Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis
BackgroundUnwarranted extended length of stay (LOS) increases the risk of hospital-acquired complications, morbidity, and all-cause mortality and needs to be recognized and addressed proactively.ObjectiveThis systematic review aimed to identify validated prediction variables and methods used in tool...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2023.1192969/full |
| _version_ | 1797741641235169280 |
|---|---|
| author | Swapna Gokhale Swapna Gokhale David Taylor Jaskirath Gill Jaskirath Gill Yanan Hu Nikolajs Zeps Nikolajs Zeps Vincent Lequertier Vincent Lequertier Luis Prado Helena Teede Helena Teede Joanne Enticott Joanne Enticott |
| author_facet | Swapna Gokhale Swapna Gokhale David Taylor Jaskirath Gill Jaskirath Gill Yanan Hu Nikolajs Zeps Nikolajs Zeps Vincent Lequertier Vincent Lequertier Luis Prado Helena Teede Helena Teede Joanne Enticott Joanne Enticott |
| author_sort | Swapna Gokhale |
| collection | DOAJ |
| description | BackgroundUnwarranted extended length of stay (LOS) increases the risk of hospital-acquired complications, morbidity, and all-cause mortality and needs to be recognized and addressed proactively.ObjectiveThis systematic review aimed to identify validated prediction variables and methods used in tools that predict the risk of prolonged LOS in all hospital admissions and specifically General Medicine (GenMed) admissions.MethodLOS prediction tools published since 2010 were identified in five major research databases. The main outcomes were model performance metrics, prediction variables, and level of validation. Meta-analysis was completed for validated models. The risk of bias was assessed using the PROBAST checklist.ResultsOverall, 25 all admission studies and 14 GenMed studies were identified. Statistical and machine learning methods were used almost equally in both groups. Calibration metrics were reported infrequently, with only 2 of 39 studies performing external validation. Meta-analysis of all admissions validation studies revealed a 95% prediction interval for theta of 0.596 to 0.798 for the area under the curve. Important predictor categories were co-morbidity diagnoses and illness severity risk scores, demographics, and admission characteristics. Overall study quality was deemed low due to poor data processing and analysis reporting.ConclusionTo the best of our knowledge, this is the first systematic review assessing the quality of risk prediction models for hospital LOS in GenMed and all admissions groups. Notably, both machine learning and statistical modeling demonstrated good predictive performance, but models were infrequently externally validated and had poor overall study quality. Moving forward, a focus on quality methods by the adoption of existing guidelines and external validation is needed before clinical application.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42021272198. |
| first_indexed | 2024-03-12T14:30:39Z |
| format | Article |
| id | doaj.art-bc9e74782d564740bc53a142f59f8553 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-03-12T14:30:39Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-bc9e74782d564740bc53a142f59f85532023-08-17T14:35:17ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2023-08-011010.3389/fmed.2023.11929691192969Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysisSwapna Gokhale0Swapna Gokhale1David Taylor2Jaskirath Gill3Jaskirath Gill4Yanan Hu5Nikolajs Zeps6Nikolajs Zeps7Vincent Lequertier8Vincent Lequertier9Luis Prado10Helena Teede11Helena Teede12Joanne Enticott13Joanne Enticott14Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing, and Health Sciences, Monash University, Clayton, VIC, AustraliaEastern Health, Box Hill, VIC, AustraliaOffice of Research and Ethics, Eastern Health, Box Hill, VIC, AustraliaMonash Centre for Health Research and Implementation, Faculty of Medicine, Nursing, and Health Sciences, Monash University, Clayton, VIC, AustraliaAlfred Health, Melbourne, VIC, AustraliaMonash Centre for Health Research and Implementation, Faculty of Medicine, Nursing, and Health Sciences, Monash University, Clayton, VIC, AustraliaMonash Partners Academic Health Sciences Centre, Clayton, VIC, AustraliaEastern Health Clinical School, Monash University Faculty of Medicine, Nursing and Health Sciences, Clayton, VIC, AustraliaUniv. Lyon, INSA Lyon, Univ Lyon 2, Université Claude Bernard Lyon 1, Lyon, FranceResearch on Healthcare Performance (RESHAPE), INSERM U1290, Université Claude Bernard Lyon 1, Lyon, FranceEpworth Healthcare, Academic and Medical Services, Melbourne, VIC, AustraliaMonash Centre for Health Research and Implementation, Faculty of Medicine, Nursing, and Health Sciences, Monash University, Clayton, VIC, AustraliaMonash Partners Academic Health Sciences Centre, Clayton, VIC, AustraliaMonash Centre for Health Research and Implementation, Faculty of Medicine, Nursing, and Health Sciences, Monash University, Clayton, VIC, AustraliaMonash Partners Academic Health Sciences Centre, Clayton, VIC, AustraliaBackgroundUnwarranted extended length of stay (LOS) increases the risk of hospital-acquired complications, morbidity, and all-cause mortality and needs to be recognized and addressed proactively.ObjectiveThis systematic review aimed to identify validated prediction variables and methods used in tools that predict the risk of prolonged LOS in all hospital admissions and specifically General Medicine (GenMed) admissions.MethodLOS prediction tools published since 2010 were identified in five major research databases. The main outcomes were model performance metrics, prediction variables, and level of validation. Meta-analysis was completed for validated models. The risk of bias was assessed using the PROBAST checklist.ResultsOverall, 25 all admission studies and 14 GenMed studies were identified. Statistical and machine learning methods were used almost equally in both groups. Calibration metrics were reported infrequently, with only 2 of 39 studies performing external validation. Meta-analysis of all admissions validation studies revealed a 95% prediction interval for theta of 0.596 to 0.798 for the area under the curve. Important predictor categories were co-morbidity diagnoses and illness severity risk scores, demographics, and admission characteristics. Overall study quality was deemed low due to poor data processing and analysis reporting.ConclusionTo the best of our knowledge, this is the first systematic review assessing the quality of risk prediction models for hospital LOS in GenMed and all admissions groups. Notably, both machine learning and statistical modeling demonstrated good predictive performance, but models were infrequently externally validated and had poor overall study quality. Moving forward, a focus on quality methods by the adoption of existing guidelines and external validation is needed before clinical application.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42021272198.https://www.frontiersin.org/articles/10.3389/fmed.2023.1192969/fullrisk assessment/risk prediction tools/factors/methodslength of stayregressionmachine learningmedicine |
| spellingShingle | Swapna Gokhale Swapna Gokhale David Taylor Jaskirath Gill Jaskirath Gill Yanan Hu Nikolajs Zeps Nikolajs Zeps Vincent Lequertier Vincent Lequertier Luis Prado Helena Teede Helena Teede Joanne Enticott Joanne Enticott Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis Frontiers in Medicine risk assessment/risk prediction tools/factors/methods length of stay regression machine learning medicine |
| title | Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis |
| title_full | Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis |
| title_fullStr | Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis |
| title_full_unstemmed | Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis |
| title_short | Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis |
| title_sort | hospital length of stay prediction tools for all hospital admissions and general medicine populations systematic review and meta analysis |
| topic | risk assessment/risk prediction tools/factors/methods length of stay regression machine learning medicine |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2023.1192969/full |
| work_keys_str_mv | AT swapnagokhale hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT swapnagokhale hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT davidtaylor hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT jaskirathgill hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT jaskirathgill hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT yananhu hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT nikolajszeps hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT nikolajszeps hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT vincentlequertier hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT vincentlequertier hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT luisprado hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT helenateede hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT helenateede hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT joanneenticott hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis AT joanneenticott hospitallengthofstaypredictiontoolsforallhospitaladmissionsandgeneralmedicinepopulationssystematicreviewandmetaanalysis |