90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model

Ross D. Williams; Jenna M. Reps; The OHDSI/EHDEN Knee Arthroplasty Group; Peter R. Rijnbeek; Patrick B. Ryan; Daniel Prieto-Alhambra; Henrik John

doi:10.1007/s00167-021-06799-y

90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model

Ross D. Williams, Jenna M. Reps, The OHDSI/EHDEN Knee Arthroplasty Group, Peter R. Rijnbeek, Patrick B. Ryan, Daniel Prieto-Alhambra^*, Henrik John

^*Corresponding author for this work

Medical Informatics

Research output: Contribution to journal › Article › Academic › peer-review

11 Citations (Scopus)

44 Downloads (Pure)

Abstract

Purpose: The purpose of this study was to develop and validate a prediction model for 90-day mortality following a total knee replacement (TKR). 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 high-risk patients who could be targeted with preventative interventions. The aim was to develop and validate a simple model to help inform treatment choices. Methods: A mortality prediction model for knee OA patients following TKR was developed and externally validated using a US claims database and a UK general practice database. The target population consisted of patients undergoing a primary TKR for knee OA, aged ≥ 40 years and registered for ≥ 1 year before surgery. LASSO logistic regression models were developed for post-operative (90-day) mortality. A second mortality model was developed with a reduced feature set to increase interpretability and usability. Results: A total of 193,615 patients were included, with 40,950 in The Health Improvement Network (THIN) database and 152,665 in Optum. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and 0.70 when externally validated on THIN. The 12 variable model achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. Conclusions: A simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR was developed that demonstrated good, robust performance. 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 targeting prophylaxis for those at high risk. Level of evidence: III.

Original language	English
Journal	Knee Surgery, Sports Traumatology, Arthroscopy
DOIs	https://doi.org/10.1007/s00167-021-06799-y
Publication status	Published - 6 Dec 2021

Bibliographical note

Funding Information:
All authors have completed the ICMJE uniform disclosure form at http://www.icmje.org/coi_disclosure.pdf and declare: AS, JW, JR, MvS and PBR are full-time employees of Janssen Research & Development, a pharmaceutical company of Johnson & Johnson, and shareholders in Johnson & Johnson. the Johnson & Johnson family of companies also includes DePuy Synthes, which is the maker of medical devices for joint reconstruction. DPA reports grants from Amgen, Grants from UCB Biopharma, grants from Les Laboratoires Servier, outside the submitted work. CO is a part-time employee of IQVIA.

Funding Information:
This activity under the European Health Data & Evidence Network (EHDEN) has received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No 806968. This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA. The sponsor of the study did not have any involvement in the writing of the manuscript or the decision to submit it for publication. The corresponding author had full access to all the data in the study and had final responsibility for the decision to submit for publication

Publisher Copyright:
© 2021, The Author(s).

Access to Document

10.1007/s00167-021-06799-yLicence: CC BY

90-Day all-cause mortality can be predicted following a total knee replacement an international, network study to develop and validate a prediction modelFinal published version, 703 KBLicence: CC BY

Cite this

Williams, R. D., Reps, J. M., The OHDSI/EHDEN Knee Arthroplasty Group, Rijnbeek, P. R., Ryan, P. B., Prieto-Alhambra, D., & John, H. (2021). 90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model. Knee Surgery, Sports Traumatology, Arthroscopy. https://doi.org/10.1007/s00167-021-06799-y

@article{7c63917f0cd54af184629db5fa22ca76,

title = "90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model",

abstract = "Purpose: The purpose of this study was to develop and validate a prediction model for 90-day mortality following a total knee replacement (TKR). 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 high-risk patients who could be targeted with preventative interventions. The aim was to develop and validate a simple model to help inform treatment choices. Methods: A mortality prediction model for knee OA patients following TKR was developed and externally validated using a US claims database and a UK general practice database. The target population consisted of patients undergoing a primary TKR for knee OA, aged ≥ 40 years and registered for ≥ 1 year before surgery. LASSO logistic regression models were developed for post-operative (90-day) mortality. A second mortality model was developed with a reduced feature set to increase interpretability and usability. Results: A total of 193,615 patients were included, with 40,950 in The Health Improvement Network (THIN) database and 152,665 in Optum. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and 0.70 when externally validated on THIN. The 12 variable model achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. Conclusions: A simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR was developed that demonstrated good, robust performance. 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 targeting prophylaxis for those at high risk. Level of evidence: III.",

author = "Williams, \{Ross D.\} and Reps, \{Jenna M.\} and \{The OHDSI/EHDEN Knee Arthroplasty Group\} and Rijnbeek, \{Peter R.\} and Ryan, \{Patrick B.\} and Daniel Prieto-Alhambra and Sena, \{Anthony G.\} and Edward Burn and Ying He and Morales, \{Daniel R.\} and David Culliford and Dahai Yu and Strauss, \{Victoria Y.\} and Talita Duarte-Salles and Albert Prats-Uribe and Antonella Delmestri and James Weaver and William Sproviero and Danielle Robinson and Stewart, \{Henry Morgan\} and Belay Birlie and Rafael Pinedo-Villanueva and Spyros Kolovos and John, \{Luis H.\} and Costello, \{Ruth E.\} and \{van Speybroeck\}, Michel and Caroline O{\textquoteright}Leary and Evan Minty and Thomas Falconer and Alison Callahan and Stephen Pfohl and Theresa Burkard and Jennifer Lane and Henrik John",

note = "Funding Information: All authors have completed the ICMJE uniform disclosure form at http://www.icmje.org/coi\_disclosure.pdf and declare: AS, JW, JR, MvS and PBR are full-time employees of Janssen Research \& Development, a pharmaceutical company of Johnson \& Johnson, and shareholders in Johnson \& Johnson. the Johnson \& Johnson family of companies also includes DePuy Synthes, which is the maker of medical devices for joint reconstruction. DPA reports grants from Amgen, Grants from UCB Biopharma, grants from Les Laboratoires Servier, outside the submitted work. CO is a part-time employee of IQVIA. Funding Information: This activity under the European Health Data \& Evidence Network (EHDEN) has received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No 806968. This Joint Undertaking receives support from the European Union{\textquoteright}s Horizon 2020 research and innovation programme and EFPIA. The sponsor of the study did not have any involvement in the writing of the manuscript or the decision to submit it for publication. The corresponding author had full access to all the data in the study and had final responsibility for the decision to submit for publication Publisher Copyright: {\textcopyright} 2021, The Author(s).",

year = "2021",

month = dec,

day = "6",

doi = "10.1007/s00167-021-06799-y",

language = "English",

journal = "Knee Surgery, Sports Traumatology, Arthroscopy",

issn = "0942-2056",

publisher = "John Wiley \& Sons Inc.",

}

Williams, RD, Reps, JM, The OHDSI/EHDEN Knee Arthroplasty Group, Rijnbeek, PR, Ryan, PB, Prieto-Alhambra, D & John, H 2021, '90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model', Knee Surgery, Sports Traumatology, Arthroscopy. https://doi.org/10.1007/s00167-021-06799-y

90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model. / Williams, Ross D.; Reps, Jenna M.; The OHDSI/EHDEN Knee Arthroplasty Group et al.
In: Knee Surgery, Sports Traumatology, Arthroscopy, 06.12.2021.

Research output: Contribution to journal › Article › Academic › peer-review

TY - JOUR

T1 - 90-Day all-cause mortality can be predicted following a total knee replacement

T2 - an international, network study to develop and validate a prediction model

AU - Williams, Ross D.

AU - Reps, Jenna M.

AU - The OHDSI/EHDEN Knee Arthroplasty Group

AU - Rijnbeek, Peter R.

AU - Ryan, Patrick B.

AU - Prieto-Alhambra, Daniel

AU - Sena, Anthony G.

AU - Burn, Edward

AU - He, Ying

AU - Morales, Daniel R.

AU - Culliford, David

AU - Yu, Dahai

AU - Strauss, Victoria Y.

AU - Duarte-Salles, Talita

AU - Prats-Uribe, Albert

AU - Delmestri, Antonella

AU - Weaver, James

AU - Sproviero, William

AU - Robinson, Danielle

AU - Stewart, Henry Morgan

AU - Birlie, Belay

AU - Pinedo-Villanueva, Rafael

AU - Kolovos, Spyros

AU - John, Luis H.

AU - Costello, Ruth E.

AU - van Speybroeck, Michel

AU - O’Leary, Caroline

AU - Minty, Evan

AU - Falconer, Thomas

AU - Callahan, Alison

AU - Pfohl, Stephen

AU - Burkard, Theresa

AU - Lane, Jennifer

AU - John, Henrik

N1 - Funding Information: All authors have completed the ICMJE uniform disclosure form at http://www.icmje.org/coi_disclosure.pdf and declare: AS, JW, JR, MvS and PBR are full-time employees of Janssen Research & Development, a pharmaceutical company of Johnson & Johnson, and shareholders in Johnson & Johnson. the Johnson & Johnson family of companies also includes DePuy Synthes, which is the maker of medical devices for joint reconstruction. DPA reports grants from Amgen, Grants from UCB Biopharma, grants from Les Laboratoires Servier, outside the submitted work. CO is a part-time employee of IQVIA. Funding Information: This activity under the European Health Data & Evidence Network (EHDEN) has received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No 806968. This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA. The sponsor of the study did not have any involvement in the writing of the manuscript or the decision to submit it for publication. The corresponding author had full access to all the data in the study and had final responsibility for the decision to submit for publication Publisher Copyright: © 2021, The Author(s).

PY - 2021/12/6

Y1 - 2021/12/6

N2 - Purpose: The purpose of this study was to develop and validate a prediction model for 90-day mortality following a total knee replacement (TKR). 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 high-risk patients who could be targeted with preventative interventions. The aim was to develop and validate a simple model to help inform treatment choices. Methods: A mortality prediction model for knee OA patients following TKR was developed and externally validated using a US claims database and a UK general practice database. The target population consisted of patients undergoing a primary TKR for knee OA, aged ≥ 40 years and registered for ≥ 1 year before surgery. LASSO logistic regression models were developed for post-operative (90-day) mortality. A second mortality model was developed with a reduced feature set to increase interpretability and usability. Results: A total of 193,615 patients were included, with 40,950 in The Health Improvement Network (THIN) database and 152,665 in Optum. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and 0.70 when externally validated on THIN. The 12 variable model achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. Conclusions: A simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR was developed that demonstrated good, robust performance. 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 targeting prophylaxis for those at high risk. Level of evidence: III.

AB - Purpose: The purpose of this study was to develop and validate a prediction model for 90-day mortality following a total knee replacement (TKR). 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 high-risk patients who could be targeted with preventative interventions. The aim was to develop and validate a simple model to help inform treatment choices. Methods: A mortality prediction model for knee OA patients following TKR was developed and externally validated using a US claims database and a UK general practice database. The target population consisted of patients undergoing a primary TKR for knee OA, aged ≥ 40 years and registered for ≥ 1 year before surgery. LASSO logistic regression models were developed for post-operative (90-day) mortality. A second mortality model was developed with a reduced feature set to increase interpretability and usability. Results: A total of 193,615 patients were included, with 40,950 in The Health Improvement Network (THIN) database and 152,665 in Optum. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and 0.70 when externally validated on THIN. The 12 variable model achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. Conclusions: A simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR was developed that demonstrated good, robust performance. 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 targeting prophylaxis for those at high risk. Level of evidence: III.

UR - https://www.scopus.com/pages/publications/85120889201

U2 - 10.1007/s00167-021-06799-y

DO - 10.1007/s00167-021-06799-y

M3 - Article

AN - SCOPUS:85120889201

SN - 0942-2056

JO - Knee Surgery, Sports Traumatology, Arthroscopy

JF - Knee Surgery, Sports Traumatology, Arthroscopy

ER -

90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this