Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation

Charles Hamesse, Ruibo Tu, Paul Ackermann, Hedvig Kjellström, Cheng Zhang
Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:614-640, 2019.

Abstract

Achilles Tendon Rupture (ATR) is one of the typical soft tissue injuries. Rehabilitation after such a musculoskeletal injury remains a prolonged process with a very variable outcome. Accurately predicting rehabilitation outcome is crucial for treatment decision support. However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes. In this work, we design an end-to-end probabilistic framework to impute missing data entries and predict rehabilitation outcomes simultaneously. We evaluate our model on a real-life ATR clinical cohort, comparing with various baselines. The proposed method demonstrates its clear superiority over traditional methods which typically perform imputation and prediction in two separate stages.

Cite this Paper


BibTeX
@InProceedings{pmlr-v106-hamesse19a, title = {Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation}, author = {Hamesse, Charles and Tu, Ruibo and Ackermann, Paul and Kjellstr{\"{o}}m, Hedvig and Zhang, Cheng}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {614--640}, year = {2019}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {106}, series = {Proceedings of Machine Learning Research}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/hamesse19a/hamesse19a.pdf}, url = {https://proceedings.mlr.press/v106/hamesse19a.html}, abstract = {Achilles Tendon Rupture (ATR) is one of the typical soft tissue injuries. Rehabilitation after such a musculoskeletal injury remains a prolonged process with a very variable outcome. Accurately predicting rehabilitation outcome is crucial for treatment decision support. However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes. In this work, we design an end-to-end probabilistic framework to impute missing data entries and predict rehabilitation outcomes simultaneously. We evaluate our model on a real-life ATR clinical cohort, comparing with various baselines. The proposed method demonstrates its clear superiority over traditional methods which typically perform imputation and prediction in two separate stages.} }
Endnote
%0 Conference Paper %T Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation %A Charles Hamesse %A Ruibo Tu %A Paul Ackermann %A Hedvig Kjellström %A Cheng Zhang %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-hamesse19a %I PMLR %P 614--640 %U https://proceedings.mlr.press/v106/hamesse19a.html %V 106 %X Achilles Tendon Rupture (ATR) is one of the typical soft tissue injuries. Rehabilitation after such a musculoskeletal injury remains a prolonged process with a very variable outcome. Accurately predicting rehabilitation outcome is crucial for treatment decision support. However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes. In this work, we design an end-to-end probabilistic framework to impute missing data entries and predict rehabilitation outcomes simultaneously. We evaluate our model on a real-life ATR clinical cohort, comparing with various baselines. The proposed method demonstrates its clear superiority over traditional methods which typically perform imputation and prediction in two separate stages.
APA
Hamesse, C., Tu, R., Ackermann, P., Kjellström, H. & Zhang, C.. (2019). Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation. Proceedings of the 4th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 106:614-640 Available from https://proceedings.mlr.press/v106/hamesse19a.html.

Related Material