Cooperating for better care.

personalized medicine

Tag Archives

The age of algorithms in disease prediction

Flow chart of an algorithm.

Algorithms from machine learning have been beating  humans in predicting such illnesses as heart disease and diabetes. Those algorithms  will probably become  even more accurate as they include personal data from smartphones and wearables, suggests an article from the Harvard Business Review.

Yannis Paschalidis, the director of the Center for Information Systems Engineering at Boston University, wrote in the Harvard Business Review that engineers at BU  are working with such local hospitals as Brigham and Women’s Hospital and Boston Medical Center to manage heart disease and diabetes using algorithms that can predict hospitalizations up to a year in advance with 82 percent accuracy.

That’s compared, for example, to a 56 percent predictive accuracy of guidelines used by cardiologists to predict a patient’s risk of cardiovascular disease.

Of course, early identification of risk of serious diseases could  save patients, providers and insurers billions of dollars as well a prevent many premature deaths.

Mr. Paschalidis, FierceHealthcare paraphrased, said that “machine learning will only become more accurate as data sets expand with access to personal data from wearables and smartphones. And as value-based payment models take hold, hospitals are likely to build analytics into their care processes.”

He wrote in the article: “If we can now predict future hospitalizations with more than 80% accuracy using medical records alone, imagine what is possible if we can tap into this trove of personal data. Recommender systems could be used to nudge us to adopt healthier eating habits and behaviors. The holy grail of heading off the emergence of conditions by keeping people well could be realized.”

Still, Mr. Paschalidis warned in his article:

“Yes, analytics and data-driven personalized medicine and health monitoring present risks. Do we want our employers and health insurers to know the status of our health and the risks we face? Privacy, security, and reliability of new systems and methods are also critical concerns. But rather than retreating from this new era, we should be working on how to strengthen our methods, institutions, laws, and regulatory framework to avoid those unintended consequences. Algorithms — the foundation of encryption methods, privacy-preserving data processing, and intrusion- and fraud detection systems — could help.”

T0 read the Harvard Business Review piece, please hit this link.

To read the FierceHealthcare report, please hit this link.

5 suggestions to advance personalized medicine


Among their ideas:

  1. “Before {the patient meets}  with the clinician, a member of the care team  {should} assesses the patient’s level of engagement and capacity for self-management, so that the patient can participate in his or her care in a meaningful way. As part of that process, the patient completes a self-assessment of health needs, preferences, and goals by telephone, electronically, or in person. Through the medical record, this information is conveyed to the clinician before or at the time of the appointment.
  2. “The clinician assesses the patient’s health status and health risks using the best available conventional, genomic, and other precision diagnostic tools. Optimal risk-mitigation and therapeutic goals for the patient are identified.
  3. The clinician and patient set and clearly articulate shared goals, using the clinician’s health assessment and the patient’s self-assessment.
  4. “The shared goals are then incorporated into a personalized health plan that the patient is directly involved in crafting. The clinician chooses appropriate metrics for monitoring progress, identified explicitly for the patient; an electronic medical record is used for data collection and tracking.
  5. “The clinician coordinates care with the rest of the patient’s care team and arranges for appropriate follow-up.

“With this five-step process, the personalized health plan becomes a living, adaptable document — available to all team members — that is continually revisited in person, by phone, and/or via patient portals and mobile applications.”

To read their article, please hit this link.

Maybe psychiatry can’t join the personalized-medicine bandwagon


Image of a psychiatrist from the 1930s.

Can or should psychiatry  join the personalized-medicine bandwagon?

An article in STAT,  Boston Globe affiliate, says:

“Despite the tremendous effort being poured into identifying biomarkers to help guide treatment for various psychiatric disorders, this work has yet to significantly improve clinical outcomes. {unlike with, for example,  personalized medicine’s advances in treating certain cancers}. A big roadblock is that we haven’t yet found strong genetic mutations that can guide treatment for mental health issues. It’s not for lack of trying. In 2013, three large groups of investigatorsset out to analyze 1.2 million genetic variants in 2,256 patients with depression. They were hoping to find a genetic marker that reliably predicted whether a patient would get better with antidepressant medications.

“They didn’t find one. Continuing to look for genetic mutations linked to mental health certainly makes sense. But it’s already possible to match patients with effective treatments using other types of cheap and accessible information. Analyzing an individual’s sociodemographic data, such as race or gender, and self-reported behavioral information, such as how poorly he or she sleeps, can often point the way to knowing how he or she will respond to a particular therapy.”

To read the STAT article, please hit this link.

Personalized-medicine focus seen threatening public-health efforts


1802 caricature of Edward Jenner vaccinating patients who feared it would make them sprout cowlike appendages.

Ronald Bayer, Ph.D., and Sandro Galea, M.D., both of the Columbia University Mailman School of Public Health, argue in The New England Journal of Medicine that the federal government and the healthcare industry’s focus on personalized medicine could hurt efforts to improve population health.

They argue that  precision medicine advocates’ focus on treatment  at the individual level means that they tend to ignore such  pressing concerns as  the United States’ low ranking among developed nations in care quality or socio-economic factors’ (aka the “social determinants of health”) big effect on mortality.

The authors say that  the Feds have invested about five times more in  National Institutes of Health research, increasingly focused  on individualized-care models, than in the Centers for Disease Control and Prevention.  And, they write, the proportion of NIH-funded initiatives with “population” or “public” in their names fell 90 percent in the last decade.

“Without minimizing the possible gains to clinical care from greater realization of precision medicine’s promise, we worry that an unstinting focus on precision medicine by trusted spokespeople for health is a mistake — and a distraction from the goal of producing a healthier population.”

Contact Info

(617) 230-4965

Wellesley, Mass