One of these decision support tools (SCARS-1), now published, is downloadable<\/a> and free of charge. However, the interpretation of the results from the algorithm needs people with the right skills. AI-based decision support is expanding strongly in many areas of health care, and extensive discussions are underway on how care services and patients alike can benefit most from it.<\/p>\n\n\n\n The app accesses data from the Swedish Cardiopulmonary Resuscitation Register on tens of thousands of patient cases. The University of Gothenburg researchers have used an advanced form of machine learning to teach clinical prediction models to recognize various factors that have affected previous outcomes. The algorithms take into account numerous factors relating, for example, to the cardiac arrest, treatment provided, previous ill-health, medication, and socioeconomic status.<\/p>\n\n\n It will be a few years before official recommendations for cardiac arrest are likely to include AI-based decision support, but doctors are free to use these prediction models and other new, evidence-based methods. Araz Rawshani, a researcher at the University\u2019s Sahlgrenska Academy and resident physician in cardiology at Sahlgrenska University Hospital, heads the research group working on the AI model.<\/p>\n\n\n\n \u201cMy colleagues and I who tested the tool see great potential in its use in our clinical everyday life. Often the answer from the decision support means that the doctor is strengthened in an opinion he has already arrived at. It helps us not to expose patients to painful care without benefit, while at the same time it saves on healthcare resources,\u201d Rawshani says.<\/p>\n\n\n\n He emphasizes, nevertheless, that the decision support is still at a research stage and not yet among the hospital’s guidelines. However, it can be useful in making a survival calculation.<\/p>\n\n\n\n To date, the research group has published two decision support tools. One clinical prediction model, known as SCARS-1, is presented in The Lancet\u2019s eBioMedicine journal. This model indicates whether a new patient case resembles other, previous cases where, 30 days after their cardiac arrest, patients had survived or died. Fredrik Hessulf, a doctoral student at Sahlgrenska Academy, University of Gothenburg, and anesthesiologist, created this support.<\/p>\n\n\n\n \u201cThis decision support is one of several pieces in a big puzzle: the doctor\u2019s overall assessment of a patient. We have many different factors to consider in deciding whether to go ahead with cardiopulmonary resuscitation. It\u2019s a highly demanding treatment that we should give only to patients who will benefit from it and be able, after their hospital stay, to lead a life of value to themselves,\u201d Hessulf says.<\/p>\n\n\n\n This form of support is based on 393 factors affecting patients\u2019 chances of surviving their cardiac arrest for 30 days after the event. The model\u2019s high accuracy depends on the huge number of patient cases (roughly 55,000) on which the algorithm is based. Also, by the fact that ten of the nearly 400 factors have an heavy impact on survival. By far, the most important factor was whether the heart regained a viable cardiac rhythm again after the patient\u2019s admission to the emergency department.<\/p>\n\n\n\n The second decision support tool appeared in the journal Resuscitation. This tool is based on data from patients who survived their out-of-hospital cardiac arrest until they were discharged from hospital. The predictive models are based on 886 factors in 5098 patient cases from the Swedish Cardiopulmonary Resuscitation Register. This tool partly aims at helping doctors identify which patients are at risk of another cardiac arrest or death within a year of discharge from hospital following their cardiac arrest. It also aims to highlight which factors are important for long-term survival after cardiac arrest. An aspect of the subject area, this last one, currently in need of further exploration.<\/p>\n\n\n\n \u201cThe accuracy of this tool is reasonably good. It can predict with about 70 percent reliability whether the patient will die, or will have had another cardiac arrest, within a year. Like Fredrik\u2019s tool, this one has the advantage that just a few factors can predict outcome almost as well as the model with several hundred variables,\u201d says Gustaf Hells\u00e9n, the research doctor who developed this decision support tool.<\/p>\n\n\n\n \u201cWe hope,\u201d he continues, \u201cto succeed in developing this prediction model, so as to enhance its precision. Today, it can already serve as support for doctors in identifying factors with an important bearing on survival among cardiac arrest patients who are to be discharged from hospital.\u201d <\/p>\n\n\n\n Currently, the SCARS-1 tool is available to use as an online app. SCARS-2 will launch shortly. During 2023, publication of SCARS-3 (for in-hospital cardiac arrest) is in plans.<\/p>\n","protected":false},"author":2583,"featured_media":514011,"template":"views\/single-selected.blade.php","meta":{"_acf_changed":false,"advgb_blocks_editor_width":"","advgb_blocks_columns_visual_guide":""},"categories":[34665],"tags":[10373,129549,34100,4647,57454],"location":[54353],"internal_archives":[],"class_list":["post-437071","selected","type-selected","status-publish","has-post-thumbnail","hentry","category-health","tag-ai","tag-cardiac-arrest-3","tag-doctors","tag-health-en","tag-university-of-gothenburg","location-sweden"],"blocksy_meta":[],"acf":[],"featured_img":"https:\/\/ioplus.nl\/archive\/wp-content\/uploads\/2022\/04\/P443NzXV-csm_20211215_Horyzn_Drone_AH_667982_ac75692fd2.jpg","coauthors":[],"author_meta":{"author_link":"https:\/\/ioplus.nl\/archive\/author\/francesco-morelli\/","display_name":"Francesco Morelli"},"relative_dates":{"created":"Posted 3 years ago","modified":"Updated 3 years ago"},"absolute_dates":{"created":"Posted on February 15, 2023","modified":"Updated on February 15, 2023"},"absolute_dates_time":{"created":"Posted on February 15, 2023 12:45 pm","modified":"Updated on February 15, 2023 12:45 pm"},"featured_img_caption":"","tax_additional":{"category":{"linked":["Health<\/a>"],"unlinked":["Health<\/span>"],"slug":"category","name":"Categories"},"post_tag":{"linked":["AI<\/a>","cardiac arrest<\/a>","doctors<\/a>","health<\/a>","University of Gothenburg<\/a>"],"unlinked":["AI<\/span>","cardiac arrest<\/span>","doctors<\/span>","health<\/span>","University of Gothenburg<\/span>"],"slug":"post_tag","name":"Tags"},"language":{"linked":["EN<\/a>"],"unlinked":["EN<\/span>"],"slug":"language","name":"Tags"},"post_translations":{"linked":[],"unlinked":[],"slug":"post_translations","name":""},"location":{"linked":["Sweden<\/a>"],"unlinked":["Sweden<\/span>"],"slug":"location","name":"Locations"},"internal_archives":{"linked":[],"unlinked":[],"slug":"internal_archives","name":"Internal Archives"}},"series_order":"","_links":{"self":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/selected\/437071","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/selected"}],"about":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/types\/selected"}],"author":[{"embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/users\/2583"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/media\/514011"}],"wp:attachment":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/media?parent=437071"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/categories?post=437071"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/tags?post=437071"},{"taxonomy":"location","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/location?post=437071"},{"taxonomy":"internal_archives","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/internal_archives?post=437071"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}![\"\"](\"https:\/\/ioplus.nl\/archive\/wp-content\/uploads\/2022\/04\/P443NzXV-csm_20211215_Horyzn_Drone_AH_667982_ac75692fd2-1.jpg\")
<\/div><\/div>Evidence-based methods<\/h2>\n\n\n\n
High accuracy and reliability<\/h2>\n\n\n\n
The model\u2019s accuracy is unusually high. Based on the ten most significant factors alone, the model has a sensitivity of 95 percent and a specificity of 89 percent. The \u201cAUC-ROC value\u201d (ROC being the receiver operating characteristic curve for the model and AUC the area under the ROC curve) for this model is 0.97. The highest possible AUC-ROC value is 1.0 and the threshold for a clinically relevant model is 0.7.<\/p>\n\n\nOnly “one piece of the puzzle”<\/h2>\n\n\n\n
Further risk of cardiac arrest<\/h2>\n\n\n\n