{"id":53599,"date":"2018-08-15T08:41:23","date_gmt":"2018-08-15T12:41:23","guid":{"rendered":"http:\/\/webapp2.wright.edu\/web1\/newsroom\/?p=53599"},"modified":"2018-08-15T08:41:23","modified_gmt":"2018-08-15T12:41:23","slug":"venturebeat-wright-state-researchers-part-of-team-using-use-ai-to-match-patients-with-primary-care-doctors","status":"publish","type":"post","link":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/2018\/08\/15\/venturebeat-wright-state-researchers-part-of-team-using-use-ai-to-match-patients-with-primary-care-doctors\/","title":{"rendered":"VentureBeat: Wright State researchers part of team using use AI to match patients with primary care doctors"},"content":{"rendered":"<p><em><strong>Excerpt<\/strong><\/em><\/p>\n<div id=\"attachment_53602\" style=\"width: 470px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-53602\" class=\"size-large wp-image-53602\" src=\"http:\/\/webapp2.wright.edu\/web1\/newsroom\/files\/2018\/08\/heal-app-photo-508x324.jpg\" alt=\"\" width=\"460\" height=\"293\" \/><p id=\"caption-attachment-53602\" class=\"wp-caption-text\">Above: A doctor making a house call, thanks to the Heal app.<br \/>Image Credit: Heal<\/p><\/div>\n<p>Finding a primary care doctor is simpler than it used to be, thanks to on-demand services like ZocDoc, SimplyBook, and Doodle. But matching up with a clinician who\u2019s compatible with your (or your family\u2019s) personality is another story.<\/p>\n<p>Researchers at Wright State University, University of California, Davis, and Universidade Nova de Lisboa think artificial intelligence (AI) has a role to play. In a new paper (\u201c<a href=\"https:\/\/arxiv.org\/pdf\/1808.03265.pdf\">A Hybrid Recommender System for Patient-Doctor Matchmaking in Primary Care<\/a>\u201c), they\u00a0propose a recommender system they claim makes primary care providers \u201cmore directly accessible\u201d by improving patient-doctor matches.<\/p>\n<p>\u201cGiven that trust in patient-doctor relationships plays a central role in improving patients\u2019 health outcomes and satisfaction with their care, it would be preferable to match patients with family doctors that they are willing to consult with high trust,\u201d they wrote. \u201c[Our\u00a0approach] generate[s] personalized doctor recommendations for each patient that they may trust the most.\u201d<\/p>\n<p>In designing the algorithm, the team considered factors that have been shown to affect patients\u2019 trust and confidence in primary care doctors \u2014 particularly demographic characteristics and \u201cpsychosocial\u201d elements such as a \u201csense of being taken seriously\u201d and \u201cbeing involved in decisions.\u201d<\/p>\n<p>They then sourced data from a private health care provider and clinical network in Portugal that serves over 2.5 million patients a year. With a database of 42 million interactions between patients and doctors (\u201cinteractions\u201d defined here as episodes that included a set of services provided to treat a clinical condition) between 2012 and 2017, plus basic demographic information (gender, age, residence, etc.), doctor registration data, and a complementary dataset describing hospital inpatient procedures in hand, they set about training the system.<\/p>\n<p>It didn\u2019t treat all patients the same. Instead, it matched new patients only by their demographic profile, while existing patients who\u2019d been to visit clinicians were subjected to a modified \u201chybrid\u201d recommendation that took into account metadata such as interactions, demographics, and behavior.<\/p>\n<p>Because a system designed to perform matchmaking across different use cases wouldn\u2019t scale particularly well, the team trained it to learn \u201clatent representations\u201d \u2014 combinations of their characteristics \u2014 for patients and doctors from interactions. This allowed it to infer the preferences of new patients from similar patients.<\/p>\n<p>The resulting AI was able to match over 80 percent of patients with relevant primary care doctors compared to the baseline\u2019s 37 percent. In the future, the researchers plan to deploy it into a digital health system to gather patients\u2019 preference and evaluate the recommendations in controlled trials.<\/p>\n<p>\u201cContinuity of care and familiarity helps doctors better understand their patients\u2019 needs and helps patients act preventatively and live healthier lives, thus reinforcing the strength of the relationship,\u201d they wrote. \u201cThe underlying logic is simple: patients who trust their doctors are more likely to follow their advice and develop long-lasting relationships with them.\u201d<\/p>\n<p>View the original story at <a href=\"https:\/\/venturebeat.com\/2018\/08\/14\/researchers-use-ai-to-match-patients-with-primary-care-doctors\/\">venturebeat.com<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Excerpt Finding a primary care doctor is simpler than it used to be, thanks to on-demand services like ZocDoc, SimplyBook, and Doodle. But matching up with a clinician who\u2019s compatible with your (or your family\u2019s) personality is another story. Researchers &hellip; <a href=\"https:\/\/webapp2.wright.edu\/web1\/newsroom\/2018\/08\/15\/venturebeat-wright-state-researchers-part-of-team-using-use-ai-to-match-patients-with-primary-care-doctors\/\" class=\"morelink\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":21,"featured_media":53602,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[730],"tags":[],"class_list":["post-53599","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-wright-state-in-the-news"],"_links":{"self":[{"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/posts\/53599","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/users\/21"}],"replies":[{"embeddable":true,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/comments?post=53599"}],"version-history":[{"count":2,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/posts\/53599\/revisions"}],"predecessor-version":[{"id":53603,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/posts\/53599\/revisions\/53603"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/media\/53602"}],"wp:attachment":[{"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/media?parent=53599"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/categories?post=53599"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/webapp2.wright.edu\/web1\/newsroom\/wp-json\/wp\/v2\/tags?post=53599"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}