{"692594":{"#nid":"692594","#data":{"type":"news","title":"AI Tool Aims to Catch Critically Ill Children ","body":[{"value":"\u003Cp\u003EA child can be in the hospital and seemingly getting better. Then, suddenly, everything changes.\u003C\/p\u003E\u003Cp\u003EOne moment they\u0027re playing games or watching television. The next, they experience breathing failure, shock, or neurological decline. If the warning signs aren\u0027t recognized early enough, the child may require emergency transfer to the intensive care unit (ICU), where interventions can include breathing tubes, blood pressure medications, and other lifesaving measures.\u003C\/p\u003E\u003Cp\u003EThe phenomenon is called \u201cemergent deterioration.\u201d\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0022Kids will look fine, and then all of a sudden they\u0027ll fall off a cliff and rapidly deteriorate,\u0022 said\u0026nbsp;\u003Ca href=\u0022https:\/\/www.choa.org\/doctors\/mark-vu-mai\u0022\u003EDr. Mark Mai,\u003C\/a\u003E a pediatric intensivist at Children\u2019s Healthcare of Atlanta, who cares for critically ill children in the ICU. \u0022When those kids go to the ICU and need emergency interventions, they have a much higher rate of death than kids we bring up to the ICU in a controlled fashion.\u0022\u003C\/p\u003E\u003Cp\u003ETo help clinicians identify those high-risk patients sooner, researchers at Georgia Tech are partnering with Children\u0027s clinicians and technology teams to create an artificial intelligence-powered warning system.\u0026nbsp;Known as\u0026nbsp;Algorithm for Counteracting the Clinical Onset of Rapid Deterioration (ACCORD), the three-year project is one of the\u0026nbsp;first funded projects focused on a software solution\u0026nbsp;by the\u0026nbsp;\u003Ca href=\u0022https:\/\/ptc.gatech.edu\/\u0022\u003EChildren\u2019s Healthcare of Atlanta Pediatric Technology Center at Georgia Tech\u0026nbsp;\u003C\/a\u003E(PTC).\u0026nbsp;Project teams are working simultaneously on model development, app design, and user testing. And, unlike many healthcare AI projects that remain confined to research papers, ACCORD is being designed from the beginning for use in a real hospital. The ultimate goal is to help clinicians intervene before a child reaches a life-threatening emergency.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETeaching AI to Spot Trouble Earlier\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EToday, clinicians rely on an early warning score that combines measurements such as heart rate, blood pressure, and breathing rate into a single risk assessment. While helpful, the approach simplifies a complex clinical picture.\u003C\/p\u003E\u003Cp\u003E\u0022The current system is a pretty basic rubric that sums up all the data points and then decides whether they are high-risk or low-risk, but from the data science and machine learning perspective it\u0027s not optimal,\u0022 said\u0026nbsp;\u003Ca href=\u0022https:\/\/people.research.gatech.edu\/kai-wang\u0022\u003EKai Wang\u003C\/a\u003E, an assistant professor in the\u0026nbsp;\u003Ca href=\u0022https:\/\/cse.gatech.edu\/\u0022\u003ESchool of Computational Science and Engineering\u003C\/a\u003E and project co-principal investigator with Mai.\u003C\/p\u003E\u003Cp\u003ERather than evaluating patients through a fixed scoring system, ACCORD\u0027s AI model analyzes dozens of data streams, including vital signs, laboratory results, and clinical observations. The goal is to uncover subtle patterns that may signal deterioration hours before the physical warning signs become obvious to clinicians.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0022We want to build a more sophisticated algorithm that can look into vitals, blood pressure, heart rate, and other measures to provide a more granular forecast of risk,\u0022 Wang said.\u003C\/p\u003E\u003Cp\u003EBuilding that capability into an algorithm requires making sense of one of healthcare\u0027s biggest challenges: messy, incomplete, and constantly changing data. To develop the model, researchers are training and testing it using information pulled from Children\u0027s electronic health records. Some information, such as vital signs, is collected continuously. Other information may be recorded less frequently or at irregular intervals, such as nursing observations.\u003C\/p\u003E\u003Cp\u003E\u0022That is both the most challenging and the most exciting part of this project,\u0022 said Himadri Pandey, a machine learning Ph.D. student working on ACCORD. \u0022We have to consider the realities of a healthcare setting. Data may be incomplete or delayed, staffing and resources may change, and any recommendation must be understandable and usable by clinicians.\u0022\u003C\/p\u003E\u003Cp\u003E\u0022The goal is not simply to build a model that works mathematically,\u0022 she added. \u0022It\u0027s to build something that could genuinely support decision-making in a hospital.\u0022\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBuilding Technology Nurses Will Use\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EFor ACCORD to improve patient outcomes, the technology must fit naturally into clinicians\u0027 daily workflow. Most nurses care for multiple patients simultaneously and cannot continuously monitor a single child. Because episodes of emergent deterioration are relatively rare in a full day of care, opportunities to gain experience recognizing the earliest warning signs can be limited. Acknowledging that reality, project leaders involved frontline nurses from the beginning.\u003C\/p\u003E\u003Cp\u003E\u0022We went straight to the nurses and said, \u0027This is what we\u0027re trying to do. You tell us what would make your job easier, how you need the flow, what it needs to look like, and we will build according to that,\u201d said Christina Roberts, program manager for PTC and the Health Informatics Core at Children\u2019s. \u0022We brought them into the process very early and gave them a say in the development, so they know exactly what to expect when the tool comes to the floor.\u0022\u003C\/p\u003E\u003Cp\u003EThe team plans to integrate ACCORD directly into the Children\u2019s electronic health record system, where clinicians already access patient information. The application will combine vital signs, laboratory results, and other clinical data into a single dashboard that can automatically flag patients at elevated risk of deterioration.\u003C\/p\u003E\u003Cp\u003EResearchers and clinicians continue to meet regularly as the platform evolves.\u003C\/p\u003E\u003Cp\u003E\u0022How do we distinguish what the algorithm finds important and what is just always there?\u0022 said Dr.\u0026nbsp;\u003Ca href=\u0022https:\/\/www.choa.org\/doctors\/claire-stokes\u0022\u003EClaire Stokes,\u003C\/a\u003E a pediatric hematologist and oncologist with the Aflac Cancer and Blood Disorders Center at Children\u2019s, who is involved in the project. \u0022Because a clinician probably always wants to see the vital signs, even if they\u0027re not alert levels, for example.\u0022\u003C\/p\u003E\u003Cp\u003EThose conversations help ensure that the system provides useful information without overwhelming clinicians with additional data or alerts. The team hopes to begin testing the system in clinical settings by 2027 before broader deployment. For the researchers working on ACCORD, however, the project\u0027s success will ultimately be measured by the patients it helps.\u003C\/p\u003E\u003Cp\u003E\u0022I know that one research project cannot solve every problem in healthcare,\u0022 said Pandey, who has experienced the hospitalization of a close family member. \u0022But being able to contribute, even in a small way, allows me to replace some of that earlier helplessness with purpose.\u0022\u003C\/p\u003E\u003Cp\u003EIf successful, ACCORD could give clinicians something they rarely have when a child begins to decline \u2014 time.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003EGeorgia Tech and Children\u0027s Healthcare of Atlanta are developing a real-time warning system to help clinicians spot a child\u2019s emergent deterioration before it becomes a life-threatening emergency.\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Georgia Tech and Children\u0027s Healthcare of Atlanta are developing a real-time warning system to help clinicians spot a child\u2019s emergent deterioration before it becomes a life-threatening emergency."}],"uid":"34541","created_gmt":"2026-09-15 15:55:05","changed_gmt":"2026-09-15 16:07:10","author":"Tess Malone","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-15T00:00:00-04:00","iso_date":"2026-09-15T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681150":{"id":"681150","type":"image","title":"2026_COMM_EC_AMBH_Emergency_295.jpg","body":"\u003Cp\u003E\u003Cem\u003EPediatric healthcare professional reviewing electronic health record information at Children\u2019s Healthcare of Atlanta Arthur M. Blank Hospital. (Photo courtesy of Children\u0027s Healthcare of Atlanta)\u003C\/em\u003E\u003C\/p\u003E","created":"1789487781","gmt_created":"2026-09-15 15:56:21","changed":"1789487781","gmt_changed":"2026-09-15 15:56:21","alt":"Pediatric healthcare professional reviewing electronic health record information at Children\u2019s Healthcare of Atlanta Arthur M. Blank Hospital.","file":{"fid":"265512","name":"2026_COMM_EC_AMBH_Emergency_295.jpg","image_path":"\/sites\/default\/files\/2026\/09\/15\/2026_COMM_EC_AMBH_Emergency_295.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/15\/2026_COMM_EC_AMBH_Emergency_295.jpg","mime":"image\/jpeg","size":8272359,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/15\/2026_COMM_EC_AMBH_Emergency_295.jpg?itok=gB8rxWmG"}}},"media_ids":["681150"],"groups":[{"id":"1214","name":"News Room"},{"id":"1188","name":"Research Horizons"}],"categories":[],"keywords":[{"id":"187915","name":"go-researchnews"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003ETess Malone, Senior Research Writer\/Editor\u003C\/p\u003E\u003Cp\u003Etess.malone@gatech.edu\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}