Machine learning models featuring somatic and mental comorbidities for prolonged length-of-stay in a maximum care university hospital [code]
Abstract Background: Knowledge about the influencing factors on hospital in-patient length-of-stay is integral for optimizing care and resource planning. Existing studies on prolonged length-of-stay prediction choose a precise figure as threshold for the number of days that classifies the length-of-...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Datenbank Forschungsdaten |
| Sprache: | Englisch |
| Veröffentlicht: |
Heidelberg
Universität
2025-06-27
|
| DOI: | 10.11588/DATA/HP9O2J |
| Schlagworte: | |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.11588/DATA/HP9O2J Verlag, kostenfrei, Volltext: https://heidata.uni-heidelberg.de/dataset.xhtml?persistentId=doi:10.11588/DATA/HP9O2J 
|
| Verfasserangaben: | Sophia Stahl-Toyota, Ivo Dönnhoff, Ede Nagy, Achim Hochlehnert, Stefan Bönsel, Inga Unger, Julia Szendrödi, Norbert Frey, Patrick Michl, Carsten Müller-Tidow, Dirk Jäger, Hans-Christoph Friederich, Christoph Nikendei |
MARC
| LEADER | 00000nmi a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1932803343 | ||
| 003 | DE-627 | ||
| 005 | 20250807112459.0 | ||
| 006 | su| d|o |0 |0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 250807c20259999xx |o | eng c | ||
| 024 | 7 | |a 10.11588/DATA/HP9O2J |2 doi | |
| 035 | |a (DE-627)1932803343 | ||
| 035 | |a (DE-599)KXP1932803343 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 11 |2 sdnb | ||
| 100 | 1 | |a Stahl-Toyota, Sophia |e VerfasserIn |0 (DE-588)1294099566 |0 (DE-627)1851056106 |4 aut | |
| 245 | 1 | 0 | |a Machine learning models featuring somatic and mental comorbidities for prolonged length-of-stay in a maximum care university hospital [code] |c Sophia Stahl-Toyota, Ivo Dönnhoff, Ede Nagy, Achim Hochlehnert, Stefan Bönsel, Inga Unger, Julia Szendrödi, Norbert Frey, Patrick Michl, Carsten Müller-Tidow, Dirk Jäger, Hans-Christoph Friederich, Christoph Nikendei |
| 264 | 1 | |a Heidelberg |b Universität |c 2025-06-27 | |
| 300 | |a 1 Online-Ressource (3 Files) | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 336 | |a Computerdaten |b cod |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 07.08.2025 | ||
| 520 | |a Abstract Background: Knowledge about the influencing factors on hospital in-patient length-of-stay is integral for optimizing care and resource planning. Existing studies on prolonged length-of-stay prediction choose a precise figure as threshold for the number of days that classifies the length-of-stay as prolonged and base the analysis on either a large and diverse sample or a very specific cohort. Most studies take somatic comorbidities into account, while only a subset incorporates mental comorbidities, with varying definitions of the composition of comorbidity subgroups. Objectives: (I) After which timeframe does the number of days of inpatient treatment indicate a prolonged length-of-stay if the threshold for outliers is computed department-wise in a maximum care internal medicine university hospital? (II) How accurate can machine learning models predict prolonged length-of-stay in internal medicine patients? (III) Which mental and somatic comorbidities have the strongest influence on length-of-stay prediction? Methods: From six internal medicine departments at the German University Hospital in Heidelberg, a total of N=28,536 cases treated in the years 2017 to 2019 comprised the study population for which a department-level threshold for prolonged length-of-stay was computed. For each of the six departments, four machine learning models were built that were based on the prolonged length-of-stay classification on variables derived from demographics and mental as well as somatic comorbidities. Results: Length-of-stay was classified as prolonged if the number of days at the hospital equaled or exceeded 9 (Cardiology), 10 (General and Psychosomatics, Gastroenterology, Medical Oncology), 11 (Endocrinology) or 26 (Hematology). With Area under the Receiver Operator Curve (AUROC)=0.89 the random forest for the Department of Hematology had the highest predictive power, the random forest for the Department of General and Psychosomatic with AUROC=0.72 the lowest. The variables with strongest influence on the prediction comprised the number of somatic comorbidities, the age at diagnosis, mental and somatic comorbidity subgroups. Among the mental comorbidities, stress-related adjustment disorder was the most prominent factor. Conclusions: Consideration of department-level factors is recommended for prolonged length-of-stay prediction models. Mental as well as somatic comorbidities were among the most relevant factors for the prediction of prolonged length-of-stay and require adequate treatment and reimbursement opportunities. | ||
| 650 | 4 | |a Computer and Information Science | |
| 650 | 4 | |a Health and Life Sciences | |
| 650 | 4 | |a Medicine | |
| 655 | 7 | |a Forschungsdaten |0 (DE-588)1098579690 |0 (DE-627)857755366 |0 (DE-576)469182156 |2 gnd-content | |
| 655 | 7 | |a Datenbank |0 (DE-588)4011119-2 |0 (DE-627)106354256 |0 (DE-576)208891943 |2 gnd-content | |
| 700 | 1 | |a Dönnhoff, Ivo |d 1991- |e VerfasserIn |0 (DE-588)1275342892 |0 (DE-627)1826823948 |4 aut | |
| 700 | 1 | |a Nagy, Ede |d 1976- |e VerfasserIn |0 (DE-588)1076995608 |0 (DE-627)835535584 |0 (DE-576)314946055 |4 aut | |
| 700 | 1 | |a Hochlehnert, Achim |d 1972- |e VerfasserIn |0 (DE-588)121857808 |0 (DE-627)705680061 |0 (DE-576)292921926 |4 aut | |
| 700 | 1 | |a Bönsel, Stefan |e VerfasserIn |4 aut | |
| 700 | 1 | |a Unger, Inga |e VerfasserIn |0 (DE-588)1299588980 |0 (DE-627)1856526461 |4 aut | |
| 700 | 1 | |a Szendrödi, Julia |e VerfasserIn |0 (DE-588)1226436463 |0 (DE-627)1747448249 |4 aut | |
| 700 | 1 | |a Frey, Norbert |e VerfasserIn |0 (DE-588)141244976 |0 (DE-627)625824075 |0 (DE-576)322969514 |4 aut | |
| 700 | 1 | |a Michl, Patrick |d 1971- |e VerfasserIn |0 (DE-588)121336328 |0 (DE-627)081239203 |0 (DE-576)292654677 |4 aut | |
| 700 | 1 | |a Müller-Tidow, Carsten |d 1968- |e VerfasserIn |0 (DE-588)1015101798 |0 (DE-627)705330230 |0 (DE-576)351197893 |4 aut | |
| 700 | 1 | |a Jäger, Dirk |d 1964- |e VerfasserIn |0 (DE-588)1032507535 |0 (DE-627)738505323 |0 (DE-576)380074125 |4 aut | |
| 700 | 1 | |a Friederich, Hans-Christoph |d 1971- |e VerfasserIn |0 (DE-588)122302524 |0 (DE-627)70585311X |0 (DE-576)293208417 |4 aut | |
| 700 | 1 | |a Nikendei, Christoph |d 1971- |e VerfasserIn |0 (DE-588)123417023 |0 (DE-627)08254350X |0 (DE-576)184450977 |4 aut | |
| 856 | 4 | 0 | |u https://doi.org/10.11588/DATA/HP9O2J |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://heidata.uni-heidelberg.de/dataset.xhtml?persistentId=doi:10.11588/DATA/HP9O2J |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a BO | ||
| 992 | |a 20250807 | ||
| 993 | |a ResearchData | ||
| 994 | |a 2025 | ||
| 998 | |g 123417023 |a Nikendei, Christoph |m 123417023:Nikendei, Christoph |d 910000 |d 910100 |d 50000 |e 910000PN123417023 |e 910100PN123417023 |e 50000PN123417023 |k 0/910000/ |k 1/910000/910100/ |k 0/50000/ |p 13 |y j | ||
| 998 | |g 122302524 |a Friederich, Hans-Christoph |m 122302524:Friederich, Hans-Christoph |d 910000 |d 910100 |e 910000PF122302524 |e 910100PF122302524 |k 0/910000/ |k 1/910000/910100/ |p 12 | ||
| 998 | |g 1032507535 |a Jäger, Dirk |m 1032507535:Jäger, Dirk |d 50000 |e 50000PJ1032507535 |k 0/50000/ |p 11 | ||
| 998 | |g 1015101798 |a Müller-Tidow, Carsten |m 1015101798:Müller-Tidow, Carsten |d 910000 |d 910100 |e 910000PM1015101798 |e 910100PM1015101798 |k 0/910000/ |k 1/910000/910100/ |p 10 | ||
| 998 | |g 121336328 |a Michl, Patrick |m 121336328:Michl, Patrick |d 910000 |d 910100 |e 910000PM121336328 |e 910100PM121336328 |k 0/910000/ |k 1/910000/910100/ |p 9 | ||
| 998 | |g 141244976 |a Frey, Norbert |m 141244976:Frey, Norbert |d 910000 |d 910100 |e 910000PF141244976 |e 910100PF141244976 |k 0/910000/ |k 1/910000/910100/ |p 8 | ||
| 998 | |g 1226436463 |a Szendrödi, Julia |m 1226436463:Szendrödi, Julia |d 910000 |d 910100 |e 910000PS1226436463 |e 910100PS1226436463 |k 0/910000/ |k 1/910000/910100/ |p 7 | ||
| 998 | |g 121857808 |a Hochlehnert, Achim |m 121857808:Hochlehnert, Achim |d 50000 |e 50000PH121857808 |k 0/50000/ |p 4 | ||
| 998 | |g 1076995608 |a Nagy, Ede |m 1076995608:Nagy, Ede |d 910000 |d 910100 |e 910000PN1076995608 |e 910100PN1076995608 |k 0/910000/ |k 1/910000/910100/ |p 3 | ||
| 998 | |g 1275342892 |a Dönnhoff, Ivo |m 1275342892:Dönnhoff, Ivo |d 910000 |d 910100 |e 910000PD1275342892 |e 910100PD1275342892 |k 0/910000/ |k 1/910000/910100/ |p 2 | ||
| 998 | |g 1294099566 |a Stahl-Toyota, Sophia |m 1294099566:Stahl-Toyota, Sophia |d 910000 |d 910100 |e 910000PS1294099566 |e 910100PS1294099566 |k 0/910000/ |k 1/910000/910100/ |p 1 |x j | ||
| 999 | |a KXP-PPN1932803343 |e 4754929675 | ||
| BIB | |a Y | ||
| JSO | |a {"title":[{"title_sort":"Machine learning models featuring somatic and mental comorbidities for prolonged length-of-stay in a maximum care university hospital [code]","title":"Machine learning models featuring somatic and mental comorbidities for prolonged length-of-stay in a maximum care university hospital [code]"}],"language":["eng"],"name":{"displayForm":["Sophia Stahl-Toyota, Ivo Dönnhoff, Ede Nagy, Achim Hochlehnert, Stefan Bönsel, Inga Unger, Julia Szendrödi, Norbert Frey, Patrick Michl, Carsten Müller-Tidow, Dirk Jäger, Hans-Christoph Friederich, Christoph Nikendei"]},"origin":[{"publisher":"Universität","dateIssuedDisp":"2025-06-27","dateIssuedKey":"2025","publisherPlace":"Heidelberg"}],"recId":"1932803343","person":[{"given":"Sophia","display":"Stahl-Toyota, Sophia","family":"Stahl-Toyota","role":"aut"},{"role":"aut","given":"Ivo","display":"Dönnhoff, Ivo","family":"Dönnhoff"},{"family":"Nagy","display":"Nagy, Ede","given":"Ede","role":"aut"},{"family":"Hochlehnert","given":"Achim","display":"Hochlehnert, Achim","role":"aut"},{"family":"Bönsel","given":"Stefan","display":"Bönsel, Stefan","role":"aut"},{"given":"Inga","display":"Unger, Inga","family":"Unger","role":"aut"},{"given":"Julia","display":"Szendrödi, Julia","family":"Szendrödi","role":"aut"},{"family":"Frey","given":"Norbert","display":"Frey, Norbert","role":"aut"},{"given":"Patrick","display":"Michl, Patrick","family":"Michl","role":"aut"},{"role":"aut","family":"Müller-Tidow","display":"Müller-Tidow, Carsten","given":"Carsten"},{"role":"aut","family":"Jäger","given":"Dirk","display":"Jäger, Dirk"},{"given":"Hans-Christoph","display":"Friederich, Hans-Christoph","family":"Friederich","role":"aut"},{"family":"Nikendei","display":"Nikendei, Christoph","given":"Christoph","role":"aut"}],"note":["Gesehen am 07.08.2025"],"id":{"doi":["10.11588/DATA/HP9O2J"],"eki":["1932803343"]},"type":{"bibl":"dataset","media":"Online-Ressource"},"physDesc":[{"extent":"1 Online-Ressource (3 Files)"}]} | ||
| SRT | |a STAHLTOYOTMACHINELEA2025 | ||