Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model
Abstract Background Unplanned readmission, a measure of surgical quality, occurs after 4.8% of primary total knee arthroplasties (TKA). Although the prediction of individualized readmission risk may inform appropriate preoperative interventions, current predictive models, such as the American Colleg...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Knee Surgery & Related Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43019-024-00256-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594598103351296 |
|---|---|
| author | Anirudh Buddhiraju Michelle Riyo Shimizu Tony Lin-Wei Chen Henry Hojoon Seo Blake M. Bacevich Pengwei Xiao Young-Min Kwon |
| author_facet | Anirudh Buddhiraju Michelle Riyo Shimizu Tony Lin-Wei Chen Henry Hojoon Seo Blake M. Bacevich Pengwei Xiao Young-Min Kwon |
| author_sort | Anirudh Buddhiraju |
| collection | DOAJ |
| description | Abstract Background Unplanned readmission, a measure of surgical quality, occurs after 4.8% of primary total knee arthroplasties (TKA). Although the prediction of individualized readmission risk may inform appropriate preoperative interventions, current predictive models, such as the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) surgical risk calculator (SRC), have limited utility. This study aims to compare the predictive accuracy of the SRC with a novel artificial neural network (ANN) algorithm for 30-day readmission after primary TKA, using the same set of clinical variables from a large national database. Methods Patients undergoing primary TKA between 2013 and 2020 were identified from the ACS-NSQIP database and randomly stratified into training and validation cohorts. The ANN was developed using data from the training cohort with fivefold cross-validation performed five times. ANN and SRC performance were subsequently evaluated in the distinct validation cohort, and predictive performance was compared on the basis of discrimination, calibration, accuracy, and clinical utility. Results The overall cohort consisted of 365,394 patients (trainingN = 362,559; validationN = 2835), with 11,392 (3.1%) readmitted within 30 days. While the ANN demonstrated good discrimination and calibration (area under the curve (AUC)ANN = 0.72, slope = 1.32, intercept = −0.09) in the validation cohort, the SRC demonstrated poor discrimination (AUCSRC = 0.55) and underestimated readmission risk (slope = −0.21, intercept = 0.04). Although both models possessed similar accuracy (Brier score: ANN = 0.03; SRC = 0.02), only the ANN demonstrated a higher net benefit than intervening in all or no patients on the decision curve analysis. The strongest predictors of readmission were body mass index (> 33.5 kg/m2), age (> 69 years), and male sex. Conclusions This study demonstrates the superior predictive ability and potential clinical utility of the ANN over the conventional SRC when constrained to the same variables. By identifying the most important predictors of readmission following TKA, our findings may assist in the development of novel clinical decision support tools, potentially improving preoperative counseling and postoperative monitoring practices in at-risk patients. |
| format | Article |
| id | doaj-art-0baabfb35827429fbd68f06f8ea6087f |
| institution | Kabale University |
| issn | 2234-2451 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Knee Surgery & Related Research |
| spelling | doaj-art-0baabfb35827429fbd68f06f8ea6087f2025-01-19T12:28:02ZengBMCKnee Surgery & Related Research2234-24512025-01-013711910.1186/s43019-024-00256-zComparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network modelAnirudh Buddhiraju0Michelle Riyo Shimizu1Tony Lin-Wei Chen2Henry Hojoon Seo3Blake M. Bacevich4Pengwei Xiao5Young-Min Kwon6Bioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolBioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolBioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolBioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolBioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolBioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolBioengineering Laboratory, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical SchoolAbstract Background Unplanned readmission, a measure of surgical quality, occurs after 4.8% of primary total knee arthroplasties (TKA). Although the prediction of individualized readmission risk may inform appropriate preoperative interventions, current predictive models, such as the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) surgical risk calculator (SRC), have limited utility. This study aims to compare the predictive accuracy of the SRC with a novel artificial neural network (ANN) algorithm for 30-day readmission after primary TKA, using the same set of clinical variables from a large national database. Methods Patients undergoing primary TKA between 2013 and 2020 were identified from the ACS-NSQIP database and randomly stratified into training and validation cohorts. The ANN was developed using data from the training cohort with fivefold cross-validation performed five times. ANN and SRC performance were subsequently evaluated in the distinct validation cohort, and predictive performance was compared on the basis of discrimination, calibration, accuracy, and clinical utility. Results The overall cohort consisted of 365,394 patients (trainingN = 362,559; validationN = 2835), with 11,392 (3.1%) readmitted within 30 days. While the ANN demonstrated good discrimination and calibration (area under the curve (AUC)ANN = 0.72, slope = 1.32, intercept = −0.09) in the validation cohort, the SRC demonstrated poor discrimination (AUCSRC = 0.55) and underestimated readmission risk (slope = −0.21, intercept = 0.04). Although both models possessed similar accuracy (Brier score: ANN = 0.03; SRC = 0.02), only the ANN demonstrated a higher net benefit than intervening in all or no patients on the decision curve analysis. The strongest predictors of readmission were body mass index (> 33.5 kg/m2), age (> 69 years), and male sex. Conclusions This study demonstrates the superior predictive ability and potential clinical utility of the ANN over the conventional SRC when constrained to the same variables. By identifying the most important predictors of readmission following TKA, our findings may assist in the development of novel clinical decision support tools, potentially improving preoperative counseling and postoperative monitoring practices in at-risk patients.https://doi.org/10.1186/s43019-024-00256-zReadmissionsTotal knee arthroplastyRisk assessmentsDeep learningClinical decision support |
| spellingShingle | Anirudh Buddhiraju Michelle Riyo Shimizu Tony Lin-Wei Chen Henry Hojoon Seo Blake M. Bacevich Pengwei Xiao Young-Min Kwon Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model Knee Surgery & Related Research Readmissions Total knee arthroplasty Risk assessments Deep learning Clinical decision support |
| title | Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model |
| title_full | Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model |
| title_fullStr | Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model |
| title_full_unstemmed | Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model |
| title_short | Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model |
| title_sort | comparing prediction accuracy for 30 day readmission following primary total knee arthroplasty the acs nsqip risk calculator versus a novel artificial neural network model |
| topic | Readmissions Total knee arthroplasty Risk assessments Deep learning Clinical decision support |
| url | https://doi.org/10.1186/s43019-024-00256-z |
| work_keys_str_mv | AT anirudhbuddhiraju comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel AT michelleriyoshimizu comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel AT tonylinweichen comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel AT henryhojoonseo comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel AT blakembacevich comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel AT pengweixiao comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel AT youngminkwon comparingpredictionaccuracyfor30dayreadmissionfollowingprimarytotalkneearthroplastytheacsnsqipriskcalculatorversusanovelartificialneuralnetworkmodel |