Development and validation of patient-level prediction models for adverse outcomes following total knee arthroplasty
Abstract Background Elective total knee replacement (TKR) is a safe and cost-effective surgical procedure for treating severe knee osteoarthritis (OA). Although complications following surgery are rare, prediction tools could help identify those patients who are at particularly high risk who could then be targeted with preventative interventions. We aimed to develop a simple model to help inform treatment choices. Methods We trained and externally validated adverse event prediction models for patients with TKR using electronic health records (EHR) and claims data from the US (OPTUM, CCAE, MDCR, and MDCD) and general practice data in the UK (IQVIA Medical Research Database ([IMRD], incorporating data from The Health Improvement Network [THIN], a Cegedim database). The target population consisted of patients undergoing a primary TKR, aged ≥40 years and registered in any of the contributing data sources for ≥1 year before surgery. LASSO logistic regression models were developed for four adverse outcomes: post-operative (90-day) mortality, venous thromboembolism (VTE), readmission, and long-term (5-year) revision surgery. A second model was developed with a reduced feature set to increase interpretability and usability. Findings A total of 508,082 patients were included, with sample size per data source ranging from 1,853 to 158,549 patients. Overall, 90-day mortality, VTE, and readmission prevalence occurred in a range of 0.20%-0.32%, 1.7%-3.0% and 2.2%-4.8%, respectively. Five-year revision surgery was observed in 1.5%-3.1% of patients. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and yielded an AUROC of 0.70 when externally validated on THIN. We then developed a 12 variable model which achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. The discriminative performances of the models predicting 90-day VTE, readmission, and 5-year revision were consistently poor across the datasets (AUROC<0.7). Interpretation We developed and externally validated a simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR. Our model had a greater discriminative ability than the Charlson Comorbidity Index in predicting 90-day mortality. The 12-feature mortality model is easily implemented and the performance suggests it could be used to inform evidence based shared decision-making prior to surgery and for appropriate precautions to be taken for those at high risk. The other outcomes examined had low performance..
| Medienart: |
|
|---|
Preprint| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
bioRxiv.org - (2020) vom: 17. Dez. Zur Gesamtaufnahme - year:2020 |
|---|
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Williams, Ross [VerfasserIn] |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| doi: |
10.1101/2020.12.14.20240994 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
XBI019561857 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | XBI019561857 | ||
| 003 | DE-627 | ||
| 005 | 20230429095932.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 201218s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/2020.12.14.20240994 |2 doi | |
| 035 | |a (DE-627)XBI019561857 | ||
| 035 | |a (DE-599)biorXiv10.1101/2020.12.14.20240994 | ||
| 035 | |a (biorXiv)10.1101/2020.12.14.20240994 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | |a 570 |q DE-84 | |
| 100 | 1 | |a Williams, Ross |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Development and validation of patient-level prediction models for adverse outcomes following total knee arthroplasty |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract Background Elective total knee replacement (TKR) is a safe and cost-effective surgical procedure for treating severe knee osteoarthritis (OA). Although complications following surgery are rare, prediction tools could help identify those patients who are at particularly high risk who could then be targeted with preventative interventions. We aimed to develop a simple model to help inform treatment choices. Methods We trained and externally validated adverse event prediction models for patients with TKR using electronic health records (EHR) and claims data from the US (OPTUM, CCAE, MDCR, and MDCD) and general practice data in the UK (IQVIA Medical Research Database ([IMRD], incorporating data from The Health Improvement Network [THIN], a Cegedim database). The target population consisted of patients undergoing a primary TKR, aged ≥40 years and registered in any of the contributing data sources for ≥1 year before surgery. LASSO logistic regression models were developed for four adverse outcomes: post-operative (90-day) mortality, venous thromboembolism (VTE), readmission, and long-term (5-year) revision surgery. A second model was developed with a reduced feature set to increase interpretability and usability. Findings A total of 508,082 patients were included, with sample size per data source ranging from 1,853 to 158,549 patients. Overall, 90-day mortality, VTE, and readmission prevalence occurred in a range of 0.20%-0.32%, 1.7%-3.0% and 2.2%-4.8%, respectively. Five-year revision surgery was observed in 1.5%-3.1% of patients. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and yielded an AUROC of 0.70 when externally validated on THIN. We then developed a 12 variable model which achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. The discriminative performances of the models predicting 90-day VTE, readmission, and 5-year revision were consistently poor across the datasets (AUROC<0.7). Interpretation We developed and externally validated a simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR. Our model had a greater discriminative ability than the Charlson Comorbidity Index in predicting 90-day mortality. The 12-feature mortality model is easily implemented and the performance suggests it could be used to inform evidence based shared decision-making prior to surgery and for appropriate precautions to be taken for those at high risk. The other outcomes examined had low performance. | ||
| 700 | 1 | |a Reps, Jenna |e verfasserin |4 aut | |
| 700 | 1 | |a Sena, Anthony |e verfasserin |4 aut | |
| 700 | 1 | |a Burn, Edward |e verfasserin |4 aut | |
| 700 | 1 | |a Ying, Helen |e verfasserin |4 aut | |
| 700 | 1 | |a Morales, Daniel |e verfasserin |4 aut | |
| 700 | 1 | |a Culliford, David |e verfasserin |4 aut | |
| 700 | 1 | |a Yu, Dahai |e verfasserin |4 aut | |
| 700 | 1 | |a Strauss, Victoria |e verfasserin |4 aut | |
| 700 | 1 | |a Duarte-Salles, Talita |e verfasserin |4 aut | |
| 700 | 1 | |a Prats-Uribe, Albert |e verfasserin |4 aut | |
| 700 | 1 | |a Delmestri, Antonella |e verfasserin |4 aut | |
| 700 | 1 | |a Weaver, James |e verfasserin |4 aut | |
| 700 | 1 | |a Sproviero, William |e verfasserin |4 aut | |
| 700 | 1 | |a Robinson, Danielle |e verfasserin |4 aut | |
| 700 | 1 | |a Morgan-Stewart, Henry |e verfasserin |4 aut | |
| 700 | 1 | |a Birlie, Belay |e verfasserin |4 aut | |
| 700 | 1 | |a Pinedo-Villanueva, Rafael |e verfasserin |4 aut | |
| 700 | 1 | |a Kolovos, Spyros |e verfasserin |4 aut | |
| 700 | 1 | |a John, Luis |e verfasserin |4 aut | |
| 700 | 1 | |a Costello, Ruth |e verfasserin |4 aut | |
| 700 | 1 | |a van Speybroeck, Michel |e verfasserin |4 aut | |
| 700 | 1 | |a O'Leary, Caroline |e verfasserin |4 aut | |
| 700 | 1 | |a Minty, Evan |e verfasserin |4 aut | |
| 700 | 1 | |a Falconer, Thomas |e verfasserin |4 aut | |
| 700 | 1 | |a Bourke, Alison |e verfasserin |4 aut | |
| 700 | 1 | |a Pfohl, Stephen |e verfasserin |4 aut | |
| 700 | 1 | |a Burkard, Theresa |e verfasserin |4 aut | |
| 700 | 1 | |a Lane, Jennifer |e verfasserin |4 aut | |
| 700 | 1 | |a Rijnbeek, Peter |e verfasserin |4 aut | |
| 700 | 1 | |a Ryan, Patrick |e verfasserin |4 aut | |
| 700 | 1 | |a Prieto-Alhambra, Daniel |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2020) vom: 17. Dez. |
| 773 | 1 | 8 | |g year:2020 |g day:17 |g month:12 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/2020.12.14.20240994 |z kostenfrei |3 Volltext |
| 912 | |a GBV_XBI | ||
| 912 | |a SSG-OLC-PHA | ||
| 951 | |a AR | ||
| 952 | |j 2020 |b 17 |c 12 | ||
| 953 | |2 045F |a 570 | ||