@article{Bennett2012a,
abstract = {Objectives Electronic health records (EHRs) are only a first step in capturing and utilizing health-related data—the challenge is turning that data into useful information. Furthermore, EHRs are increasingly likely to include data relating to patient outcomes, functionality such as clinical decision support, and genetic information as well, and, as such, can be seen as repositories of increasingly valuable information about patients' health conditions and responses to treatment over time. Methods We describe a case study of 423 patients treated by Centerstone within Tennessee and Indiana in which we utilized electronic health record data to generate predictive algorithms of individual patient treatment response. Multiple models were constructed using predictor variables derived from clinical, financial and geographic data. Results For the 423 patients, 101 deteriorated, 223 improved and in 99 there was no change in clinical condition. Based on modeling of various clinical indicators at baseline, the highest accuracy in predicting individual patient response ranged from 70% to 72% within the models tested. In terms of individual predictors, the Centerstone Assessment of Recovery Level—Adult (CARLA) baseline score was most significant in predicting outcome over time (odds ratio 4.1+2.27). Other variables with consistently significant impact on outcome included payer, diagnostic category, location and provision of case management services. Conclusions This approach represents a promising avenue toward reducing the current gap between research and practice across healthcare, developing data-driven clinical decision support based on real-world populations, and serving as a component of embedded clinical artificial intelligences that “learn” over time.},
author = {Bennett, Casey C and Doub, Thomas W and Selove, Rebecca},
doi = {https://doi.org/10.1016/j.hlpt.2012.03.001},
issn = {2211-8837},
journal = {Health Policy and Technology},
number = {2},
pages = {105--114},
title = {{EHRs connect research and practice: Where predictive modeling, artificial intelligence, and clinical decision support intersect}},
url = {http://www.sciencedirect.com/science/article/pii/S221188371200038X},
volume = {1},
year = {2012}
}

{"_id":"bSmRzyuzFw6npy89i","bibbaseid":"bennett-doub-selove-ehrsconnectresearchandpracticewherepredictivemodelingartificialintelligenceandclinicaldecisionsupportintersect-2012","author_short":["Bennett, C. C","Doub, T. W","Selove, R."],"bibdata":{"bibtype":"article","type":"article","abstract":"Objectives Electronic health records (EHRs) are only a first step in capturing and utilizing health-related data—the challenge is turning that data into useful information. Furthermore, EHRs are increasingly likely to include data relating to patient outcomes, functionality such as clinical decision support, and genetic information as well, and, as such, can be seen as repositories of increasingly valuable information about patients' health conditions and responses to treatment over time. Methods We describe a case study of 423 patients treated by Centerstone within Tennessee and Indiana in which we utilized electronic health record data to generate predictive algorithms of individual patient treatment response. Multiple models were constructed using predictor variables derived from clinical, financial and geographic data. Results For the 423 patients, 101 deteriorated, 223 improved and in 99 there was no change in clinical condition. Based on modeling of various clinical indicators at baseline, the highest accuracy in predicting individual patient response ranged from 70% to 72% within the models tested. In terms of individual predictors, the Centerstone Assessment of Recovery Level—Adult (CARLA) baseline score was most significant in predicting outcome over time (odds ratio 4.1+2.27). Other variables with consistently significant impact on outcome included payer, diagnostic category, location and provision of case management services. Conclusions This approach represents a promising avenue toward reducing the current gap between research and practice across healthcare, developing data-driven clinical decision support based on real-world populations, and serving as a component of embedded clinical artificial intelligences that “learn” over time.","author":[{"propositions":[],"lastnames":["Bennett"],"firstnames":["Casey","C"],"suffixes":[]},{"propositions":[],"lastnames":["Doub"],"firstnames":["Thomas","W"],"suffixes":[]},{"propositions":[],"lastnames":["Selove"],"firstnames":["Rebecca"],"suffixes":[]}],"doi":"https://doi.org/10.1016/j.hlpt.2012.03.001","issn":"2211-8837","journal":"Health Policy and Technology","number":"2","pages":"105–114","title":"EHRs connect research and practice: Where predictive modeling, artificial intelligence, and clinical decision support intersect","url":"http://www.sciencedirect.com/science/article/pii/S221188371200038X","volume":"1","year":"2012","bibtex":"@article{Bennett2012a,\nabstract = {Objectives Electronic health records (EHRs) are only a first step in capturing and utilizing health-related data—the challenge is turning that data into useful information. Furthermore, EHRs are increasingly likely to include data relating to patient outcomes, functionality such as clinical decision support, and genetic information as well, and, as such, can be seen as repositories of increasingly valuable information about patients' health conditions and responses to treatment over time. Methods We describe a case study of 423 patients treated by Centerstone within Tennessee and Indiana in which we utilized electronic health record data to generate predictive algorithms of individual patient treatment response. Multiple models were constructed using predictor variables derived from clinical, financial and geographic data. Results For the 423 patients, 101 deteriorated, 223 improved and in 99 there was no change in clinical condition. Based on modeling of various clinical indicators at baseline, the highest accuracy in predicting individual patient response ranged from 70% to 72% within the models tested. In terms of individual predictors, the Centerstone Assessment of Recovery Level—Adult (CARLA) baseline score was most significant in predicting outcome over time (odds ratio 4.1+2.27). Other variables with consistently significant impact on outcome included payer, diagnostic category, location and provision of case management services. Conclusions This approach represents a promising avenue toward reducing the current gap between research and practice across healthcare, developing data-driven clinical decision support based on real-world populations, and serving as a component of embedded clinical artificial intelligences that “learn” over time.},\nauthor = {Bennett, Casey C and Doub, Thomas W and Selove, Rebecca},\ndoi = {https://doi.org/10.1016/j.hlpt.2012.03.001},\nissn = {2211-8837},\njournal = {Health Policy and Technology},\nnumber = {2},\npages = {105--114},\ntitle = {{EHRs connect research and practice: Where predictive modeling, artificial intelligence, and clinical decision support intersect}},\nurl = {http://www.sciencedirect.com/science/article/pii/S221188371200038X},\nvolume = {1},\nyear = {2012}\n}\n","author_short":["Bennett, C. C","Doub, T. W","Selove, R."],"key":"Bennett2012a","id":"Bennett2012a","bibbaseid":"bennett-doub-selove-ehrsconnectresearchandpracticewherepredictivemodelingartificialintelligenceandclinicaldecisionsupportintersect-2012","role":"author","urls":{"Paper":"http://www.sciencedirect.com/science/article/pii/S221188371200038X"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://leandrosweb.com/library.bib","dataSources":["vRJd4wNg9HpoZSMHD"],"keywords":[],"search_terms":["ehrs","connect","research","practice","predictive","modeling","artificial","intelligence","clinical","decision","support","intersect","bennett","doub","selove"],"title":"EHRs connect research and practice: Where predictive modeling, artificial intelligence, and clinical decision support intersect","year":2012}