Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase
Abstract Predicting poor neurological outcomes after resuscitation is important for planning treatment strategies. We constructed an explainable artificial intelligence-based prognostic model using head computed tomography (CT) scans taken immediately within 3 h of resuscitation from cardiac arrest...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-32899-5 |
| _version_ | 1797850120914468864 |
|---|---|
| author | Yasuyuki Kawai Yohei Kogeichi Koji Yamamoto Keita Miyazaki Hideki Asai Hidetada Fukushima |
| author_facet | Yasuyuki Kawai Yohei Kogeichi Koji Yamamoto Keita Miyazaki Hideki Asai Hidetada Fukushima |
| author_sort | Yasuyuki Kawai |
| collection | DOAJ |
| description | Abstract Predicting poor neurological outcomes after resuscitation is important for planning treatment strategies. We constructed an explainable artificial intelligence-based prognostic model using head computed tomography (CT) scans taken immediately within 3 h of resuscitation from cardiac arrest and compared its predictive accuracy with that of previous methods using gray-to-white matter ratio (GWR). We included 321 consecutive patients admitted to our institution after resuscitation for out-of-hospital cardiopulmonary arrest with circulation resumption over 6 years. A machine learning model using head CT images with transfer learning was used to predict the neurological outcomes at 1 month. These predictions were compared with the predictions of GWR for multiple regions of interest in head CT using receiver operating characteristic (ROC)-area under curve (AUC) and precision recall (PR)-AUC. The regions of focus were visualized using a heatmap. Both methods had similar ROC-AUCs, but the machine learning model had a higher PR-AUC (0.73 vs. 0.58). The machine learning-focused area of interest for classification was the boundary between gray and white matter, which overlapped with the area of focus when diagnosing hypoxic– ischemic brain injury. The machine learning model for predicting poor outcomes had superior accuracy to conventional methods and could help optimize treatment. |
| first_indexed | 2024-04-09T18:56:19Z |
| format | Article |
| id | doaj.art-b4c9e3b0d8be46e3a665f1f7ea2b7aeb |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T18:56:19Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-b4c9e3b0d8be46e3a665f1f7ea2b7aeb2023-04-09T11:12:19ZengNature PortfolioScientific Reports2045-23222023-04-011311810.1038/s41598-023-32899-5Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phaseYasuyuki Kawai0Yohei Kogeichi1Koji Yamamoto2Keita Miyazaki3Hideki Asai4Hidetada Fukushima5Department of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityAbstract Predicting poor neurological outcomes after resuscitation is important for planning treatment strategies. We constructed an explainable artificial intelligence-based prognostic model using head computed tomography (CT) scans taken immediately within 3 h of resuscitation from cardiac arrest and compared its predictive accuracy with that of previous methods using gray-to-white matter ratio (GWR). We included 321 consecutive patients admitted to our institution after resuscitation for out-of-hospital cardiopulmonary arrest with circulation resumption over 6 years. A machine learning model using head CT images with transfer learning was used to predict the neurological outcomes at 1 month. These predictions were compared with the predictions of GWR for multiple regions of interest in head CT using receiver operating characteristic (ROC)-area under curve (AUC) and precision recall (PR)-AUC. The regions of focus were visualized using a heatmap. Both methods had similar ROC-AUCs, but the machine learning model had a higher PR-AUC (0.73 vs. 0.58). The machine learning-focused area of interest for classification was the boundary between gray and white matter, which overlapped with the area of focus when diagnosing hypoxic– ischemic brain injury. The machine learning model for predicting poor outcomes had superior accuracy to conventional methods and could help optimize treatment.https://doi.org/10.1038/s41598-023-32899-5 |
| spellingShingle | Yasuyuki Kawai Yohei Kogeichi Koji Yamamoto Keita Miyazaki Hideki Asai Hidetada Fukushima Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase Scientific Reports |
| title | Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase |
| title_full | Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase |
| title_fullStr | Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase |
| title_full_unstemmed | Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase |
| title_short | Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase |
| title_sort | explainable artificial intelligence based prediction of poor neurological outcome from head computed tomography in the immediate post resuscitation phase |
| url | https://doi.org/10.1038/s41598-023-32899-5 |
| work_keys_str_mv | AT yasuyukikawai explainableartificialintelligencebasedpredictionofpoorneurologicaloutcomefromheadcomputedtomographyintheimmediatepostresuscitationphase AT yoheikogeichi explainableartificialintelligencebasedpredictionofpoorneurologicaloutcomefromheadcomputedtomographyintheimmediatepostresuscitationphase AT kojiyamamoto explainableartificialintelligencebasedpredictionofpoorneurologicaloutcomefromheadcomputedtomographyintheimmediatepostresuscitationphase AT keitamiyazaki explainableartificialintelligencebasedpredictionofpoorneurologicaloutcomefromheadcomputedtomographyintheimmediatepostresuscitationphase AT hidekiasai explainableartificialintelligencebasedpredictionofpoorneurologicaloutcomefromheadcomputedtomographyintheimmediatepostresuscitationphase AT hidetadafukushima explainableartificialintelligencebasedpredictionofpoorneurologicaloutcomefromheadcomputedtomographyintheimmediatepostresuscitationphase |