Oncora Medical and MD Anderson embark on personalized radiation oncology study


Philadelphia-based clinical decision support startup Oncora Medical is collaborating with University of Texas MD Anderson Cancer Center in Houston in a study to help radiation oncologists develop personalized treatment plans with the goal of improving outcomes, according to a news release. The Phase 1 study will focus on data from 2,000 breast cancer patients and last three to nine months.

Oncora’s Precision Radiation Oncology Platform will analyze data from MD Anderson’s electronic medical record system, tumor registry, radiation therapy planning system, and Brocade — a Web-based clinical documentation tool for medical records developed by MD Anderson Associate Professor of Radiation Oncology, Dr. Benjamin Smith.

Oncora will be tasked with creating interoperability between its Precision Radiation Oncology Platform and Brocade to explore the potential value of a combined product, the release said.

“Through this alliance, we hope to improve workflows and processes for radiation oncologists and simultaneously give radiation oncologists access to better information to support real-time, precision medical decision making,” Smith said in the release.

Although most people think of precision medicine as targeted therapy, Lindsay noted that the company defines precision medicine as the “right treatment for the right patient at the right time” and wants to expand the conventionally accepted definition beyond drugs and diagnostics.

The study was a year in the making and will be Oncora’s biggest endeavor to date, Lindsay said.

“Our software needs to access data across multiple software systems at a center that treats nearly 10,000 patients per year. That is part of the reason why we spent so long planning for the partnership. We want everything to go smoothly and we want to deliver MD Anderson a seamlessly integrated product.”

The study will also assess physician utilization and quality of the company’s predictive modeling efforts. But the ultimate criteria for success will be the deployment of a “functioning product” at MD Anderson, noted Lindsay.

The second phase of the of the collaboration with MD Anderson will expand the study to all cancer types treated with radiation.

One of the challenges in healthcare is de-siloing data, particularly for clinical decision support. When it comes to cancer treatment, radiation oncology data risks being siloed in different hospital software systems, which makes it tough to collect and analyze. Oncora Medical views its approach as a way to make predictive analytics and precision radiation oncology succeed.

Photo: Jirsak, Getty Images

Some of the most exciting (and scary) aspects of machine learning that you may not know about

The decibel of chatter around artificial intelligence is rising to the point where many are inclined to dismiss it as hype. It’s unfair because while certain aspects of the technology are a long way away from becoming mainstream tech, like self-driving cars, it’s a fascinating topic. After listening to a talk recently by Dr. Eric Horvitz, Microsoft Research managing director, I can appreciate that the number of applications being conceived around the technology is only matched by the ethical dilemmas surrounding it. But in both cases, they are much more varied than what typically dominates the conversation about AI.

For fans of the ethical roads less traveled in AI, Horvitz offered a fair few items for his audience to consider at the SXSW conference last week that alternated between hope for the human condition and fear for it. Although I previously highlighted some of the healthcare applications he discussed, there are plenty of issues he raised that one day could be just as relevant to healthcare. I have included a few of them here.

Interpreting facial expressions


The idea of machine learning being applied to make people more connected to each other improve in subtle ways our communication skills is fascinating to me. One example used was a blind man conducting a meeting and receiving auditory cues on the facial expressions of his audience. The idea is to provide more insight on the people around him so he can have a better sense of how the points he raised are perceived beyond what the people in the meeting actually say. In a practical way, it gives him an additional layer of knowledge he wouldn’t have otherwise and makes him feel more connected to others.

The ethical decisions of self-driving cars

As exciting as the prospect of self-driving cars is, Horvitz called attention to some of the still unresolved, important questions of how they would perform in an accident or when trying to avoid an accident. What decisions would the computer make when, say a collision with a pedestrian is likely and the car has to make a split-second choice? Does it preserve the life of the driver or the pedestrian, if it comes to that?  What responsibility does the manufacturer have?  What values will be embedded in the system? How should manufacturers disclose this information?

Horvitz slide

A slide that was part of Dr. Eric Horvitz’s talk at SXSW this year.

Adversarial machine learning

One fascinating topic addressed in the talk was how machine learning could be used with negative intent —referred to as adversarial machine learning. It involves feeding a computer information that changes how it interprets images, words, and how it processes information. In one study, a computer that was fed images of a stop sign could be retained to interpret those images as a yield sign. That has important implications for self-driving cars and automated tasks in other sectors.

Another facet of adversarial machine learning is the use of information tracking individuals’ Web searches, likes and dislikes shared in social networks and the kinds of content they tend to click on and using that information to manipulate these people. That could cover a wide swathe of misdeeds from manipulation through fake Tweets designed by neural networks in the personality of the account holder to particularly nasty phishing attacks. Horvitz noted that these AI attacks on human minds will be an important issue in our lifetime.

“We’re talking about technologies that will touch us in much more intimate ways because they are the technologies of intellect,” Horvitz said.

Appling AI to judicial sentencing software

Although machine learning for clinical decision support tools is an area of interest in healthcare to help identify patients at risk of readmission or to analyze medical images for patterns and anomalies, it’s also entering the realm of judicial sentencing. The concern is that these software tools that some states permit judges to use in determining sentencing include the bias of their human creators and further erode confidence in the legal system. ProPublica drew attention to the issue last year.

Wrestling with ethical issues and challenges of AI

Although he likened the stage of AI development to the first airplane flight by the Wright Brothers at Kittyhawk, North Carolina which was 20 feet off the ground and lasted all of 12 seconds. But the risk and challenge of many technologies is that a certain point it can progress far faster than anyone can anticipate. This is why there’s been a push to wrestle with the ethical issues of AI rather than address them after the fact in a reactive way, such as Partnership on AI. Eight years ago, Stanford University set up AI100, an initiative to study AI for the next 100 years. The idea is that the group will study and anticipate how the effects of artificial intelligence will impact every aspect of how people work and live.

Photo: Andrzej Wojcicki, Getty Images

Digital Pharmacist acquires rival app to accelerate pharmacy services product development

A digital health business formed from the merger of RxWiki and TeleManager Technologies in January has made its first acquisition, according to a news release. Digital Pharmacist acquired PocketRx —an app that’s designed to help community pharmacists enable their customers to better engage with pharmacists. The deal will help Digital Pharmacists speed up product development and consolidate their products and services into one app.

Alan Stickler, Digital Pharmacist Chief Technology Officer, shared some information about the deal in a phone interview.

The financial terms of the deal were not disclosed.

Stickler said the deal would support Digital Pharmacist’s efforts to provide a more personalized service to pharmacists and their own customer base. Customers use the app to track their own medications and refills. But for community pharmacists, the services are designed to give them access to resources that most pharmacists lack compared with the likes of CVS and Walgreens. Pharmacies use the app to improve their marketing reach and give them better insights on the needs of their customer base.

As part of the acquisition deal, Digital Pharmacist is acquiring the app from software developer Praeses. Robert Terrell, product manager for PocketRx, has joined Digital Pharmacist as product development director. Praeses will also give software development and support for Digital Pharmacist.

Stickler estimated that a fully consolidated app would be ready by the end of the second quarter or the beginning of the third quarter.

The acquisition of PocketRx follows a string of digital health acquisitions last week and the consolidation that has been happening across healthcare, particularly in the pharmacy sector.

Photo: Nicols Meroo, Getty Images

Texas Medicaid payment reform initiative curbs elective early deliveries

Even though the health risks to babies born before they reach full term at 39 weeks have long been recognized, nearly 1 in 10 babies in the United States is born prematurely. Texas decided to try to change that.

In 2011, the Texas Medicaid program was the first in the country to take steps to curb elective early deliveries by refusing to pay providers who induced early labor or performed a cesarean section that wasn’t medically necessary before 39 weeks. In the first two years after that, Texas reduced the rate of unnecessary early delivery by as much as 14 percent. The state’s efforts also led to an increase in the length of pregnancies by nearly a week, with infants weighing on average nearly half a pound more, a new study found.

Those reimbursement changes were part of a Texas Medicaid payment reform law. Before it took effect, 10.63 percent of Medicaid single births in the state were early elective deliveries, according to the study, which was published in the March issue of Health Affairs.  After the law passed, the percentage of unnecessary early deliveries declined 2.03 percentage points.

About half of the decline was due to the payment reforms, while the rest could be attributed to other efforts to reduce early deliveries, unrelated trends and the economy, said Heather Dahlen, a research associate at Medica Research Institute in Minnetonka, Minnesota, and the study’s lead author.

Still, “in order for the rate to fall that much, there was a relatively significant effect on the target population,” Dahlen said.

The impact on early elective delivery was greatest for Latinos, whose rate declined 1.77 percentage points to 8.14 percent. The rate for non-Latino blacks declined 1.4 percentage points to 9.57 percent, while non-Latino whites saw a much smaller decline — 0.72 percentage point, to 8.43 percent.

Infants born before 39 weeks are more likely to have a range of health problems, including respiratory disorders, sepsis and feeding issues, and to be admitted to hospital neonatal intensive care units. Doctors and expectant mothers who opt for early delivery may not realize the risk or choose to go ahead for convenience. In some rural areas, women may be encouraged to schedule early deliveries to ensure they’re able to get to the hospital in time.

For the study, researchers analyzed data from 2009 to 2013 on the national Vital Statistics System’s Natality Detail Files, which is derived from information reported on birth certificates.

The federal-state Medicaid program for low-income people pays for roughly half of all births in the United States. After Texas passed its law, five other states passed similar laws in 2013: Georgia, Michigan, New Mexico, New York and South Carolina.

Reducing preterm births generally, and early elective deliveries in particular, is a priority for many groups, including health care providers, hospitals and patient-advocacy organizations. In addition to payment reform, these groups have employed other strategies such as educational programs for health care providers and patients and “hard-stop” policies that prohibit doctors from scheduling early elective deliveries unless they meet medical necessity standards.

“The Medicaid program was paying doctors for doing things that actually harm babies,” said Dr. Paul Jarris, chief medical officer at the March of Dimes, which publishes an annual report card that ranks states based on their preterm birth rates. “These payment changes actually make huge differences if they’re done right.”

Photo: Bigstock

At a pediatric innovation challenge, startups illustrate growing maturity of healthcare entrepreneurs

CEO Vidur Bhatnagar’s company Keriton won the digital health track of the Impact Pediatric Health pitch at SXSW.

The two companies that walked away with awards in their hands and $15,000 checks in their pockets from the Impact Pediatric Health pitch event at SXSW offered practical solutions to common problems.

Luminopia used virtual reality to tackle and treat a common problem —lazy eye, which affects 2 percent to 3 percent of the population. Keriton, which MedCity News profiled earlier this month, developed a system to bring more organization to the task of making sure a mother’s breast milk gets to the right baby in the neonatal ICU and tracking how much mothers are producing.

Not only are many digital health and medtech entrepreneurs making better choices of which pain points to go after, they are increasingly showing a grasp of marketing that makes their pitch more persuasive.

Team Luminopia cofounders Scott Xiao (left) and Dean Travers

Team Luminopia won in the medtech category.

The medtech winner,  Luminopia,  was formed by a group of Harvard freshman who developed a way to use virtual reality goggles to correct amblyopia or lazy eye. Long term, the company’s technology holds the potential to provide a way to detect this condition, which can frequently go undiagnosed. The current practice for treating lazy eye is an eye patch but that comes with a social stigma that is likely to mean children are inclined not to wear it.

Dean Travers is the CEO and one of three cofounders at Luminopia. His presentation noted that one nice aspect of its approach is that primary care physicians can prescribe the virtual reality device to children and they can do the necessary exercises with it from home.

“We don’t need to disrupt the workflow,” Travers said.

The Impact Pediatric Health pitch event at SXSW offers a glimpse not only at how entrepreneurs are trying to solve the healthcare challenges of an often overlooked market. It also offers a perspective on how children’s hospitals are evaluating startups’ technology.

Certa Dose was founded by a physician who developed a color-coordinated syringe showing the appropriate amount by weight as a way to reduce the risk of overdosing young children. The company targets high-risk drugs. The device is aimed at hospitals and parents. Dr. Caleb Hernandez, the Chief Medical Officer and cofounder, noted that the company’s device eliminated the need to make complex mathematical calculations to determine dosage by weight. It also envisions paramedics using its device for conditions like anaphylactic shock, signaling it plans to compete with EpiPen.

Neuroelectrics developed a connected cap to monitor and stimulate targeted brain areas for children with epilepsy. Ana Maiques, the CEO, who modeled the company’s head gear, showed that to make the device less intimidating to children, it provides a cover with mouse ears to make the device more appealing. Asked by judges how the company knows it’s the best for the market it is targeting, Maiques gave an unusual but gutsy answer.

“I don’t know if it will meet the endpoints in the [upcoming]clinical trial, but if we fail we fail.”

Photo: Daniel Kraft of Singularity University, who served as a judge and emcee for the event,  Impact Pediatric Health

At the intersection of cancer treatment and technology, it’s more evolution than revolution

For the first time at SXSW, a series of panel discussions in the health track zoomed in on cancer — Connect to End Cancer. The themes that dominated tended to be the role of technology such as telemedicine and data from connected devices, the role of 5G technology and technology’s shortcomings. But concerns over what Trump’s FDA nominee will do with the FDA cast a long shadow over parts of the discussion.

Here were some of the more interesting conversation points across a couple of the panel discussions I attended.

 Telemedicine, telehealth and the impact of 5G


Most people don’t think of cancer treatment and telemedicine intersecting but as Rebecca Kaul, Houston-based MD Anderson Chief Innovation Officer noted, cancer center patients tend to have a varied geographical base. “We think telemedicine is highly important — two-thirds of our patients come from outside of Texas.”

John Donovan, AT&T Chief Strategy Officer and group president for AT&T Technology and Operations, noted that 5G had the potential to improve the quality of virtual interactions between patients and physicians.

5G will improve the quality of technology execution from telemedicine from near real time to real time, he noted. Donovan pointed out that healthcare is one of several industries hindered by slow technology. This advancement could help not only healthcare but other industries as well such as fintech.

Coping with technology shortcomings

Another interesting part was when the discussion tackled some of the shortcomings of technology, particularly when our expectations can’t be matched by the reality on the ground. Greg Simon, director of the Biden Cancer Initiative at the Biden Foundation, defended platforms like IBM Watson by noting that even the Hubble space telescope when initially launched had blurry vision. It took a team of scientists to correct that.  The computer platform is not a panacea because one of the challenges of new technology is that it takes time before it rises to its potential.

“It’s not that surprising that Watson isn’t perfect,” Simon noted. “It is still a student. It reads everything but it doesn’t know everything.”

Aman Bhandari, Merck executive director of data, sciences and partnerships, observed that there is dissonance between what we have the ability to do and what is actually happening in the healthcare delivery system.

“So much great innovation is happening, yet our current health delivery system isn’t working to make those innovations available to everyone,” Bhandari said.

Even immunotherapy, which is a hot area of investment for venture capital and is regarded as a promising new technology, has its own set of shortcomings. The problem with immunotherapy is that it can attack healthy tissue as well as unhealthy tissue.

Big data and interoperability often rise to the surface as obstacles in healthcare and these sessions were no exception. In a lightning round for a panel moderated by Halle Tecco, who founded Rock Health and now teaches a class at Columbia Business School, she asked panelists what’s the biggest challenge they currently face. Bhandari noted data liquidity and Tecco’s husband Jeff Hammerbacher, the cofounder of Cloudera, called attention to the “Tower of Babel” around data.

Every regulation at the FDA has been written in blood

With speculation that President Donald Trump’s nomination to head up the U.S. Food and Drug Administration will champion deregulation, several of the panelists in one session feared what the consequences might be. Simon and Bhandari touched on the evolution of the FDA.

“Every regulation at the FDA has been written in blood,” said Simon solemnly. “You will not hear from the cancer community that the FDA is slow and burdensome.”

Bhandari added, “Every major regulation has happened because of a public health concern.”

Simon expressed the hope that the administration would steer clear of cancer initiatives that have already been launched.

Another panelist expressed the hope that providing better education support to patients about particular clinical trials would help with poor recruitment efforts.

Simon was also frustrated by the way data from clinical trials is not released until one year after the clinical study was finished and hoped that would change.

Advice for startups

Tecco also asked her panel to offer some advice for startups. At some point in the conversation, Bhandari expressed some frustration with startups that make AI and machine learning claims without providing a more nuanced approach to how they are using these tools or even noting the slight differences between the two. Machine learning is one aspect of AI, which is a much broader term.

Simon advised entrepreneurs to “immerse yourself in patients” and focus on their interests and priorities rather than investors, adding:

“Don’t think about investors or the markets — if you immerse yourself in patients, you will figure something out.”

Photo: xrisca30, Getty Images,

5 startups from the SXSW Accelerator that you should meet

Sound Scouts, an Australian-based business that developed a DIY hearing test app that parents can download and run for their children, emerged as the winner of the SXSW Accelerator pitch competition in the digital health and wearables track, according to an emailed announcement from the organizers. The test is cleverly disguised as a game designed to create a more interactive experience for kids but alert parents to any hearing problems that warrant attention from healthcare professionals.

It wasn’t immediately clear what Sound Scouts’ plans for the U.S. market are, but Founder Carolyn Mee said during her initial presentation that she wants to make the product available to adults and children around the world.

Although there was only one dedicated health track, the technology behind a few of the other startup winners have direct or indirect applications for healthcare as well.

Enterprise and Smart Data

Deep 6 AI developed technology to make it easier to match patients with appropriate clinical trials through natural language processing and artificial intelligence. The clinical trial recruitment process is one of the most time consuming and costly aspects of drug development and Deep 6 AI is one of several companies to take up the gauntlet of creating a more streamlined process. Wout Brusselaers is the founder and CEO.

Security and Privacy

UnifyID uses data collected by sensors from an individual’s mobile devices such as GPS, accelerometer, gyroscope, magnetometer, barometer, ambient light, and WiFi and Bluetooth signal telemetries to figure out what makes the owner unique, according to the San Francisco company’s website. The data is kept on the local device, is encrypted and anonymized. UnifyID’s approach can also be applied to desktop and laptop computers. Given the cybersecurity concerns in healthcare over the theft of personal health data it seems like UnifyID’s approach could have useful applications in this sector.

Innovative World

Thimble.io in Buffalo, New York wants customers to discover their inner engineer, their inner maker. A monthly subscription gives users an electronics kit each month that teaches them how to code, hack and construct electronic devices. By playing the long game, stimulating young and older minds to use these kits as stepping stones towards realizing their creative interests, they could help create a new generation of software developers and biomedical engineers wherever they might be.

Augmented and Virtual Reality

Lampix shuns the goggles and other head gear that tends to be associated with augmented and virtual reality. Instead, it takes a more subtle approach. The company’s product lets users adopt flat surfaces like a table to project a computer screen and interact with the screen projection as if it’s a touchscreen. As for healthcare applications, Lampix’s platform could be used as another approach to gaming technology for cognitive assessment to expanding health literacy delivery tools.