Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models
Objective Systematic review of length of stay (LOS) prediction models to assess the study methods (including prediction variables), study quality, and performance of predictive models (using area under receiver operating curve (AUROC)) for general surgery populations and total knee arthroplasty (TKA...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-05-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076231177497 |
| _version_ | 1827933044972978176 |
|---|---|
| author | Swapna Gokhale David Taylor Jaskirath Gill Yanan Hu Nikolajs Zeps Vincent Lequertier Helena Teede Joanne Enticott |
| author_facet | Swapna Gokhale David Taylor Jaskirath Gill Yanan Hu Nikolajs Zeps Vincent Lequertier Helena Teede Joanne Enticott |
| author_sort | Swapna Gokhale |
| collection | DOAJ |
| description | Objective Systematic review of length of stay (LOS) prediction models to assess the study methods (including prediction variables), study quality, and performance of predictive models (using area under receiver operating curve (AUROC)) for general surgery populations and total knee arthroplasty (TKA). Method LOS prediction models published since 2010 were identified in five major research databases. The main outcomes were model performance metrics including AUROC, prediction variables, and level of validation. Risk of bias was assessed using the PROBAST checklist. Results Five general surgery studies (15 models) and 10 TKA studies (24 models) were identified. All general surgery and 20 TKA models used statistical approaches; 4 TKA models used machine learning approaches. Risk scores, diagnosis, and procedure types were predominant predictors used. Risk of bias was ranked as moderate in 3/15 and high in 12/15 studies. Discrimination measures were reported in 14/15 and calibration measures in 3/15 studies, with only 4/39 externally validated models (3 general surgery and 1 TKA). Meta-analysis of externally validated models (3 general surgery) suggested the AUROC 95% prediction interval is excellent and ranges between 0.803 and 0.970. Conclusion This is the first systematic review assessing quality of risk prediction models for prolonged LOS in general surgery and TKA groups. We showed that these risk prediction models were infrequently externally validated with poor study quality, typically related to poor reporting. Both machine learning and statistical modelling methods, plus the meta-analysis, showed acceptable to good predictive performance, which are encouraging. Moving forward, a focus on quality methods and external validation is needed before clinical application. |
| first_indexed | 2024-03-13T07:19:09Z |
| format | Article |
| id | doaj.art-70497d072c2f4a54bea3f1c01107ba44 |
| institution | Directory Open Access Journal |
| issn | 2055-2076 |
| language | English |
| last_indexed | 2024-03-13T07:19:09Z |
| publishDate | 2023-05-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj.art-70497d072c2f4a54bea3f1c01107ba442023-06-04T23:33:19ZengSAGE PublishingDigital Health2055-20762023-05-01910.1177/20552076231177497Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction modelsSwapna Gokhale0David Taylor1Jaskirath Gill2Yanan Hu3Nikolajs Zeps4Vincent Lequertier5Helena Teede6Joanne Enticott7 , Box Hill, Victoria, Australia Office of Research and Ethics, , Box Hill, Victoria, Australia , Melbourne, Victoria, Australia , Nursing, and Health Sciences, Monash Centre for Health Research and Implementation, School of Public Health and Preventive Medicine, , Clayton, Victoria, Australia Eastern Health Clinical School, , Nursing and Health Sciences, Box Hill, Australia Univ. Lyon, INSA Lyon, Univ Lyon 2, , Lyon, France Graduate Research Industry Partnerships (GRIP) Program, Monash Partners Academic Health Science Centre, Clayton, Victoria, Australia Graduate Research Industry Partnerships (GRIP) Program, Monash Partners Academic Health Science Centre, Clayton, Victoria, AustraliaObjective Systematic review of length of stay (LOS) prediction models to assess the study methods (including prediction variables), study quality, and performance of predictive models (using area under receiver operating curve (AUROC)) for general surgery populations and total knee arthroplasty (TKA). Method LOS prediction models published since 2010 were identified in five major research databases. The main outcomes were model performance metrics including AUROC, prediction variables, and level of validation. Risk of bias was assessed using the PROBAST checklist. Results Five general surgery studies (15 models) and 10 TKA studies (24 models) were identified. All general surgery and 20 TKA models used statistical approaches; 4 TKA models used machine learning approaches. Risk scores, diagnosis, and procedure types were predominant predictors used. Risk of bias was ranked as moderate in 3/15 and high in 12/15 studies. Discrimination measures were reported in 14/15 and calibration measures in 3/15 studies, with only 4/39 externally validated models (3 general surgery and 1 TKA). Meta-analysis of externally validated models (3 general surgery) suggested the AUROC 95% prediction interval is excellent and ranges between 0.803 and 0.970. Conclusion This is the first systematic review assessing quality of risk prediction models for prolonged LOS in general surgery and TKA groups. We showed that these risk prediction models were infrequently externally validated with poor study quality, typically related to poor reporting. Both machine learning and statistical modelling methods, plus the meta-analysis, showed acceptable to good predictive performance, which are encouraging. Moving forward, a focus on quality methods and external validation is needed before clinical application.https://doi.org/10.1177/20552076231177497 |
| spellingShingle | Swapna Gokhale David Taylor Jaskirath Gill Yanan Hu Nikolajs Zeps Vincent Lequertier Helena Teede Joanne Enticott Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models Digital Health |
| title | Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models |
| title_full | Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models |
| title_fullStr | Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models |
| title_full_unstemmed | Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models |
| title_short | Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: Systematic review and meta-analysis of published prediction models |
| title_sort | hospital length of stay prediction for general surgery and total knee arthroplasty admissions systematic review and meta analysis of published prediction models |
| url | https://doi.org/10.1177/20552076231177497 |
| work_keys_str_mv | AT swapnagokhale hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT davidtaylor hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT jaskirathgill hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT yananhu hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT nikolajszeps hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT vincentlequertier hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT helenateede hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels AT joanneenticott hospitallengthofstaypredictionforgeneralsurgeryandtotalkneearthroplastyadmissionssystematicreviewandmetaanalysisofpublishedpredictionmodels |