Streamlining the KOOS Activities of Daily Living Subscale Using Machine Learning

Application of machine learning in the context of reoperation, outcome and management after ACL reconstruction - A systematic review

INTRODUCTION

Machine learning-based tools are becoming increasingly popular in clinical practice. They offer new possibilities but are also limited in their reliability and accuracy.

OBJECTIVES

The present systematic review updates and discusses the existing literature regarding machine learning algorithm-based tools to predict outcome and management in patients after ACL reconstruction.

METHOD

PubMed was searched for articles containing machine learning algorithms related to anterior cruciate ligament reconstruction and its outcome and management. No additional filters or time constraints were used. All eligible studies were accessed by hand.

RESULTS

After screening of 115 articles, 15 were included. Six studies evaluated predictors for reoperation after ACL surgery. Four studies investigated the clinical outcome prediction after ACL reconstruction including prediction of secondary meniscus tear and secondary knee osteoarthritis. Single topics addressed in patients with ACL reconstruction were costs, opioid use, the need for a femoral nerve block, short term complications, hospital admission, and reduction of the burden to complete the Knee Osteoarthritis and Outcome score questionnaire. Predictive power was very heterogeneous, depending on the specific research question and parameters included.

CONCLUSION

New machine-learning tools offer interesting insights into variables affecting the target outcome and general management of patients with ACL reconstruction. While present machine-learning based prediction models seem to outperform previous existing benchmark regression models, their predictive ability often is still too low to base individual decision making on them. With the rapid progress observed over the last few years, it is conceivable that this might change, however, in the foreseeable future.

Approaching Artificial Intelligence in Orthopaedics: Predictive Analytics and Machine Learning to Prognosticate Arthroscopic Rotator Cuff Surgical Outcomes

Machine learning (ML) has not yet been used to identify factors predictive for post-operative functional outcomes following arthroscopic rotator cuff repair (ARCR). We propose a novel algorithm to predict ARCR outcomes using machine learning. This is a retrospective cohort study from a prospectively collected database. Data were collected from the Surgical Outcome System Global Registry (Arthrex, Naples, FL, USA). Pre-operative and 3-month, 6-month, and 12-month post-operative American Shoulder and Elbow Surgeons (ASES) scores were collected and used to develop a ML model. Pre-operative factors including demography, comorbidities, cuff tear, tissue quality, and fixation implants were fed to the ML model. The algorithm then produced an expected post-operative ASES score for each patient. The ML-produced scores were compared to actual scores using standard test-train machine learning principles. Overall, 631 patients who underwent shoulder arthroscopy from January 2011 to March 2020 met inclusion criteria for final analysis. A substantial number of the test dataset predictions using the XGBoost algorithm were within the minimal clinically important difference (MCID) and substantial clinical benefit (SCB) thresholds: 67% of the 12-month post-operative predictions were within MCID, while 84% were within SCB. Pre-operative ASES score, pre-operative pain score, body mass index (BMI), age, and tendon quality were the most important features in predicting patient recovery as identified using Shapley additive explanations (SHAP). In conclusion, the proposed novel machine learning algorithm can use pre-operative factors to predict post-operative ASES scores accurately. This can further supplement pre-operative counselling, planning, and resource allocation. Level of Evidence: III.

Machine Learning Can Accurately Predict Overnight Stay, Readmission, and 30-Day Complications Following Anterior Cruciate Ligament Reconstruction

PURPOSE

This study aimed to develop machine learning (ML) models to predict hospital admission (overnight stay) as well as short-term complications and readmission rates following anterior cruciate ligament reconstruction (ACLR). Furthermore, we sought to compare the ML models with logistic regression models in predicting ACLR outcomes.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients who underwent elective ACLR from 2012 to 2018. Artificial neural network ML and logistic regression models were developed to predict overnight stay, 30-day postoperative complications, and ACL-related readmission, and model performance was compared using the area under the receiver operating characteristic curve. Regression analyses were used to identify variables that were significantly associated with the predicted outcomes.

RESULTS

A total of 21,636 elective ACLR cases met inclusion criteria. Variables associated with hospital admission included White race, obesity, hypertension, and American Society of Anesthesiologists classification 3 and greater, anesthesia other than general, prolonged operative time, and inpatient setting. The incidence of hospital admission (overnight stay) was 10.2%, 30-day complications was 1.3%, and 30-day readmission for ACLR-related causes was 0.9%. Compared with logistic regression models, artificial neural network models reported superior area under the receiver operating characteristic curve values in predicting overnight stay (0.835 vs 0.589), 30-day complications (0.742 vs 0.590), reoperation (0.842 vs 0.601), ACLR-related readmission (0.872 vs 0.606), deep-vein thrombosis (0.804 vs 0.608), and surgical-site infection (0.818 vs 0.596).

CONCLUSIONS

The ML models developed in this study demonstrate an application of ML in which data from a national surgical patient registry was used to predict hospital admission and 30-day postoperative complications after elective ACLR. ML models developed performed well, outperforming regression models in predicting hospital admission and short-term complications following elective ACLR. ML models performed best when predicting ACLR-related readmissions and reoperations, followed by overnight stay.

LEVEL OF EVIDENCE

IV, retrospective comparative prognostic trial.

PROMIS Versus Legacy Patient-Reported Outcome Measures for Sports Medicine Patients Undergoing Arthroscopic Knee, Shoulder, and Hip Interventions: A Systematic Review

BACKGROUND

The Patient-Reported Outcomes Measurement Information System (PROMIS®) was designed to monitor the global wellbeing of patients, with the Physical Function Computer-Adaptive Test (PF-CAT) component focused specifically on functional outcome. PROMIS aims for increased item-bank accuracy, lower administrative burden, and decreased floor and ceiling effects compared to legacy patient-reported outcome measures (PROMs). Our primary research outcomes focused on sports medicine surgical populations, which may skew younger or have wide-ranging functional statuses. Specifically, for this population, we questioned if PROMIS PF-CAT was equal to legacy PROMs in (1) construct validity and (2) convergent/divergent validities; and superior to legacy PROMs with respect to (3) survey burden and (4) floor and ceiling effects.

METHODS

Searches were performed in April 2019 in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, utilizing PubMed, Cochrane Central, and Embase databases for Level I-III evidence. This resulted in 541 records, yielding 12 studies for inclusion. PROM data was available for patients undergoing arthroscopic orthopaedic procedures of the knee, shoulder, and hip. Measures of construct validity, convergent/divergent validity, survey burden, and floor/ceiling effects were evaluated for PROMIS PF-CAT versus legacy PROMs.

RESULTS

PROMIS PF-CAT demonstrated excellent or excellent-good correlation with legacy PROMS for physical function and quality of life for patients undergoing arthroscopic interventions of the knee, shoulder, and hip. Compared to legacy PROM instruments, PROMIS PF-CAT demonstrated the lowest overall survey burden and had the lowest overall number of floor or ceiling effects across participants.

CONCLUSION

PROMIS PF-CAT is an accurate, efficient evaluation tool for sports medicine surgical patients. PROMIS PF-CAT strongly correlates with legacy physical function PROMs while having a lower test burden and less incidence of floor and ceiling effects. PROMIS PF-CAT may be an optimal alternative for traditional physical function PROMs in sports medicine patients undergoing arthroscopic procedures. Further studies are required to extend the generalizability of these findings to patients during postoperative timepoints after shoulder and hip interventionsLevel of Evidence: III.

Predicting the Risk of Hypertension Based on Several Easy-to-Collect Risk Factors: A Machine Learning Method

Hypertension is a widespread chronic disease. Risk prediction of hypertension is an intervention that contributes to the early prevention and management of hypertension. The implementation of such intervention requires an effective and easy-to-implement hypertension risk prediction model. This study evaluated and compared the performance of four machine learning algorithms on predicting the risk of hypertension based on easy-to-collect risk factors. A dataset of 29,700 samples collected through a physical examination was used for model training and testing. Firstly, we identified easy-to-collect risk factors of hypertension, through univariate logistic regression analysis. Then, based on the selected features, 10-fold cross-validation was utilized to optimize four models, random forest (RF), CatBoost, MLP neural network and logistic regression (LR), to find the best hyper-parameters on the training set. Finally, the performance of models was evaluated by AUC, accuracy, sensitivity and specificity on the test set. The experimental results showed that the RF model outperformed the other three models, and achieved an AUC of 0.92, an accuracy of 0.82, a sensitivity of 0.83 and a specificity of 0.81. In addition, Body Mass Index (BMI), age, family history and waist circumference (WC) are the four primary risk factors of hypertension. These findings reveal that it is feasible to use machine learning algorithms, especially RF, to predict hypertension risk without clinical or genetic data. The technique can provide a non-invasive and economical way for the prevention and management of hypertension in a large population.

Safety and efficacy of umbilical cord-derived Wharton's jelly compared to hyaluronic acid and saline for knee osteoarthritis: study protocol for a randomized, controlled, single-blind, multi-center trial

BACKGROUND

Osteoarthritis (OA) is the most common joint disorder in the United States of America (USA) with a fast-rising prevalence. Current treatment modalities are limited, and total knee replacement surgeries have shown disadvantages, especially for grade II/III OA. The interest in the use of biologics, including umbilical cord (UC)-derived Wharton's jelly (WJ), has grown in recent years. The results from a preliminary study demonstrated the presence of essential components of regenerative medicine, namely growth factors, cytokines, hyaluronic acid (HA), and extracellular vesicles, including exosomes, in WJ. The proposed study aims to evaluate the safety and efficacy of intra-articular injection of UC-derived WJ for the treatment of knee OA symptoms.

METHODS

A randomized, controlled, single-blind, multi-center, prospective study will be conducted in which the safety and efficacy of intra-articular administration of UC-derived WJ are compared to HA (control) and saline (placebo control) in patients suffering from grade II/III knee OA. A total of 168 participants with grade II or III knee OA on the KL scale will be recruited across 53 sites in the USA with 56 participants in each arm and followed for 1 year post-injection. Patient satisfaction, Numeric Pain Rating Scale, Knee Injury and Osteoarthritis Outcome Score, 36-Item Short Form Survey (SF-36), and 7-point Likert Scale will be used to assess the participants. Physical exams, X-rays, and MRI with Magnetic Resonance Observation of Cartilage Repair Tissue score will be used to assess improvement in associated anatomy.

DISCUSSION

The study results will provide valuable information into the safety and efficacy of intra-articular administration of Wharton's jelly for grade II/III knee osteoarthritis. The results of this study will also add to the treatment options available for grade II/III OA as well as help facilitate the development of a more focused treatment strategy for patients.

TRIAL REGISTRATION

ClinicalTrials.gov, NCT04711304 . Registered on January 15, 2021.

Machine learning model for predicting malaria using clinical information

BACKGROUND

Rapid diagnosing is crucial for controlling malaria. Various studies have aimed at developing machine learning models to diagnose malaria using blood smear images; however, this approach has many limitations. This study developed a machine learning model for malaria diagnosis using patient information.

METHODS

To construct datasets, we extracted patient information from the PubMed abstracts from 1956 to 2019. We used two datasets: a solely parasitic disease dataset and total dataset by adding information about other diseases. We compared six machine learning models: support vector machine, random forest (RF), multilayered perceptron, AdaBoost, gradient boosting (GB), and CatBoost. In addition, a synthetic minority oversampling technique (SMOTE) was employed to address the data imbalance problem.

RESULTS

Concerning the solely parasitic disease dataset, RF was found to be the best model regardless of using SMOTE. Concerning the total dataset, GB was found to be the best. However, after applying SMOTE, RF performed the best. Considering the imbalanced data, nationality was found to be the most important feature in malaria prediction. In case of the balanced data with SMOTE, the most important feature was symptom.

CONCLUSIONS

The results demonstrated that machine learning techniques can be successfully applied to predict malaria using patient information.

Artificial intelligence and machine learning in orthopedic surgery: a systematic review protocol

BACKGROUND

Artificial intelligence (AI) and machine learning (ML) are interwoven into our everyday lives and have grown enormously in some major fields in medicine including cardiology and radiology. While these specialties have quickly embraced AI and ML, orthopedic surgery has been slower to do so. Fortunately, there has been a recent surge in new research emphasizing the need for a systematic review. The primary objective of this systematic review will be to provide an update on the advances of AI and ML in the field of orthopedic surgery. The secondary objectives will be to evaluate the applications of AI and ML in providing a clinical diagnosis and predicting post-operative outcomes and complications in orthopedic surgery.

METHODS

A systematic search will be conducted in PubMed, ScienceDirect, and Google Scholar databases for articles written in English, Italian, French, Spanish, and Portuguese language articles published up to September 2020. References will be screened and assessed for eligibility by at least two independent reviewers as per PRISMA guidelines. Studies must apply to orthopedic interventions and acute and chronic orthopedic musculoskeletal injuries to be considered eligible. Studies will be excluded if they are animal studies and do not relate to orthopedic interventions or if no clinical data were produced. Gold standard processes and practices to obtain a clinical diagnosis and predict post-operative outcomes shall be compared with and without the use of ML algorithms. Any case reports and other primary studies assessing the prediction rate of post-operative outcomes or the ability to identify a diagnosis in orthopedic surgery will be included. Systematic reviews or literature reviews will be examined to identify further studies for inclusion, and the results of meta-analyses will not be included in the analysis.

DISCUSSION

Our findings will evaluate the advances of AI and ML in the field of orthopedic surgery. We expect to find a large quantity of uncontrolled studies and a smaller subset of articles describing actual applications and outcomes for clinical care. Cohort studies and large randomized control trial will likely be needed.

TRIAL REGISTRATION

The protocol will be registered on PROSPERO international prospective register of systematic reviews prior to commencement.