Digital Health Frontier
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/04/shutterstock_705165757-1.jpg)
By John Halamka and Paul Cerrato - The potential benefits of AI-enabled algorithms have to be weighed against the risk of dataset shift, which can compromise their accuracy in ways that developers never anticipated.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/03/shutterstock_651441421-1.jpg)
By John Halamka and Paul Cerrato - Our vision for health care technology includes a steadfast determination to use AI to augment human intelligence — not contribute to a dystopian future some fear is already upon us.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/03/GettyImages-1169108502.jpg)
By John Halamka and Paul Cerrato - One of the privileges we enjoy working in digital health is the opportunity to use state-of-the-art AI tools to unearth actionable insights from millions of patient records, without compromising their privacy.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/02/shutterstock_1238330020.jpg)
By John Halamka and Paul Cerrato - Machine learning-enhanced algorithms may help clinicians select the best medications for each patient, speeding up the long journey to find effective relief for a crippling disorder.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/02/1677050_3776308_0019.jpg)
By John Halamka and Paul Cerrato - Some clinicians reject any AI-infused recommendations, while others are so confident in these tools that they forfeit their independent diagnostic skills. A closer look at the research can turn these mistakes into insights.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/02/shutterstock_208232557.jpg)
By John Halamka and Paul Cerrato - Randomized controlled trials (RCTs), the gold standard in clinical medicine, only tell us how the average patient responds to a treatment or an AI-based algorithm. N of 1 trials provide a unique opportunity to individualize patient care.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/02/shutterstock_147907604-1024x683.jpg)
By John Halamka and Paul Cerrato - Predicting cardiovascular disease and death is an imperfect science; the right AI algorithms can make these estimates more accurate.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/01/shutterstock_775224916_Web_800_ppi800px__800px.jpg)
By John Halamka and Paul Cerrato - Affective computing and sentiment analysis can help clinicians read between the lines, allowing them to detect patients’ unexpressed feelings and subtle emotional cues that may signal subclinical disease—and much more.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/01/GettyImages-1325334297.jpg)
By John Halamka and Paul Cerrato - A better understanding of proteomics, genomics, and a variety of other biomarkers can help personalize patient care and shed new light on human physiology and pathology.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2022/01/GettyImages-1286840350.jpg)
By John Halamka and Paul Cerrato - Most AI-driven algorithms take the clinician from A—the ailing patient—to D—the final diagnosis—ignoring intermediate steps B and C in the diagnostic journey. There is a better way.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2021/12/shutterstock_728787643.jpg)
By John Halamka and Paul Cerrato - Once considered a revolutionary way to keep patient data secure and easily accessible, the technology continues to look for its sweet spot.
![](https://cdn.prod-carehubs.net/n1/c03538cfbe9dca05/uploads/2021/12/shutterstock_460700098.jpg)
By John Halamka and Paul Cerrato - Personalized nutrition therapy that takes into account one’s genotype has tremendous promise, but the evidence supporting its use in routine patient care is mixed.