Dataset Information

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning.

ABSTRACT: BACKGROUND:Machine-learning classifiers mostly offer good predictive performance and are increasingly used to support shared decision-making in clinical practice. Focusing on performance and practicability, this study evaluates prediction of patient-reported outcomes (PROs) by eight supervised classifiers including a linear model, following hip and knee replacement surgery. METHODS:NHS PRO data (130,945 observations) from April 2015 to April 2017 were used to train and test eight classifiers to predict binary postoperative improvement based on minimal important differences. Area under the receiver operating characteristic, J-statistic and several other metrics were calculated. The dependent outcomes were generic and disease-specific improvement based on the EQ-5D-3L visual analogue scale (VAS) as well as the Oxford Hip and Knee Score (Q score). RESULTS:The area under the receiver operating characteristic of the best training models was around 0.87 (VAS) and 0.78 (Q score) for hip replacement, while it was around 0.86 (VAS) and 0.70 (Q score) for knee replacement surgery. Extreme gradient boosting, random forests, multistep elastic net and linear model provided the highest overall J-statistics. Based on variable importance, the most important predictors for post-operative outcomes were preoperative VAS, Q score and single Q score dimensions. Sensitivity analysis for hip replacement VAS evaluated the influence of minimal important difference, patient selection criteria as well as additional data years. Together with a small benchmark of the NHS prediction model, robustness of our results was confirmed. CONCLUSIONS:Supervised machine-learning implementations, like extreme gradient boosting, can provide better performance than linear models and should be considered, when high predictive performance is needed. Preoperative VAS, Q score and specific dimensions like limping are the most important predictors for postoperative hip and knee PROMs.

SUBMITTER: Huber M

PROVIDER: S-EPMC6325823 | biostudies-other | 2019 Jan

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning.

Huber Manuel M Kurz Christoph C Leidl Reiner R

BMC medical informatics and decision making 20190108 1

<h4>Background</h4>Machine-learning classifiers mostly offer good predictive performance and are increasingly used to support shared decision-making in clinical practice. Focusing on performance and practicability, this study evaluates prediction of patient-reported outcomes (PROs) by eight supervised classifiers including a linear model, following hip and knee replacement surgery.<h4>Methods</h4>NHS PRO data (130,945 observations) from April 2015 to April 2017 were used to train and test eight ...[more]

PMID: 30621670

Similar Datasets

Project description:BackgroundPatients undergoing hip or knee replacement are at high risk of developing a postoperative venous thromboembolism even after discharge from hospital. We sought to identify hospital and patient characteristics associated with receiving thromboprophylaxis after discharge and to compare the risk of short-term mortality among those who did or did not receive thromboprophylaxis.MethodsWe conducted a retrospective cohort study using system-wide hospital discharge summary records, physician billing information, medication reimbursement claims and demographic records. We included patients aged 65 years and older who received a hip or knee replacement and who were discharged home after surgery.ResultsIn total we included 10 744 patients. Of these, 7058 patients who received a hip replacement and 3686 who received a knee replacement. The mean age was 75.4 (standard deviation [SD] 6.8) years and 38% of patients were men. In total, 2059 (19%) patients received thomboprophylaxis at discharge. Patients discharged from university teaching hospitals were less likely than those discharged from community hospitals to received thromboprophylaxis after discharge (odds ratio [OR] 0.89, 95% confidence interval [CI] 0.80-1.00). Patients were less likely to receive thromboprophylaxis after discharge if they had a longer hospital stay (15-30 days v. 1-7 days, OR 0.69, 95% CI 0.59-0.81). Patients were more likely to receive thromboprophylaxis if they had hip (v. knee) replacement, osteoarthritis, heart failure, atrial fibrillation or hypertension, higher (v. lower) income or if they were treated at medium-volume hospitals (69-116 hip and knee replacements per year). In total, 223 patients (2%) died in the 3-month period after discharge. The risk of short-term mortality was lower among those who received thromboprophylaxis after discharge (hazard ratio [HR] 0.34, 95% CI 0.20-0.57).InterpretationFewer than 1 in 5 elderly patients discharged home after a hip-or knee-replacement surgery received postdischarge thromboprophylaxis. Those prescribed these medications had a lower risk of short-term mortality. The benefits of and barriers to thromboprophylaxis therapy after discharge in this population requires further study.

Project description:BACKGROUND:Gait analysis can be used to measure variations in joint function in patients with knee osteoarthritis (OA), and is useful when observing longitudinal biomechanical changes following Total Knee Replacement (TKR) surgery. The Cardiff Classifier is an objective classification tool applied previously to examine the extent of biomechanical recovery following TKR. In this study, it is further developed to reveal the salient features that contribute to recovery towards healthy function. METHODS:Gait analysis was performed on 30 patients before and after TKR surgery, and 30 healthy controls. Median TKR follow-up time was 13 months. The combined application of principal component analysis (PCA) and the Cardiff Classifier defined 18 biomechanical features that discriminated OA from healthy gait. Statistical analysis tested whether these features were affected by TKR surgery and, if so, whether they recovered to values found for the controls. RESULTS:The Cardiff Classifier successfully discriminated between OA and healthy gait in all 60 cases. Of the 18 discriminatory features, only six (33%) were significantly affected by surgery, including features in all three planes of the ground reaction force (p<0.001), ankle dorsiflexion moment (p<0.001), hip adduction moment (p = 0.003), and transverse hip angle (p = 0.007). All but two (89%) of these features remained significantly different to those of the control group after surgery. CONCLUSIONS:This approach was able to discriminate gait biomechanics associated with knee OA. The ground reaction force provided the strongest discriminatory features. Despite increased gait velocity and improvements in self-reported pain and function, which would normally be clinical indicators of recovery, the majority of features were not affected by TKR surgery. This TKR cohort retained pre-operative gait patterns; reduced sagittal hip and knee moments, decreased knee flexion, increased hip flexion, and reduced hip adduction. The changes that were associated with surgery were predominantly found at the ankle and hip, rather than at the knee.

Project description:BackgroundTotal joint replacements are high-volume and high-cost procedures that should be monitored for cost and quality control. Models that can identify patients at high risk of readmission might help reduce costs by suggesting who should be enrolled in preventive care programs. Previous models for risk prediction have relied on structured data of patients rather than clinical notes in electronic health records (EHRs). The former approach requires manual feature extraction by domain experts, which may limit the applicability of these models.ObjectiveThis study aims to develop and evaluate a machine learning model for predicting the risk of 30-day readmission following knee and hip arthroplasty procedures. The input data for these models come from raw EHRs. We empirically demonstrate that unstructured free-text notes contain a reasonably predictive signal for this task.MethodsWe performed a retrospective analysis of data from 7174 patients at Partners Healthcare collected between 2006 and 2016. These data were split into train, validation, and test sets. These data sets were used to build, validate, and test models to predict unplanned readmission within 30 days of hospital discharge. The proposed models made predictions on the basis of clinical notes, obviating the need for performing manual feature extraction by domain and machine learning experts. The notes that served as model inputs were written by physicians, nurses, pathologists, and others who diagnose and treat patients and may have their own predictions, even if these are not recorded.ResultsThe proposed models output readmission risk scores (propensities) for each patient. The best models (as selected on a development set) yielded an area under the receiver operating characteristic curve of 0.846 (95% CI 82.75-87.11) for hip and 0.822 (95% CI 80.94-86.22) for knee surgery, indicating reasonable discriminative ability.ConclusionsMachine learning models can predict which patients are at a high risk of readmission within 30 days following hip and knee arthroplasty procedures on the basis of notes in EHRs with reasonable discriminative power. Following further validation and empirical demonstration that the models realize predictive performance above that which clinical judgment may provide, such models may be used to build an automated decision support tool to help caretakers identify at-risk patients.

Project description:BACKGROUND:Chronic spinal pain conditions affect millions of US adults and carry a high healthcare cost burden, both direct and indirect. Conservative interventions for spinal pain conditions, including chiropractic care, have been associated with lower healthcare costs and improvements in pain status in different clinical populations, including veterans. Little is currently known about predicting healthcare service utilization in the domain of conservative interventions for spinal pain conditions, including the frequency of use of chiropractic services. The purpose of this retrospective cohort study was to explore the use of supervised machine learning approaches to predicting one-year chiropractic service utilization by veterans receiving VA chiropractic care. METHODS:We included 19,946 veterans who entered the Musculoskeletal Diagnosis Cohort between October 1, 2003 and September 30, 2013 and utilized VA chiropractic services within one year of cohort entry. The primary outcome was one-year chiropractic service utilization following index chiropractic visit, split into quartiles represented by the following classes: 1 visit, 2 to 3 visits, 4 to 6 visits, and 7 or greater visits. We compared the performance of four multiclass classification algorithms (gradient boosted classifier, stochastic gradient descent classifier, support vector classifier, and artificial neural network) in predicting visit quartile using 158 sociodemographic and clinical features. RESULTS:The selected algorithms demonstrated poor prediction capabilities. Subset accuracy was 42.1% for the gradient boosted classifier, 38.6% for the stochastic gradient descent classifier, 41.4% for the support vector classifier, and 40.3% for the artificial neural network. The micro-averaged area under the precision-recall curve for each one-versus-rest classifier was 0.43 for the gradient boosted classifier, 0.38 for the stochastic gradient descent classifier, 0.43 for the support vector classifier, and 0.42 for the artificial neural network. Performance of each model yielded only a small positive shift in prediction probability (approximately 15%) compared to naïve classification. CONCLUSIONS:Using supervised machine learning to predict chiropractic service utilization remains challenging, with only a small shift in predictive probability over naïve classification and limited clinical utility. Future work should examine mechanisms to improve model performance.

Dataset Information

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning.

Publications

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets