Thanks to a large influx of stimulus spending, a debate over electronic health records (EHRs) has been bubbling through newspages and blogs. Some people are concerned about privacy, others are worried that EHRs will help the government will take over healthcare. But few have focused on the potential benefits to patients.
Here’s a smattering of recent studies highlighting how electronic health records might help our costly and overburdened health system:
A study I wrote about earlier last month found that hospitals with the most effective electronic medical record systems had healthier patients–they saw fewer deaths and complications–and lower bills.
Electronic systems also seem to improve preventative medicine by boosting screening. A study from Harvard Medical School found that patients who were sent reminders for colorectal cancer screenings, which were generated from electronic medical data, were more likely to get themselves screened. Electronic reminders sent to physicians had no effect on screening rates, suggesting that patients may be an untapped resource in their own preventative healthcare.
A third study points to the potential research benefits of electronic medical records, something that some of the physicians and researchers I have spoken with are particularly excited about. According to the research, published in the British Medical Journal, statistical analysis of electronic medical record databases mimics results of clinical trials, predicting which drugs work best. This kind of data wouldn’t replace clinical trials, of course. But scientists say EMRs could be used to supplement clinical trial data, to look at a drug’s effectiveness in a more diverse population, for example. Details of the study are described in a release from the University of Pennsylvania:
[Richard Tannen, Professor of Medicine at the University of Pennsylvania School of Medicine and his] team selected six previously performed randomized trials with 17 measured outcomes and compared them to study data from an electronic database – the UK general practice research database (GPRD), which included the medical records of roughly 8 million patients. Treatment efficacy was determined by the prevalence of cardiovascular outcomes, such as stroke, heart attack and death.
After using standard biostatistical methods to adjust for differences in the treated and untreated groups in the analysis of the database information, Tannen found that there were no differences in the database outcomes compared to randomized clinical trials in nine out of 17 outcomes.
In the other eight outcomes, Tannen’s group used an additional new biostatistical approach they discovered that controlled for differences between the treated and untreated groups prior to the time the study began. By using the new biostatistical method instead of the standard approach, the researchers showed there were no differences between the outcomes in the EMR database study compared to the randomized clinical trials.
I go to a large medical practice in Boston that has been one of the pioneers in electronic medical records, and I personally find it very useful. Different doctors have access to my information, whether I’m visiting the Cambridge or Boston location. And I can look at my own health data online–seeing your weight, cholesterol and blood pressure measurements plotted out over time is a sure impetus to keep them in check.
The big new idea for making self-driving cars that can go anywhere
The mainstream approach to driverless cars is slow and difficult. These startups think going all-in on AI will get there faster.
Inside Charm Industrial’s big bet on corn stalks for carbon removal
The startup used plant matter and bio-oil to sequester thousands of tons of carbon. The question now is how reliable, scalable, and economical this approach will prove.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.