Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study
Abstract Objectives Hospitalized patients with severe obesity require adapted hospital management. The aim of this study was to evaluate a machine learning model to predict in‐hospital mortality among this population. Methods Data of unselected consecutive emergency department admissions of hospital...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-08-01
|
| Series: | Obesity Science & Practice |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/osp4.571 |
| _version_ | 1828427435585044480 |
|---|---|
| author | Shelly Soffer Eyal Zimlichman Matthew A. Levin Alexis M. Zebrowski Benjamin S. Glicksberg Robert Freeman David L. Reich Eyal Klang |
| author_facet | Shelly Soffer Eyal Zimlichman Matthew A. Levin Alexis M. Zebrowski Benjamin S. Glicksberg Robert Freeman David L. Reich Eyal Klang |
| author_sort | Shelly Soffer |
| collection | DOAJ |
| description | Abstract Objectives Hospitalized patients with severe obesity require adapted hospital management. The aim of this study was to evaluate a machine learning model to predict in‐hospital mortality among this population. Methods Data of unselected consecutive emergency department admissions of hospitalized patients with severe obesity (BMI ≥ 40 kg/m2) was analyzed. Data was retrieved from five hospitals from the Mount Sinai health system, New York. The study time frame was between January 2011 and December 2019. Data was used to train a gradient‐boosting machine learning model to identify in‐hospital mortality. The model was trained and evaluated based on the data from four hospitals and externally validated on held‐out data from the fifth hospital. Results A total of 14,078 hospital admissions of inpatients with severe obesity were included. The in‐hospital mortality rate was 297/14,078 (2.1%). In univariate analysis, albumin (area under the curve [AUC] = 0.77), blood urea nitrogen (AUC = 0.76), acuity level (AUC = 0.73), lactate (AUC = 0.72), and chief complaint (AUC = 0.72) were the best single predictors. For Youden’s index, the model had a sensitivity of 0.77 (95% CI: 0.67–0.86) with a false positive rate of 1:9. Conclusion A machine learning model trained on clinical measures provides proof of concept performance in predicting mortality in patients with severe obesity. This implies that such models may help to adopt specific decision support tools for this population. |
| first_indexed | 2024-12-10T17:01:44Z |
| format | Article |
| id | doaj.art-9dc83f0cb9aa494cb45f01dec3dedfee |
| institution | Directory Open Access Journal |
| issn | 2055-2238 |
| language | English |
| last_indexed | 2024-12-10T17:01:44Z |
| publishDate | 2022-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Obesity Science & Practice |
| spelling | doaj.art-9dc83f0cb9aa494cb45f01dec3dedfee2022-12-22T01:40:33ZengWileyObesity Science & Practice2055-22382022-08-018447448210.1002/osp4.571Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept studyShelly Soffer0Eyal Zimlichman1Matthew A. Levin2Alexis M. Zebrowski3Benjamin S. Glicksberg4Robert Freeman5David L. Reich6Eyal Klang7Internal Medicine B Assuta Medical Center Ashdod IsraelHospital Management Sheba Medical Center Tel Hashomer IsraelDepartment of Population Health Science and Policy Institute for Healthcare Delivery Science Icahn School of Medicine at Mount Sinai New York New York USADepartment of Emergency Medicine Icahn School of Medicine at Mount Sinai New York New York USAHasso Plattner Institute for Digital Health at Mount Sinai Icahn School of Medicine at Mount Sinai New York New York USADepartment of Population Health Science and Policy Institute for Healthcare Delivery Science Icahn School of Medicine at Mount Sinai New York New York USADepartment of Anesthesiology, Perioperative and Pain Medicine Icahn School of Medicine at Mount Sinai New York New York USASackler Medical School Tel Aviv University Tel Aviv IsraelAbstract Objectives Hospitalized patients with severe obesity require adapted hospital management. The aim of this study was to evaluate a machine learning model to predict in‐hospital mortality among this population. Methods Data of unselected consecutive emergency department admissions of hospitalized patients with severe obesity (BMI ≥ 40 kg/m2) was analyzed. Data was retrieved from five hospitals from the Mount Sinai health system, New York. The study time frame was between January 2011 and December 2019. Data was used to train a gradient‐boosting machine learning model to identify in‐hospital mortality. The model was trained and evaluated based on the data from four hospitals and externally validated on held‐out data from the fifth hospital. Results A total of 14,078 hospital admissions of inpatients with severe obesity were included. The in‐hospital mortality rate was 297/14,078 (2.1%). In univariate analysis, albumin (area under the curve [AUC] = 0.77), blood urea nitrogen (AUC = 0.76), acuity level (AUC = 0.73), lactate (AUC = 0.72), and chief complaint (AUC = 0.72) were the best single predictors. For Youden’s index, the model had a sensitivity of 0.77 (95% CI: 0.67–0.86) with a false positive rate of 1:9. Conclusion A machine learning model trained on clinical measures provides proof of concept performance in predicting mortality in patients with severe obesity. This implies that such models may help to adopt specific decision support tools for this population.https://doi.org/10.1002/osp4.571big datain‐hospital mortalitymachine learningobesitysevere |
| spellingShingle | Shelly Soffer Eyal Zimlichman Matthew A. Levin Alexis M. Zebrowski Benjamin S. Glicksberg Robert Freeman David L. Reich Eyal Klang Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study Obesity Science & Practice big data in‐hospital mortality machine learning obesity severe |
| title | Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study |
| title_full | Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study |
| title_fullStr | Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study |
| title_full_unstemmed | Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study |
| title_short | Machine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study |
| title_sort | machine learning to predict in hospital mortality among patients with severe obesity proof of concept study |
| topic | big data in‐hospital mortality machine learning obesity severe |
| url | https://doi.org/10.1002/osp4.571 |
| work_keys_str_mv | AT shellysoffer machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT eyalzimlichman machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT matthewalevin machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT alexismzebrowski machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT benjaminsglicksberg machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT robertfreeman machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT davidlreich machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy AT eyalklang machinelearningtopredictinhospitalmortalityamongpatientswithsevereobesityproofofconceptstudy |