User Tools

Site Tools


aihc

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
aihc [2021/10/13 16:35]
nigam
aihc [2021/10/13 17:22] (current)
nigam
Line 1: Line 1:
 ====== Stanford Medicine Program for Artificial Intelligence in Healthcare ====== ====== Stanford Medicine Program for Artificial Intelligence in Healthcare ======
  
-Consider the case of Vera, 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 pneumoniaHer 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 osteoporosisIdeally, treatment decisions ​for Vera are guided by risk stratification to decide if to treatand evidence based selection ​of how to treat. Howeverwithout accurate risk-stratification to decide who to treat, and when, Vera's care remains reactive ​and suboptimalImagine how Vera’s experience would change if we could predict risks of specific events and take proactive action.+We are working on 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 clinicsafely, cost-effectively ​and ethically{{:​shc_program_for_ai_in_healthcare.pdf|See brochure}}. The four key components are:
  
-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: +  ​- **Implementation**:​ We partner with the Technology ​and Digital Solutions team 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|effort]] in improving palliative care and its [[https://​www.statnews.com/​2020/​07/​01/​end-of-life-artificial-intelligence/​|coverage in Statnews]]. 
- +  - **Ensuring that models are useful**: ​The 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 making the intervention. 
-  ​- **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 careand recent ​[[https://​www.statnews.com/​2020/​07/​01/​end-of-life-artificial-intelligence/​|coverage in Statnews]]. +      - Check out our ideas 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]], [[https://​innovations.bmj.com/​content/​6/​2/​45|bridging the implementation gap of machine learning ​in healthcare]],​ and developing a [[https://​www.nature.com/​articles/​s41746-020-00318-y|delivery science for AI in healthcare]]. 
-  - **Ensuring that models are useful**: ​Clinical ​utility of making a predictionand 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 making the intervention. +      - Read about our framework for quantifying the [[http://​academic.oup.com/​jamia/​article/​28/​6/​1149/​6045012|impact of work capacity constraints]] on achieved benefit, estimating [[https://​www.sciencedirect.com/​science/​article/​pii/​S1532046421001544|individualized utility]], and learning [[https://​pubmed.ncbi.nlm.nih.gov/​34350942/​|optimal decision thresholds]] from aggregate clinician behavior. 
-      - 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 taking action in response to a prediction and study their varying perspectives,​ positions, stakes, and commitments to pre-empt ethical challenges. Read our perspective on [[https://​www.nejm.org/​doi/​full/​10.1056/​NEJMp1714229|addressing ethical challenges]]. We believe that the use of AI can lead to good decisions if we keep [[https://​hai.stanford.edu/​news/​when-algorithmic-fairness-fixes-fail-case-keeping-humans-loop|human intelligence in the loop]]. 
-      - +  - **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]]. Stanford students, check out the [[https://​stanfordmlgroup.github.io/​programs/​aihc-bootcamp/​|AI for Healthcare Bootcamp]].
-  - **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]]. +
-  - **Training and Partnerships**:​ We partner with multiple groups to figure out “what would we do differently” if we had a prediction from a modeland 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. 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.
  
aihc.1634168146.txt.gz · Last modified: 2021/10/13 16:35 by nigam