Today's News and Commentary

About healthcare IT

UPMC cuts hospital readmission rates with ML [Machine Learning] algorithm: Interesting article on the use of ML to effectively decrease readmissions by identifying at-risk patients. The results: “…the ML algorithm identifies patients at highest risk of re-hospitalization within seven and 30 days of discharge. To date, re-hospitalizations have been reduced by about 50 percent.” The article has a dashboard graphic that illustrates important features of the algorithm.

Read the article

Microsoft built a bot to match patients to clinical trials: Microsoft's lab in Israel has developed user-friendly software to match patients with clinical trials. Patients can enter their information and the app will ask further questions if needed. The business model is for drug companies to buy the product to help them recruit patients for their studies.

Read the article

Amazon gives AI to Harvard hospital for efficiency gains: Beth Israel Deaconess Medical Center in Boston already uses Amazon’s cloud service to store its data. Now Amazon is giving the medical center a grant to develop Artificial Intelligence to help with some routine functions, like more efficient operating room scheduling.

Read the article

‘Wired into the walls’: Voice-recognition system promises to automate data entry during office visits: One of the most burdensome tasks facing medical professionals is documentation of the patient visit. Some practitioners use “medical scribes.” The device described in this article is made by Nuance, the parent company of Dragon dictation software. Patient-physician conversations are transcribed live and aided by a locator when movement of either occurs. Having personally used Dragon for medical dictation, I can attest to its accuracy once it learns your voice and to spell technical terms. However, the transcription will still need to be reviewed since substitutions do occur.

Read the article

IQVIA debuts research platform to de-ID links between genomic and clinical data: One problem in gathering data for research is protection of patient confidentiality. IQVIA has developed a platform that de-identifies patient data while preserving clinical and genetic data.

Read how this task is accomplished

What Your Doctor Isn’t Allowed to Tell You:
Despite the promise of healthcare IT, systems do make mistakes that create errors in care. The theme of this article is: “Badly designed electronic records can be hazardous to your health, but a gag clause protects the makers.The problem is that some EHR vendors have such overwhelming market power that they insert gag clauses into their contracts with hospitals, ostensibly to protect their intellectual property.” The author calls for banning these gag clauses in order to help healthcare providers freely exchange information about functionality.

Read the article (From the Wall Street Journal, but appears to have open access)

How Banner Health Network is managing interoperability with 30-plus EHRs: Interoperability continues to be a problem, especially within healthcare systems that are expected to have freely flowing information. Phoenix-area Banner Health Network is successfully using software to link internally disparate EMRs.

Read the story

About hospitals

IBM Watson Health Announces 100 Top Hospitals:2019 Study Finds Top-Performing U.S. Hospitals Provide Better Care at Lower Cost and Higher Profit Margins than Peers Evaluated in the Study: This “top” list was formerly the Truven Health Analytics 100 Top Hospitals. Each “top hospital” ranking has its own methodology. Read this list and see if you agree with its evaluation.

Read the rankings

Speech: Remarks by Administrator Seema Verma at the Federation of American Hospitals 2019 Public Policy Conference: This speech was delivered yesterday. While Verma covered many topics (the full address is included in the link), the one part on which the media is focusing is the “Stark” laws. The laws in question (named after the now-retired Fortney “Pete” Stark, D-CA) were directed at hospitals providing financial incentives to physicians in return for referrals. With increasing prevalence of bundling and cooperative relationships like ACOs, the federal government is realizing that the laws need to be changed or “safe harbors” for the relationships need to be more clearly defined.

Read the address

About the public’s health

New funding models for health urgently needed, experts warn: The G20 Health and Development Partnership — a coalition of business, academic and non-governmental organisations- issued a report today that says disease and antimicrobial resistance pose a bigger threat to the world’s economy than global warming. Governments need to take responsibility for these problems and new methods of financing must be implemented.

Read a summary article
Read the full report

Big Pharma Gave Money To Patient Advocacy Groups Opposing Medicare Changes: For-profit entities, especially “big pharma” are influencing the lobbying efforts of nonprofits by making large donations. The Kaiser Family Foundation has a website called Pre$cription For Power that is a resource for such information.

Read the article

About insurance

Paying Patients To Switch: Impact Of A Rewards Program On Choice Of Providers, Prices, And Utilization: We know that patients who have to pay more out of pocket use fewer services. This study is the “other side of the coin.” Patients who used lower-cost, preferred providers got money back for doing so. The results: “For 131 elective services, patients who received care from a designated lower-price provider received a check ranging from $25 to $500, depending on the provider’s price and service. In the first twelve months of the program we found a 2.1 percent reduction in prices paid for services targeted by the rewards program. The reductions in price resulted in savings of $2.3 million, or roughly $8 per person, per year. These effects were primarily seen in magnetic resonance imaging and ultrasounds, with no observed price reduction among surgical procedures.”

Read the research (Subscription required)
Read an open access summary