in crowded squalor to
understand poverty. Unlike Orwell, Roy had no pretentions of solidarity with
poor people. For Roy, there was nothing heroic about getting TB. He was
embarrassed not because of TB’s infectivity; TB sanitariums are a thing of the
past. TB signaled social class decline. He believed rickshawallahs, not
traders, got TB.

“In India, many believe TB affects only
poor people, which is a dangerous misconception,” said Rhea Lobo – film maker
and TB survivor.

Tuberculosis is the new leprosy. The
stigma has consequences, not least that it’s difficult diagnosing a disease
that you don’t want diagnosed. TB, particularly extra-pulmonary TB, mimics many

“TB can cause anything except
pregnancy,” quips Dr. Justy – a veteran chest physician. “If doctors don’t
routinely think about TB they’ll routinely miss TB.”

In Lobo, the myocobacteria
domiciled in the bones of her feet, giving her heel pain, which was variously
ascribed to bone bruise, bone cancer, and staphylococcal infection. Only when a
lost biopsy report resurfaced, and after receiving the wrong antibiotics, was TB
diagnosed, by which time the settlers had moved to her neck, creating multiple pockets
of pus. After multiple surgeries and a protracted course of antibiotics, she
was free of TB.

“If I revealed I had TB no one
would marry me, I was advised” laughed Lobo. “So, I made a documentary on TB
and started ‘Bolo Didi’ (speak sister), a support group for women with TB. Also,
I got married!”

Mycobacterium tuberculosis is an
astute colonialist which lets the body retain control of its affairs. The mycobacteria
arrive in droplets, legitimately, through the airways and settle in the breezy
climate of the upper lobes and superior segment of the lower lobes of the lungs.
If they sense weakness they attack, and if successful, cause primary TB.
Occasionally they so overpower the body that an avalanche of small, discrete
snowballs, called miliary TB, spread. More often, they live silently in calcified
lymph nodes as latent TB. When apt, they reappear, causing secondary TB. The
clues to their presence are calcified mediastinal nodes or a skin rash after
injection of mycobacterial protein.

MTB divides every 20 hours. In the
bacterial world that’s Monk-like libido. E. Coli, in comparison, divides every
20 minutes. Their sexual ennui makes them frustratingly difficult to culture.
Their tempered fecundity also means they don’t overwhelm their host with their
presence, permitting them to write fiction and live long enough to allow the
myocobacteria to jump ship.

TB has been around for a while. The
World Health Organization (WHO) wants TB eradicated but the myocobacteria have
no immediate plans for retirement. Deaths from TB are declining at a tortoise
pace of 2 % a year. TB affects 10 million and kills 1.6 million every year – it
is still the number one infectious cause of death.

The oldest disease’s nonchalance to
the medical juggernaut is not for the lack of a juggernaut effort. Mass
screening for TB using chest radiographs started before World War 2, and still
happens in Japan. The search became fatigued by the low detection of TB. The
challenge wasn’t just in looking for needles in haystacks, but getting to the
haystacks which, in developing countries, are dispersed like needles.

The battleground for TB eradication
is India, which has the highest burden of TB – a testament not just to its large
population. Because TB avoids epidemics, it never scares the crap out of people.
Its distribution and spread match society’s wealth distribution and
aspirations. And in that regard India is most propitious for its durability.

Few miles north of Nepean Sea Road is
Dharavi – Asia’s largest slum, made famous by the Oscar-winning film, Slumdog
Millionaire. From atop, Dharavi looks like thousand squashed coke cans beside
thousand crumpled cardboard boxes. On the ground, it’s a hot bed of economic
activity. No one wants to stay in Dharavi forever, its people want to become Bollywood
stars, or gangsters, or just very rich. Dharavi is a reservoir of hope.

Dharavi is a reservoir also of
active TB. In slums, which are full of houses packed like sardines in which
live people packed like sardines, where cholera spreads like wildfire and
wildfire spreads like cholera, myocobacteria travel much further. Familiarity
breeds TB. One person with active TB can infect nine – and none are any the wiser
of the infection because unlike cholera, which is wildfire, TB is a slow burn
and its symptoms are indistinguishable from the maladies of living in a slum.

Slum dwellers with active TB often
continue working – there’s no safety net in India to cushion the illness – and often
travel afar to work. They could be selling chai
and samosas outside the Bombay Stock
Exchange. With the habit of expectoration – in India, spitting on the streets
isn’t considered bad manners – sputum is aplenty, and mycobacteria-laden
droplets from Dharavi can easily reach Roy’s lungs. TB, the great leveler,
bridges India’s wealth divide. Mycobacteria unite Nepean Sea Road with Dharavi.

Rat in Matrix Algebra

The major challenges in fighting tuberculosis
are finding infected people and ensuring they take the treatment for the
prescribed duration, often several months. Both obstacles can wear each other–
if patients don’t take their treatment what’s the point finding TB? If TB can’t
be found what good is the treatment?

The two twists in the battle
against TB, drug resistant TB and concurrent TB and HIV, favor the
mycobacteria. But TB detection is making a resurgence with the reemergence of
the old warrior – the chest radiograph, which now has a new ally – artificial
intelligence (AI). Artificial Intelligence is chest radiograph’s Sancho Panza.

Ten miles north of Dharavi in slick
offices in Goregaon, Mumbai’s leafy suburb, data scientists training algorithms
to read chest radiographs are puzzled by AI’s leap in performance.

“The algorithm we developed,” says
Preetham Sreenivas incredulously, “has an AUC of 1 on the new set of

AUC, or area under the receiver
operator characteristic curve, measures diagnostic accuracy. The two types of diagnostic
errors are false negatives – mistaking abnormal for normal, and false positives
– mistaking normal for abnormal. In general, fewer false negatives (FNs) means more
false positives (FPs); trade-off of errors. A higher AUC implies fewer “false”
errors, AUC of 1 is perfect accuracy; no false positives, no false negatives.

Chest radiograph are two-dimensional
images on which three dimensional structures, such as lungs, are collapsed and
which, like Houdini, hide stuff in plain sight. Pathology literally hides
behind normal structures. It’s nearly impossible for radiologists to have an
AUC of 1. Not even God knows what’s going on in certain parts of the lung, such
as the posterior segment of the left lower lobe.

Here, AI seemed better than God at
interpreting chest radiographs. But Sreenivas, who leads the chest radiograph team
in – a start-up in Mumbai which solves healthcare problems using
artificial intelligence, refused to open the champagne.

“Algorithms can’t jump from an AUC
of 0.84 to 1. It should be the other way round – their performance should drop when
they see data (radiographs) from a new hospital,” explains Sreenivas.

Algorithms mature in three stages.
First, training –  data (x-rays),
labelled with ground truth, are fed to a deep neural network (the brain),
Labels, such as pleural effusion, pulmonary edema, pneumonia, or no abnormality,
teach AI. After seeing enough cases AI is ready for the second step, validation
– in which it is tested on different cases taken from the same source as the
training set – like same hospital. If AI performs respectably, it is ready for
the third stage – the test.

Training radiology residents is
like training AI. First, residents see cases knowing the answer. Then they see
cases on call from the institution they’re training at, without knowing the
answer. Finally, released into the world, they see cases from different
institutions and give an answer.

The test and training cases come
from different sources. The algorithm invariably performs worse on test than
training set because of “overfitting” – a phenomenon where the algorithm tries
hard fitting to the local culture. It thinks the rest of the world is exactly
like the place it trained, and can’t adapt to subtle differences in images
because of different manufacturers, different acquisition parameters, or acquisition
on different patient populations. To reduce overfitting, AI is regularly fed cases
from new institutions.

When AI’s performance on
radiographs from a new hospital mysteriously improved, Sreenivas smelt a rat.

“AI is matrix algebra. It’s not corrupt
like humans – it doesn’t cheat. The problem must
be the data,” Sreenivas pondered.

Birth of a company

“I wish I could say we founded this
company to fight TB,” says Pooja Rao, co-founder of, apologetically.
“But I’d be lying. The truth is that we saw in an international public health
problem a business case for AI.” was founded by Prashant
Warier and Pooja Rao. After graduating from the Indian Institute of Technology
(IIT), Warier, a natural born mathematician, did his PhD from Georgia Tech. He
had no plans of returning to India, until he faced the immigration department’s
bureaucratic incompetence. Someone had tried entering the US illegally on his
wife’s stolen passport. The bureaucracy, unable to distinguish the robber from
the robbed, denied her a work visa. Warier reluctantly left the US.

In India, Warier founded a company which
used big data to find preferences of niche customers. His company was bought by
Fractal, a data analytic giant – the purchase motivated largely by the desire
to recruit Warier.

Warier wanted to develop an AI-enabled
solution for healthcare. In India, data-driven decisions are common in retail but
sparse in healthcare. In a move unusual in industry and uncommon even in
academia, Fractal granted him freedom to tinker, with no strings attached. was incubated by Fractal.

Warier discovered Rao, a
physician-scientist and bioinformatician, on LinkedIn and invited her to lead
the research and development. Rao became a doctor to become a scientist because
she believed that deep knowledge of medicine helps join the dots in the biomedical
sciences. After her internship, she did a PhD at the Max Planck Institute in
Germany. For her thesis, she applied deep learning to predict Alzheimer’s
disease from RNA. Though frustrated by Alzheimer’s, which seemed uncannily
difficult to predict, she fell in love with deep learning.

Rao and Warier were initially
uncertain what their start-up should focus on. There were many applications of
AI in healthcare, such as genomic analysis, analysis of electronic medical records,
insurance claims data, Rao recalled two lessons from her PhD.

“Diseases such as Alzheimer’s
are heterogeneous, so the ground truth, the simple question – is there
Alzheimer’s – is messy. The most important thing I realized is that without the ground
truth AI is useless.”

Rao echoed the sentiments of Lady
Lovelace, the first computer programmer, from the nineteenth century. When
Lovelace saw the analytical engine, the first “algorithm”, invented by Charles
Babbage, she said: “The analytical
Engine has no pretensions whatever to originate anything. It
can do whatever we know how to order it to perform. It can
follow analysis; but it has no power of anticipating any analytical relations
or truths.”

The second lesson Rao learnt was
that the ground truth must be available immediately, not in the future – i.e.
AI must be trained on diseases of the present, not outcomes, which are nebulous
and take time to reveal. The immediacy of their answer, which must be now,
right away, reduced their choices to two – radiology and pathology. Pathology
had yet to be digitized en masse.

“The obvious choice for AI was radiology”,
revealed Warier.

Why “Qure” with a Q, not “Cure”
with a C, I asked. Was it a tribute to Arabic medicine?

“We’re not that erudite,” laughed
Warier. “The internet domain for ‘cure’ had already been taken.” was founded in 2016 during peak
AI euphoria. In those days deep learning seemed magical to those who understood
it, and to those who didn’t. Geoffrey Hinton, deep learning’s titan, famously
predicted radiologists’ extinction – he advised that radiologists should stop
being trained because AI would interpret the images just as well.

Bioethicist and architect of
Obamacare, Ezekiel Emanuel, told radiologists that their profession faced an
existential threat from AI. UK’s health secretary, Jeremy Hunt, drunk on the
Silicon Valley cool aid, prophesized that algorithms will outperform general
practitioners. Venture capitalist, Vinod Khosla predicted modestly that
algorithms will replace 80 % of doctors.

Amidst the metastasizing hype,
Warier and Rao remained circumspect. Both understood AI’s limitations. Rao was
aware that radiologists hedged in their reports – which often made the ground
truth a coin toss. They concluded that AI would be an incremental technology.
AI would help radiologists become better radiologists.

“We were firing arrows in the dark.
Radiology is vast. We didn’t know where to start,” recalls Rao.

Had been funded by venture
capitalists, they’d have a deadline to have a product. But Fractal prescribed
no fixed timeline. This gave the founders an opportunity to explore radiology.
The exploration was instructive.

They spoke to several radiologists
to better understand radiology, find the profession’s pain points, see what
could be automated, and what might be better dealt by AI. The advice ranged
from the flippant to the esoteric. One radiologist recommended using AI to
quantify lung fibrosis in interstitial pulmonary fibrosis, another, knee
cartilage for precision anti-rheumatoid therapy. has a stockpile of
unused, highly niche, esoteric algorithms.

Every radiologist’s idea of
augmentation was unique. Importantly, few of their ideas comprised mainstream practice.
Augmentation seemed a way of expanding radiologist’s possibilities, rather than
dealing with radiology’s exigencies – no radiologist, for instance, suggested
that AI should look for TB on chest radiographs.

Augmentation doesn’t excite venture
capitalists as much as replacement, transformation, or disruption. And
augmentation didn’t excite Rao and Warier, either. When you have your skin in
the commercial game, relevance is the only currency.

“Working for start-ups is different
from being a scientist in an academic medical center. We do science, too. But
before we take a project, we think about the return of investment. Just because
an endeavor is academically challenging doesn’t mean that it’s commercially
useful. If product don’t sell, start-ups have to close shop,” said Rao.

The small size of start-ups means
they don’t have to run decisions through bulky corporate governance. It doesn’t
take weeks convening meetings through Doodle polls. Like free climbers who
aren’t encumbered by climbing equipment, they can reach their goal sooner. Because
a small start-up is nimble it can fail fast, fail without faltering, fail a few
time. But it can’t fail forever. Qure needed a product it could democratize. Then
an epiphany.

In World War 2, after allied
aircrafts sustained bullets in enemy fire, some returned to the airbase and
others crashed. Engineers wanted the aircrafts reinforced at their weakest
points to increase their chances of surviving enemy fire. A renowned
statistician of the time, Abraham Wald, analyzed the distribution of the
bullets and advised that reinforcements be placed where the plane hadn’t been
shot. Wald realized that the planes which didn’t return were likely shot at the
weakest points. On the planes which returned the bullets marked their strongest

Warier and Rao realized that they
needed to think about scenarios where radiologists were absent, not where
radiologists were abundant. They had asked the wrong people the wrong question.
The imminent need wasn’t replacing or even augmenting radiologists, but in supplying
near-radiologist expertise where not a radiologist was in sight. The epiphany
changed their strategy.

“It’s funny – when I’m asked whether
I see AI replacing radiologists, I point out that in most of the rest of the
world there aren’t any radiologists to replace,” said Rao.

The choice of modality – chest
radiographs – followed logically because chest radiographs are the most commonly
ordered imaging test worldwide. They’re useful for a number of clinical
problems and seem deceptively easy to interpret. Their abundance also meant
that AI would have a large sample size to learn from.

“There just weren’t enough radiologists
to read the daily chest radiograph volume at Christian Medical College,
Vellore, where I worked. I can read chest x-rays because I’m a chest physician,
but reading radiographs takes away time I could be spending with my patients,
and I just couldn’t keep up with the volumes,” recalls Dr. Justy. Several
radiographs remained unread for several weeks, many hid life-threatening conditions
such as pneumothorax or lung cancer. The hospital was helpless – their budget
was constrained and as important as radiologists were, other physicians and
services were more important. Furthermore, even if they wanted they couldn’t
recruit radiologists because the supply of radiologists in India is small.

Justy believes AI can offer two
levels of service. For expert physicians like her, it can take away the normal
radiographs, leaving her to read the abnormal ones, which reduces the workload
because the majority of the radiographs are normal. For novice physicians, and
non-physicians, AI could provide an interpretation – diagnosis, or differential
diagnoses, or just point abnormalities on the radiograph.

The team imagined those
scenarios, too. First they needed the ingredients, the data, i.e. the chest
radiographs. But the start-up comprised only a few data scientists, none of
whom had any hospital affiliations.

“I was literally on the road for
two years asking hospitals for chest radiographs. I barely saw my family,”
recalls Warier. “Getting the hospitals to share data was the most difficult
part of building”

Warier became a traveling salesman
and met with leadership of over hundred healthcare facilities of varying sizes,
resources, locations, and patient populations. He explained what wanted
to achieve and why they needed radiographs. There were long waits outside the
leadership office, last minute meeting cancellations, unanswered e-mails,
lukewarm receptions, and enthusiasm followed by silence. But he made progress,
and many places agreed to give him the chest radiographs. The data came with stipulations.
Some wanted to share revenue. Some wanted research collaborations. Some had
unrealistic demands such as share of the company. It was trial and error for
Warier, as he had done nothing of this nature before.

Actually it was Warier’s IIT alumni
network which opened doors. IITians (graduates of the Indian Institutes of
Technology) practically run India’s business, commerce, and healthcare. Heads
of private equity which funds corporate hospitals are often IITians, as are the
CEOs of these hospitals.

“Without my IIT alumni network, I
don’t think we could have pulled it off. Once an IITian introduces an IITian to
an IITian, it’s an unwritten rule that they must help,” said Warier.

Warier’s efforts paid. Qure has now
acquired over 2.5 million chest radiographs from over 100 sites for training,
validation and testing the chest radiograph algorithm.

“As a data scientist my ethos is
that there’s no such thing as ‘too much data.’ More the merrier,” smiled

“The mobile phone reached many
parts of India before the landline could get there,” explains Warier.
“Similarly, AI will reach parts of India before radiologists.”

Soon, a few others, including
Srinivas, joined the team. Whilst the data scientists were educating AI, Rao
and Warier were figuring their customer base. It was evident that radiologists
would not be their customers. Radiologists didn’t need AI. Their customers were
those who needed radiologists but were prepared to settle for AI.

“The secret to commercialization in
healthcare is need, real need, not induced demand. But it’s tricky because the
neediest are least likely to generate revenues,” said Warier in a pragmatic
tone. Unless the product can be scaled at low marginal costs. An opportunity
for arose in the public health space – the detection of tuberculosis on
chest radiographs in the global fight against TB. It was an indication that
radiologists in developing worlds didn’t mind conceding – they had plenty on
their plates, already.

“It was serendipity,” recalls Rao.
“A consultant suggested that we use our algorithm to detect TB. We then met
people working in the TB space – advocates, activists, social workers,
physicians, and epidemiologists. We were inspired particularly by Dr. Madhu Pai,
Professor of Epidemiology at McGill University. His passion to eradicate TB
made us believe that the fight against TB was personal.” started with four people.
Today 35 people work for it. They even have a person dedicated to regulatory
affairs. Rao remembers the early days. “We were lucky to have been supported by
Fractal. Had we been operating out of a garage, we might not have survived. Building
algorithms isn’t easy.”

Finding Tuberculosis

Hamlet’s modified opening soliloquy,
“TB or not TB, that is the question”, simplifies the dilemma facing TB detection,
which is a choice between fewer false positives and fewer false negatives.
Ideally, one wants neither. The treatment for tuberculosis – quadruple therapy
– exacts several month commitment. It’s not a walk in the park. Patients have
to be monitored to confirm they are treatment compliant, and though directly
observed therapy, medicine’s big brother, has become less intrusive, it still consumes
resources. Taking TB treatment when one doesn’t have TB is unfortunate. But not
taking TB treatment when one has TB can be tragic, and defeats the purpose of
detection, and perpetuates the reservoir of TB.

Hamlet’s soliloquy can be broken
into two parts – screening and confirmation. When screening for TB, “not TB is
the question”. The screening test must be sensitive –capable of finding TB in
those with TB, i.e. have a high negative predictive value (NPV), so that when
it says “no TB” – we’re (nearly) certain the person doesn’t have TB.

Those positive on screening tests
comprise two groups – true positives (TB) and false positives (not TB). We don’t
want antibiotics frivolously given, so the soliloquy reverses; it is now “TB,
that is the question.” The confirmatory test must be specific, highly capable
of finding “not TB” in those without TB, i.e. have a high positive predictive
value (PPV), so that when it says “TB” – we’re (nearly) certain that the person
has TB. Confirmatory tests should not be used to screen, and vice versa.

Tuberculosis can be inferred on
chest radiographs or myocobacteria TB can be seen on microscopy. Seeing is
believing and seeing the bacteria by microscopy was once the highest level of
proof of infection. In one method, slide containing sputum is stained with carbol
fuchsin, rendering it red. MTB retains its glow even after the slide is washed
with acid alcohol, a property responsible for its other name – acid fast

Sputum microscopy, once heavily endorsed
by the WHO for the detection of TB, is cheap but complicated. The sputum
specimen must contain sputum, not saliva, which is easily mistaken for sputum. Patients
have to be taught how to bring up the sputum from deep inside their chest. The
best time to collect sputum is early morning, so the collection needs
discipline, which means that the yield of sputum depends on the motivation of
the patient. Inspiring patients to provide sputum is hard because even those
who regularly cough phlegm can find its sight displeasing.

Which is to say nothing about the
analysis part, which requires attention to detail. It’s easier seeing mycobacteria
when they’re abundant. Sputum microscopy is best at detecting the most
infectious of the most active of the active TB sufferers. Its accuracy depends
on the spectrum of disease. If you see MTB, the patient has TB. If you don’t
see MTB, the patient could still have TB. Sputum microscopy, alone, is too
insensitive and cumbersome for mass screening – yet, in many parts of the
world, that’s all they have.

The gold standard test for TB – the
unfailing truth that the patient has TB, independent of the spectrum of disease
– is culture of mycobacteria, which was deemed impractical because on the Löwenstein–Jensen
medium, the agar made specially for MTB, it took six weeks to grow MTB, which is
too long for treatment decisions. Culture has made a comeback, in order to
detect drug resistant mycobacteria. On newer media, such as MGIT, the mycobacteria
grow much faster.

The detection of TB was
revolutionized by molecular diagnostics, notably the nucleic acid amplification
test, also known as GeneXpert MTB/ RIF, shortened to Xpert, which simultaneously
detects mycobacterial DNA and assesses whether the mycobacteria are resistant
to rifampicin – one of the mainline anti-tuberculosis drugs.

Xpert boasts a specificity of 98 %,
and with a sensitivity of 90 % it is nearly gold standard material, or at least
good enough for confirmation of TB. It gives an answer in 2 hours – a
dramatically reduced turnaround time compared to agar. Xpert can detect 131
colony-forming units of MTB per ml of specimen – which is a marked improvement
from microscopy, where there should be 10, 000 colony-forming units of MTB per
ml of specimen for reliable detection. However, Xpert can’t be used on
everyone, not just because its sensitivity isn’t high enough – 90 % is a B
plus, and for screening we need an A plus sensitivity. But also its price,
which ranges from $10 – $20 per cartridge, and is too expensive for mass
screening in developing countries.

This brings us back to the veteran
warrior, the chest radiograph, which has a long history. Shortly after Wilhelm
Röntgen’s discovery, x-rays were used to see the lungs, the lungs were a
natural choice because there was natural contrast between the air, through
which the rays passed, and the bones, which stopped the rays. Pathology in the
lungs stopped the rays, too – so the ‘stopping of rays’ became a marker for
lung disease, chief of which was tuberculosis.

X-rays were soon conscripted to the
battlefield in the Great War to locate bullets in wounded soldiers, making them
war heroes. But it was the writer, Thomas Mann, who elevated the radiograph to
literary fame in Magic Mountain – a story about a TB sanitarium. The chest
radiograph and tuberculosis became intertwined in people’s imagination. By
World War 2, chest radiographs were used for national TB screening in the US.

The findings of TB on chest
radiographs include consolidation (whiteness), big lymph nodes in the
mediastinum, cavitation (destruction of lung), nodules, shrunken lung, and
pleural effusion. These findings, though sensitive for TB – if the chest radiograph
is normal, active TB is practically excluded, aren’t terribly specific, as they’re
shared by other diseases, such as sarcoid.

Chest radiographs became popular
with immigration authorities in Britain and Australia to screen for TB in
immigrants from high TB burden countries at the port of entry. But the WHO remained
unimpressed by chest radiographs, preferring sputum analysis instead. The inter-
and intra-observer variation in the interpretation of the radiograph didn’t
inspire confidence. Radiologists would often disagree with each other, and
sometimes disagree with themselves. WHO had other concerns.

“One reason that the WHO is weary
of chest radiographs is that they fear that if radiographs alone are used for
decision making, TB will be overtreated. This is common practice in the private
medical sector in India,” explains Professor Madhu Pai.

Nonetheless, Pai advocates that
radiographs triage for TB, to select patients for Xpert, which is cost
effective because radiographs, presently, are cheaper than molecular tests.  Using Xpert only on patients with abnormal
chest radiographs would increase its diagnostic yield – i.e. percentage of
cases which test positive. Chest radiograph’s high sensitivity compliments
Xpert’s high specificity. But this combination isn’t 100 % – nothing in
diagnostic medicine is. The highly infective endobronchial TB can’t be seen on
chest radiograph, because the mycobacteria never make it to the lungs, and
remain stranded in the airway.

“Symptoms such as cough are even more
non-specific than chest radiographs for TB. Cough means shit in New Delhi,
because of the air pollution which gives everyone a cough,” explains Pai,
basically emphasizing that neither the chest radiograph nor clinical acumen,
can be removed from the diagnostic pathway for TB.

A test can’t be judged just by its
AUC. How likely people – doctors and patients – are to adopt a test is also
important and here the radiograph outshines sputum microscopy, because despite
its limitations, well known to radiologists, radiographs still carry a certain
aura, particularly in India. In the Bollywood movie, Anand, an oncologist played by Amitabh Bachchan diagnosed terminal
cancer by glancing at the patient’s radiograph for couple of seconds. Not CT,
not PET, but a humble old radiograph. Bollywood has set a very high bar for
Artificial Intelligence.

Saurabh Jha (aka @RogueRad) is a contributing editor for THCB. This is part 1 of a two-part story.

The post Artificial Intelligence vs. Tuberculosis, Part 1 appeared first on The Health Care Blog.

from The Health Care Blog

The Definition of Health Data has Changed—and HHS is All Over It | Dr. Mona Siddiqui, HHS


Dr. Mona Siddiqui, Chief Data Officer at the US Department of Health & Human Services (HHS), says the definition of health data has changed. Health data is not just about what kind of data or where it came from, but, now, she says health data is more or less data that is defined by its intent. (Think how social media data is being used in healthcare these days for just a minute here..) Mona led a meeting with over 70 stakeholders across the healthcare industry this summer to talk next steps for this new era of health data: assessing risks and benefits, talking transparency, and looking at issuing recommendations for actions that HHS can be engaged in. What’s next as the industry continues to look to HHS for guidance around data policy? Tune in to find out.

Filmed at the HIMSS Health 2.0 Conference in Santa Clara, CA in September 2019.

Jessica DaMassa is the host of the WTF Health show & stars in Health in 2 Point 00 with Matthew HoltGet a glimpse of the future of healthcare by meeting the people who are going to change it. Find more WTF Health interviews here or check out

The post The Definition of Health Data has Changed—and HHS is All Over It | Dr. Mona Siddiqui, HHS appeared first on The Health Care Blog.

from The Health Care Blog

The Lynne Chou O’Keefe Fallacy


Rob Coppedge and Bryony Winn wrote an interesting article in Xconomy yesterday. I told Rob (& the world) on Twitter yesterday that it was good but wrong. Why was it wrong? Well it encompasses something I’m going to call the Lynne Chou O’Keefe Fallacy. And yes, I’ll get to that in a minute. But first. What did Rob and Bryony say?

Having walked the halls and corridors and been deafened by the DJs at HLTH, Rob & Bryony determined why many digital health companies have failed (or will fail) and a few have succeeded. They’ve dubbed the winners “Digital Health Survivors.” And they go on to say that many of the failures have been backed by VCs who don’t know health care while the companies they’ve invested in have “product-market fit problems, sales traction hiccups, or lack of credible proof points.”

What did the ” Survivors” do? They have:  

“hired health care experts, partnered effectively, and have even co-developed their models alongside legacy players. Many raised venture capital from strategic corporate investors who have helped them refine their product, accelerate channel access, and get past the risk of “death by pilot.”

Now it won’t totally shock you to discover that Rob heads Echo Health Ventures, the joint VC fund from Cambia Heath Solutions (Blues of Oregon) & BCBS of N. Carolina) and Bryony runs innovation at BCBS of N. Carolina. So they may be a tad biased towards the strategic venture = success model. But they do have a point. Many but not all of their portfolio are selling tools and services to the incumbents in health care, which mostly includes health plans, hospitals and pharma.

And now we get to the Lynne Chou O’Keefe fallacy. (You might argue that fallacy is the wrong term, but bear with me).

Lynne is another super smart VC and having decamped from the break up of Kleiner Perkins, has just started her own fund, Define Ventures. About two years ago she gave a talk at a Health 2.0 Chapter meeting in San Francisco which was a wonderful roadmap for what a tech company needed to do to “partner with” (i.e. sell to) hospitals, plans and pharma. As you might imagine it included a bunch of getting to know your customers’ problems, doing a whole amount of data analytics, getting your clinical process correct, etc, etc. But in the end, Lynne’s assessment was that the best bet for a health tech startup’s success was to improve the life of an incumbent.

I don’t have a problem with that advice per se, and frankly I send many of the startups I advise to incumbents, hoping that they’ll become clients or investors. But here’s the mistake made by Rob & Bryony. They say:

“Despite being attacked on all sides from innovative startups, well-capitalized tech companies, big retail brands, and government regulators, traditional health care services companies simply don’t seem disrupted yet. In fact, driven by consolidation and strong financial performance, many are healthier and appear more confident than ever. And some of the more successful ones even seem downright innovative themselves, having learned from innovators to build, buy, and partner their way to new capabilities.” <snip> “These Innovative Incumbents are differentiated by their commitment to becoming good partners with the “Digital Health Survivors.” They have realized that winning in the future means bringing together better solutions and consumer experiences than their competitors.”

There’s an illusion out there that these incumbents are doing well financially because they are able to take the best of the digital health tech and ideas and change what they are doing.

No one who looks at the US health care system can possibly believe that the incumbents have changed their behavior to adopt the consumer friendly ethos of the digital health tech crowd. They are making money the old fashioned way, by creating monopolies (including buying up physician networks to feed the inpatient beast), ramping up drug prices, (something Rob’s boss Mark Ganz has been very explicit about) and aggressively pursuing patients for collections. And when they get caught in the act, they settle to keep it out of the media. Now, given that the Obama administration was set on HITECH and trying to roll out the ACA, and the Trump administration can’t manage to create a coherent policy on anything, regulators have been more or less absent so it’s no surprise that we’ve had a decade plus of incumbents running rampant. That’s why we are in the mess we are in today and why 35% of the country wants single payer and another 35% want a massive expansion of the ACA.

I’m not sure if Rob & Bryony caught the talk from one of the incumbents at HLTH, but Pam Kehaly, CEO of Blues of Arizona, said something very revealing: “we pat ourselves on the back about value based care but 90% of America is just doing fee-for-service.” The incumbents know how to play that game and they are winning. Just look at the profit totals for those top provider systems.

(Stolen from Modern Healthcare via Eric Topol)

Which brings me to what’s wrong with all of this and it’s the question I asked Lynne at that talk, mindful of her Kleiner Perkins heritage and the alleged $1bn dollar profit Kleiner made on their Amazon investment.

When Jeff Bezos came to pitch John Doerr to invest in Amazon, did he explain how he was going to build a system to help Barnes & Noble sell more books or help Sears sell more clothes? No, he came to put those companies out of business.

Where are the VCs who want to invest in today’s health care equivalent? Because that’s what we need.

Matthew Holt is the Founder and publisher of THCB

The post The Lynne Chou O’Keefe Fallacy appeared first on The Health Care Blog.

from The Health Care Blog

Health in 2 Point 00, Episode 101 | FBI Scandals, EHR Competitors, & Amazon

On Episode 101 of Health in 2 Point 00, there are some scandals and competitors brewing in the health tech space! Jess and I discuss Outcome Health’s investigation and charge by the FBI for $1 billion in fraudulently obtained funds; Mint’s founder starting Vital, a new EHR company, to reinvent the overall EHR experience (even though I believe it is currently one of the toughest markets to enter into); Amazon launching Amazon Transcribe Medical which will be a tool medical professionals can use to dictate their notes and streamline them into EHR systems; and Wellframe raising $20 million to advance digital health management. If you are in Japan, catch me at Health 2.0 in Tokyo, Japan where they will be showcasing new health tech startups in the space or if you are in Vegas, go hang with Jess at the American Society of Hospital Pharmacies conference! Last but not least, Guidewell launched its Aging in Place Accelerator that is looking for startups in the senior health tech space (applications are due December 8th). — Matthew Holt

The post Health in 2 Point 00, Episode 101 | FBI Scandals, EHR Competitors, & Amazon appeared first on The Health Care Blog.

from The Health Care Blog

Maternal Mortality – Separating Signal from Noise


When Samuel Morse left his New Haven home to paint a portrait of the
Maquis du Lafayette in Washington DC, it was the last time he would see his
pregnant wife. Shortly after his arrival in Washington, his wife developed
complications during childbirth. A messenger took several days on horseback to
relay the message to Mr Morse. Because the trip back to New Haven took several
more, his wife had died by the time he arrived at their home.  So moved was he by the tragedy of lost time
that he dedicated the majority of the rest of his life to make sure that this
would never happen to anyone again. His subsequent work on the telegraph and in
particular the mechanism of communication for the telegraph resulted in Morse
code – the first instantaneous messaging system in the world.

Mr Morse’s pain is not foreign to us in the 21st century. We feel the loss of new mothers so deeply that, when earlier this year new statistics on the rate of maternal death were released and suggested that American women died at three times the rate of other developed countries during child birth, doctors, patient advocates, and even Congress seemed willing to move heaven and earth to fix the problem. As someone who cares for expectant mothers at high risk for cardiovascular complications, I too was moved. But beyond the certainty of the headlines lay the nuance of the data, which seemed to tell a murkier story.

First at issue was the presentation of the data. Certainly, as a rate
per live births, it would seem that the United States lagged behind other OECD
countries – our maternal mortality rate was between 17.2 and 26.4 deaths per
100,000 live births, compared to 6.6 in the UK or 3.7 in Spain. But this
translated to approximately 700 maternal deaths per year across the United
States (among approximately 2.7 million annual births). While we would all agree
that one avoidable maternal death is one too many, the low incidence means that
small rates of error could have weighty implications on the reported results.
For instance, an error rate of 0.01% would put the United States in line with
other developed countries.

Surely, the error rate could not account for half the reported
deaths, right? Unfortunately, it is difficult to estimate how close to reality
the CDC reported data is, primarily because the main source data for maternal
mortality is a single question asked on the application for death certificates.
The question asks whether the deceased was pregnant at the time of death,
within 42 days of death, or in the 43 to 365 days prior to death. While
pregnancy at the time of death may be easy to assess, the latter two categories
are subject to significantly more error.

Just how much error is remarkably uncertain. One program called Review to Action attempted to ascertain this error rate by using Maternal Mortality Review committees to better understand the real causes of death among women who died around the time of the birth of their child. They looked at data from four states (Colorado (2008-12), Delaware (2009-14), Geogia (2012-13), and Ohio (2008-12)) to see if a deeper look at maternal deaths could uncover the true drivers of maternal mortality. Of the 650 deaths examined, 97 had no evidence of pregnancy in the year prior to death, a false positive rate of 15%. Among the remaining 553 deaths deemed “pregnancy associated” (death within one year of being pregnant), only 175 were thought to be pregnancy related, defined as “the death of a woman during pregnancy or within one year of the end of pregnancy from a pregnancy related complication, a chain of events initiated by pregnancy, or the aggravation of an unrelated condition by the physiologic effects of pregnancy.” If this number was used to define maternal mortality, the rate would be 5.8/100,000 births, similar to other OECD countries.

Of course, this is an unfair comparison, because there is great
variation in how maternal mortality rates are calculated across the world. Moreover,
the rate of error in small numbers has as much likelihood of underreporting as
it does overreporting. But it does demonstrate a core problem in the
measurement of maternal mortality. Because the numbers are so small to begin
with, small errors have the risk of having significant effects on the results.

Even with uncertainty in the incidence, could we learn something
from those deaths confirmed to be pregnancy related? In cardiology circles,
there is great emphasis placed on the fact that the leading cause of death was
cardiovascular disease. If true, this could offer significant insight on how to
make an impact on reducing maternal deaths. But the devil is in the details,
and here the details suggested that in order to make cardiovascular disease the
leading cause of pregnancy-related death, we had to combine stroke, cardiomyopathy,
and “other CV conditions” which include a variety of conditions (including
congenital, ischemic, hypertensive and other heart diseases) (taken from MMWR
report on pregnancy related death). Though this broad grouping may make
epidemiologic sense, it makes less sense when attempting to build measures to
prevent death.

This is at the crux of the problem of the overemphasis on these statistics. They enable well-meaning people to create broad policies that have the potential for more harm than good. Take, for example, the administrator who boasted that he reduced the death rate to half the national average by getting automatic chest x-rays for all pregnant women with shortness of breath and automatic treatment for hypertension. At first blush it seems an impressive statistic. But even if they started at the national average, they would have reduced maternal deaths by 18. How many pregnant women received unnecessary chest radiation and medications to achieve that goal? The risks to casting wide nets to catch rare conditions are real and sometimes outweigh the benefit gained.

To understand where the balance of risks and
benefits are optimized, we must start with an earnest accounting of the data in
the public sphere.  As currently reported
in both the medical and the lay media, the limitations of data derived from
small numbers are not discussed. Though messier than the headlines suggest, this
nuance offers the chance to shift focus to the actions that give clinicians,
patients, and caregivers the tools to really advocate for women at risk.

We also need to lower the barriers to expertise.
Cardiac obstetrics teams have become more common but are still not widespread. Most
programs offer great multidisciplinary care for patients with established risk,
but few offer virtual services to support the care of lower risk patients with
complex circumstances. Conditions like mild hypertension, edema, or even
palpitations are often benign conditions, but easily accessible expert support
for these circumstances could help identify signals of increased risk at times
and reassurance to the mother and her primary doctor at others. In the group I
work in, we have attempted to address this problem by creating a telemedicine
based consult system, so patients can be cared for by their own doctor with the
benefit of background support of a larger village of experts. Building virtual
support networks to broader populations offers the chance to create a safety
net without the risks of overtreatment seen with reflexive care algorithms. And
critically, patients can still be cared for by their own doctors, who they know
and trust.

We also need to rebuild the village of support networks
around new mothers. Many of the interventions that can reduce maternal risk
have to do with early detection, identification of conditions like post-partum
depression and unsafe home situations, and simpler things like offering new
moms time to engage in self-care (exercise, sleep, stress reduction, eating right).
While medical interventions seem to center on the detection of disease once
medical care is sought, broadening the frame of care and creating the
opportunity for peer based social support has the chance of helping all new
moms, not just those at highest risk.

Most importantly, though, we need to acknowledge the complexity of the issue of maternal mortality. Our solutions are not as singular as they were for Mr Morse, and accepting this will give us our best chance at success. For us, the answer is likely a series of incremental solutions, both small and large, working together to extinguish once and for all the tragedy of lost time.

Dr Ameya Kulkarni is the Chief of Cardiology in Northern Virginia at the Mid-Atlantic Permanente Medical Group.

The post Maternal Mortality – Separating Signal from Noise appeared first on The Health Care Blog.

from The Health Care Blog