| Both sides previous revision
Previous revision
|
Next revision
Both sides next revision
|
start [2020/02/23 10:11]
nigam |
start [2020/02/23 10:16]
nigam |
| We analyze multiple types of health data (EHR, Claims, Wearables, Weblogs, and Patient blogs), to answer clinical questions, generate insights, and build predictive models for the learning health system. [[:more_details|Read more ...]] | We analyze multiple types of health data (EHR, Claims, Wearables, Weblogs, and Patient blogs), to answer clinical questions, generate insights, and build predictive models for the learning health system. [[:more_details|Read more ...]] |
| |
| * We **answer clinical questions** to enable better medical decisions using EHR and Claims data, via a bedside consult service that enables the use of aggregate patient data at the [[http://stanmed.stanford.edu/2016winter/on-the-button.html|point of care]]. Check out our [[:greenbutton| Informatics Consult Service]] that puts this idea in action. | * We **answer clinical questions** to enable better medical decisions using EHR and Claims data, via a bedside consult service that enables the use of aggregate patient data at the [[http://stanmed.stanford.edu/2016winter/on-the-button.html|point of care]]. Check out our [[:greenbutton| Informatics Consult Service]] that puts this [[ https://shahlab.stanford.edu/greenbutton_idea | idea]] in action. |
| * We **make predictions** that allow taking mitigating actions, and also study the [[https://www.nejm.org/doi/full/10.1056/NEJMp1714229|ethical implications]] of using machine learning in clinical care. We have built models for predicting [[http://bmjopen.bmj.com/cgi/content/full/bmjopen-2016-011580?ijkey=oCxNIjOhCzOdmR8&keytype=ref| future increases in cost]], identifying [[http://www.ncbi.nlm.nih.gov/pubmed/26606167| slow healing wounds]], [[http://www.ncbi.nlm.nih.gov/pubmed/24988898|missed diagnoses of depression]] and for [[http://stanmed.stanford.edu/2018summer/artificial-intelligence-puts-humanity-health-care.html| improving palliative care]]. Check out our [[:paihc| Program for AI in Healthcare]] | * We **make predictions** that allow taking mitigating actions, and also study the [[https://www.nejm.org/doi/full/10.1056/NEJMp1714229|ethical implications]] of using machine learning in clinical care. We have built models for predicting [[http://bmjopen.bmj.com/cgi/content/full/bmjopen-2016-011580?ijkey=oCxNIjOhCzOdmR8&keytype=ref| future increases in cost]], identifying [[http://www.ncbi.nlm.nih.gov/pubmed/26606167| slow healing wounds]], [[http://www.ncbi.nlm.nih.gov/pubmed/24988898|missed diagnoses of depression]] and for [[http://stanmed.stanford.edu/2018summer/artificial-intelligence-puts-humanity-health-care.html| improving palliative care]]. Check out our [[:paihc| Program for AI in Healthcare]] |
| * We develop methods to analyze multiple datatypes for **generating insights**. Such as, learning effective treatment pathways in Type 2 Diabetes with [[http://www.ohdsi.org|OHDSI]] using [[https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2698083| claims data from multiple countries]]. Learning reference intervals of laboratory tests from a [[http://www.ncbi.nlm.nih.gov/pubmed/26707631|clinical data warehouse]]. Monitoring Point-of-Care glucose meters using [[http://www.ncbi.nlm.nih.gov/pubmed/26988586|coincident testing]] with central laboratory measurements. Detecting skin adverse reactions by analyzing content in a [[https://jamanetwork.com/journals/jamaoncology/fullarticle/2673831| health social network]]. Finding drug adverse events, and drug-drug interactions using [[http://www.ncbi.nlm.nih.gov/pubmed/23571773| using clinical notes]]. Mining user [[https://www.ncbi.nlm.nih.gov/pubmed/27655225| search logs]] to predict health utilization, and analyzing [[https://www.ncbi.nlm.nih.gov/pubmed/26293444| information seeking behavior]] of health professionals. Inferring physical function from [[https://www.ncbi.nlm.nih.gov/pubmed/30394876| wearables data]], and personalizing ICU [[https://www.ncbi.nlm.nih.gov/pubmed/29218906| alarm thresholds]]. Assessing [[https://www.ncbi.nlm.nih.gov/pubmed/29557976| impact of informatics tools]] and databases, and profiling [[https://jamanetwork.com/journals/jama/fullarticle/2595514| research on gun violence]]. | * We develop methods to analyze multiple datatypes for **generating insights**. Such as, learning effective treatment pathways in Type 2 Diabetes with [[http://www.ohdsi.org|OHDSI]] using [[https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2698083| claims data from multiple countries]]. Learning reference intervals of laboratory tests from a [[http://www.ncbi.nlm.nih.gov/pubmed/26707631|clinical data warehouse]]. Monitoring Point-of-Care glucose meters using [[http://www.ncbi.nlm.nih.gov/pubmed/26988586|coincident testing]] with central laboratory measurements. Detecting skin adverse reactions by analyzing content in a [[https://jamanetwork.com/journals/jamaoncology/fullarticle/2673831| health social network]]. Finding drug adverse events, and drug-drug interactions using [[http://www.ncbi.nlm.nih.gov/pubmed/23571773| using clinical notes]]. Mining user [[https://www.ncbi.nlm.nih.gov/pubmed/27655225| search logs]] to predict health utilization, and analyzing [[https://www.ncbi.nlm.nih.gov/pubmed/26293444| information seeking behavior]] of health professionals. Inferring physical function from [[https://www.ncbi.nlm.nih.gov/pubmed/30394876| wearables data]], and personalizing ICU [[https://www.ncbi.nlm.nih.gov/pubmed/29218906| alarm thresholds]]. Assessing [[https://www.ncbi.nlm.nih.gov/pubmed/29557976| impact of informatics tools]] and databases, and profiling [[https://jamanetwork.com/journals/jama/fullarticle/2595514| research on gun violence]]. |
