Health innovations

Using patient feedback in healthcare artificial intelligence could reduce health disparities

A study of a healthcare artificial intelligence program that inputs patient responses rather than information from doctors found that the new approach could reduce racial disparities (Source: “New Algorithms Could Reduce Racial Disparities in Health Care,” Wired, Jan. 25, 2021).

Health diagnostic software typically learns from doctors by digesting thousands or millions of x-rays or other data labeled by expert humans until it can accurately flag health problems by itself. A study published last month in the journal Nature Medicine took a different approach—training algorithms to read knee x-rays for arthritis by using patients as the AI arbiters of truth instead of doctors. The results revealed that radiologists may be missing important details when it comes to reading Black patients’ x-rays.

The algorithms trained on patients’ reports did a better job than doctors at accounting for the pain experienced by Black patients by discovering patterns of disease in the images that humans usually overlook.

“This sends a signal to radiologists and other doctors that we may need to reevaluate our current strategies,” says Said Ibrahim, a professor at Weill Cornell Medicine, in New York City, who researches health inequalities, and who was not involved in the study.

Algorithms designed to reveal what doctors don’t see, instead of mimicking their knowledge, could make health care more equitable. In a commentary on the new study, Ibrahim suggested it could help reduce disparities in who gets surgery for arthritis. African American patients are about 40 percent less likely than others to receive a knee replacement, he says, even though they are at least as likely to suffer osteoarthritis. Differences in income and insurance likely play a part, but so could differences in diagnosis.

Study: Healthcare software algorithms inadvertently infuse racism into care

An investigation by health news website STAT News found that a common method of using analytics software to target medical services to patients is infusing racial bias into decision-making about who should receive stepped-up care (Source: “From a small town in North Carolina to big-city hospitals, how software infuses racism into U.S. health care,” STAT News, Oct. 13).

While a study published last year documented bias in the use of an algorithm in one health system, STAT found the problems arise from multiple algorithms used in hospitals across the country. The bias is not intentional, but it reinforces deeply rooted inequities in the American health care system, effectively walling off low-income Black and Hispanic patients from services that less sick white patients routinely receive.

These algorithms are running in the background of most Americans’ interaction with the health care system. They sift data on patients’ medical problems, prior health costs, medication use, lab results and other information to predict how much their care will cost in the future and inform decisions such as whether they should get extra doctor visits or other support to manage their illnesses at home. The trouble is, these data reflect long-standing racial disparities in access to care, insurance coverage, and use of services, leading the algorithms to systematically overlook the needs of people of color in ways that insurers and providers may fail to recognize.

10 Ohio counties to participate in national opioid study

Ohio communities will be part of a $350 million federal study analyzing drug intervention techniques and policies. (Source: “Ohio Counties to Be Part of $350M Ohio counties to be part of $350M federal opioid study,” Associated Press, Nov. 9, 2019)

About $66 million will be channeled for the National Institutes of Health’s HEALing Communities Study through Ohio State University to Ashtabula, Athens, Cuyahoga, Darke, Greene, Guernsey, Hamilton, Lucas, Morrow and Scioto counties.

Research sites will test community engagement strategies and several proven opioid prevention and treatment practices.

Nine Ohio counties — Allen, Brown, Franklin, Huron, Jefferson, Ross, Stark, Williams and Wyandot — will be part of the study’s second wave. The study will also look at communities in Kentucky, New York and Massachusetts.

Feds to prioritize telemedicine funding based on ‘rurality’

The Federal Communications Commission is moving forward with plans to reform how funding is distributed for the agency's rural telemedicine program (Source: “FCC to prioritize telemedicine funding by 'rurality',” Modern Healthcare, Aug. 1, 2019).

The FCC on Thursday voted to adopt a report and order for its Rural Health Care Program, which helps fund broadband and telecommunications services for some healthcare providers in rural areas. A major part of the program involves subsidizing the difference between urban and rural rates for telecommunications services.

To address increasing demand for the program, last summer the FCC increased funding for the Rural Health Care Program to $571 million per year, up from its initial funding cap of $400 million.

With the new report and order, the FCC said it will reform the way it distributes Rural Health Care Program funding and take steps to guard against possible waste and inefficiencies in program costs.

In the event program demand outpaces available funding, the FCC now plans to prioritize support based on "rurality tiers," as well as whether the Health Resources and Services Administration designates a provider's area as part of a medically underserved population.

HPIO forum to explore innovative approaches to addressing Ohio’s health challenges

The Health Policy Institute of Ohio’s next forum, titled “Addressing Ohio’s Greatest Health Challenges through Technological Innovation,” will take place from 9:30 a.m. to 2 p.m. on Feb. 19 at the Fawcett Event Center at Ohio State University.

The forum will explore the role of technology in fostering innovative approaches to improving health and reducing health disparities, with a focus on addressing Ohio's greatest health challenges: mental health and addiction, infant mortality and chronic disease. Topics to be addressed at the forum include:

  • Telehealth services that increase access to mental health and addiction services
  • Transportation initiatives that enable better access to jobs and active living environments, while improving air quality
  • Data analytics tools that identify issues related to the social determinants of health

To register, or for more information, click here

Bundled payments cut Medicare costs, study finds

A recent change in the way Medicare pays for joint replacements is saving millions of dollars annually — and could save billions — without impacting patient care, a new study has found (Source: “Bundled Payments Work, Study Finds, But HHS Nominee No Fan,” Kaiser Health News, Jan. 3, 2017).

Under the new program, Medicare effectively agrees to pay hospitals a set fee — a bundled payment — for all care related to hip or knee replacement surgery, from the time of the surgery until 90 days after.  Starting in April 2016, CMS required around 800 hospitals in 67 cities to use the bundled payment model for joint replacements and 90 days of care after the surgery as part of the Comprehensive Care for Joint Replacement program. The program had previously been road-tested on a smaller number of hospitals on a voluntary basis, which formed the focus of the research.

Tom Price, the president-elect’s HHS nominee, a congressman from Georgia and an orthopedic surgeon, has actively opposed the idea of mandating bundled payments for these orthopedic operations, calling it “experimenting with Americans’ health,” in a letter to the Medicare agency just last September. In addition, the agency which designed and implemented the experiment, the Center for Medicare and Medicaid Innovation, was created by the Affordable Care Act to devise new methods for encouraging cost-effective care. It will disappear if the act is repealed, as President-elect Trump has promised to do.

The study appeared Tuesday in the Journal of the American Medical Association. Though one of its authors is Dr. Ezekiel Emanuel, a professor at the University of Pennsylvania who helped design the ACA, the research relies on Medicare claims data from 2008 through mid-2015, long before the presidential election.

The study found that hospitals saved an average of 8 percent under the program, and some saved much more. Price has been skeptical that bundled payments did save money, but the researchers estimate that if every hospital used this model, it would save Medicare $2 billion annually.

OHT releases population health report

The Governor’s Office of Health Transformation today released a reported titled “Improving population health planning in Ohio.”

The report, created by the Health Policy Institute of Ohio, provides recommendations for strengthening Ohio’s population health planning and implementation infrastructure and outlines ways to align population health priority areas, measures, objectives and evidence-based strategies with the design and implementation of the patient-centered medical home (PCMH) model.

HPIO was commissioned by the Governor’s Office of Health Transformation (OHT), the Ohio Department of Medicaid and the Ohio Department of Health in September 2015 to facilitate stakeholder engagement and provide guidance on improving population health planning in Ohio.

Ohio's performance on population health outcomes has declined relative to other states over the past two decades, and Ohio has significant disparities for many health outcomes by race, income and geography. Ohio also spends more on health care than most other states.   “Part of the challenge is the lack of coordination across ten state-level health improvement plans and  110 local health district and 170 hospital community health assessments/plans,” according to an OHT release. 

In December 2014, the federal Center for Medicare and Medicaid Innovation awarded Ohio a four-year $75 million State Innovation Model, or SIM, test grant for implementation of episode-based payments and rollout of a state-wide PCMH model over a four-year period. As part of that funding, Ohio must also develop a population health plan.

OHT will coordinate the implementation of the HPIO recommendations in 2016.

HHS announces Accountable Health Community funding

The Obama administration on Tuesday announced a new pilot program to test whether helping people with issues such as housing and food can save Medicare money and improve health outcomes (Source: “HHS launches test program for non-health needs,” The Hill, Jan. 5, 2015). 

The program will provide $157 million in ACA funding for “bridge organizations” that will work in certain communities to identify social needs of Medicare and Medicaid beneficiaries and help connect them to existing aid programs. 

 “For decades, we’ve known that social needs profoundly affect health, and this model will help us understand which strategies work to help improve health and spend dollars more wisely,” said Dr. Patrick Conway, Deputy Administrator of the Centers for Medicare and Medicaid Services (CMS).  

HPIO will host a call from 10 a.m. to 11 a.m. on Friday, Jan. 22 to discuss the model.  HPIO is interested in facilitating a coordinated effort to better position Ohio to receive this funding opportunity. 

HPIO ‘Beyond medical care’ publication explores upstream prevention strategies

The Health Policy Institute released its latest publication, “Beyond medical care: Emerging policy opportunities to advance prevention and improve health value in Ohio.” 

In addition to medical care, health is shaped by our behaviors and by social, economic and physical environments.  Upstream prevention strategies that address the causes of health problems rather than just the downstream consequences can help to improve health value in Ohio.

This new HPIO report provides actionable steps to improve Ohio’s commitment to upstream prevention through a balanced portfolio of health improvement activities both inside and outside the healthcare system.  The main report and a series of fact sheets provide policymakers and health leaders with a roadmap to expand the health policy agenda in Ohio to include a more balanced focus on the factors that shape our health both inside and outside the clinical care system.

At 2:30 p.m. on Thursday, September 24, HPIO will host a webinar on Beyond medical care.  The 30-minute webinar will provide an overview of the publication and supplemental materials, and ways to engage with HPIO and the Ohio Wellness and Prevention Network on upstream prevention.  Partners from philanthropy, public health and community-based organizations will review the report’s recommendations and share ideas for how they can be used. Click here to register

Ohio firm to build CMS quality data hub

Columbus-based Battelle has been awarded a four-year, $16 million federal contract to develop a framework for analyzing quality data collected by the Centers for Medicare and Medicaid Services (Source: “Battelle wins $16M federal contract for Obamacare quality data hub,” (Columbus Business First, Oct. 14, 2014).

Under its contract with CMS, Battelle will take over and make changes to the central IT infrastructure CMS uses to develop, maintain and analyze the data it’s collecting. Parikh called it “the hub in a big wheel of quality measures.”

CMS and other federal agencies for years have been collecting data on various measures, and under the ACA, Medicare is using more of those data points to determine a portion of how hospitals and doctors are paid.