| Both sides previous revision
Previous revision
Next revision
|
Previous revision
Last revision
Both sides next revision
|
aihc [2021/10/13 16:18]
nigam |
aihc [2023/11/09 10:10]
nigam |
| ====== Stanford Medicine Program for Artificial Intelligence in Healthcare ====== | ====== Responsible Artificial Intelligence in Healthcare ====== |
| |
| Consider the case of Vera, a 60 year old woman of Asian descent with a history of hypertension and asthma, entering the doctor's office with symptoms consistent with a diagnosis of pneumonia. Her primary care physician must diagnose and treat the acute illness, but also manage risk for chronic diseases such as heart attack, stroke, renal failure, and osteoporosis. Ideally, treatment decisions for Vera are guided by risk stratification to decide if to treat, and evidence based selection of how to treat. However, without accurate risk-stratification to decide who to treat, and when, Vera's care remains reactive and suboptimal. Imagine how Vera’s experience would change if we could predict risks of specific events and take proactive action. | In healthcare, predictive models play a role not unlike that of blood tests, X-rays, or MRIs: They influence decisions about whether an intervention is appropriate. Whether a model is usefulness depends on the interplay between the model's output, the intervention it triggers, and the intervention’s benefits and harms. We are working on a set of efforts collectively referred to as the [[https://stanfordhealthcare.org/stanford-health-now/ceo-report/advancing-precision-health-takes-real-smarts.html|Stanford Medicine Program for Artificial Intelligence in Healthcare]], with the mission of bringing AI technologies to the clinic, safely, cost-effectively and ethically via the work of the [[https://dsatshc.stanford.edu/ | Data Science Team at Stanford Healthcare]] |
| |
| We are working on a set of efforts, which are collectively referred to as the [[https://stanfordhealthcare.org/stanford-health-now/ceo-report/advancing-precision-health-takes-real-smarts.html|Stanford Medicine Program for Artificial Intelligence in Healthcare]], with the mission of bringing AI technologies to the clinic, safely, cost-effectively and ethically. {{:shc_program_for_ai_in_healthcare.pdf|See brochure}}. The four key components are: | {{ :model-interplay.png?nolink& }} |
| |
| - **Implementation**: We partner with analytics and IT teams at Stanford Hospital to deploy predictive models in care delivery workflows. See our [[http://stanmed.stanford.edu/2018summer/artificial-intelligence-puts-humanity-health-care.html|first effort]] in improving palliative care, and recent [[https://www.statnews.com/2020/07/01/end-of-life-artificial-intelligence/|coverage in Statnews]]. | Our research stemmed from the effort [[http://stanmed.stanford.edu/2018summer/artificial-intelligence-puts-humanity-health-care.html|in improving palliative care]] using machine learning. [[https://jamanetwork.com/journals/jama/fullarticle/2748179?guestAccessKey=8cef0271-616d-4e8e-852a-0fddaa0e5101|Ensuring that machine learning models are clinically useful]] requires [[https://www.nature.com/articles/s41591-019-0651-8| estimating the hidden deployment cost of predictive models]] as well as quantifying the [[http://academic.oup.com/jamia/article/28/6/1149/6045012|impact of work capacity constraints]] on achievable benefit, estimating [[https://www.sciencedirect.com/science/article/pii/S1532046421001544|individualized utility]], and learning [[https://pubmed.ncbi.nlm.nih.gov/34350942/|optimal decision thresholds]]. Pre-empting [[https://www.nejm.org/doi/full/10.1056/NEJMp1714229|ethical challenges]] often requires keeping [[https://hai.stanford.edu/news/when-algorithmic-fairness-fixes-fail-case-keeping-humans-loop|humans in the loop]] and focus on examining the [[https://informatics.bmj.com/content/29/1/e100460|consequences of model-guided decision making]] in the presence of clinical care guidelines. |
| - **Rethinking Utility**: Typically, we evaluate models, quantify potential net-benefit, and realize some of it with real world operational constraints. Clinical utility of making a prediction, and taking actions depends on factors beyond model accuracy, such as lead time offered by the prediction, the existence of a mitigating action, the cost and ease of intervening, the logistics of the intervention, and incentives of the providers. Check out our viewpoints on [[https://jamanetwork.com/journals/jama/fullarticle/2748179?guestAccessKey=8cef0271-616d-4e8e-852a-0fddaa0e5101|making machine learning models clinical useful]], [[https://www.nature.com/articles/s41591-019-0651-8| estimating the hidden deployment cost of predictive models]], and [[https://innovations.bmj.com/content/6/2/45| bridging the implementation gap of machine learning in healthcare]]. | |
| - **Safety, ethics, and health system effects**: We map the multiple groups involved in executing a prediction-action pair and study their varying perspectives, positions, stakes, and commitments to pre-empt ethical challenges. We believe that the use of AI can lead to good decisions if we keep human intelligence in the loop. Read our perspective on [[https://www.nejm.org/doi/full/10.1056/NEJMp1714229|addressing ethical challenges]]. | [[https://www.tinyurl.com/hai-blogs | Blog posts at HAI]] summarize our work in easily accessible manner. |
| - **Training and Partnerships**: We partner with multiple groups to figure out “what would we do differently” if we had a prediction from a model, and to investigate the pros and cons of using AI to guide care. For example, we [[https://www.researchgate.net/publication/341829909_The_accuracy_vs_coverage_trade-off_in_patient-facing_diagnosis_models|examined the accuracy vs coverage trade off in patient facing diagnosis models]], and partnered with Google on efforts to enable [[https://www.nature.com/articles/s41746-018-0029-1| scalable and accurate deep learning with electronic health records]]. | |
| If done right, the adoption of efficacious prediction-action pairs can massively improve the ability of a health system to find patients at risk and act early. As part of this effort, we search for clinical situations where the application of risk-stratification and proactive action can provide cost-effective, health system level benefits. | |
| |
| ---- | ---- |
