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.

Efficient Heparin Recovery from Porcine Intestinal Mucosa Using Zeolite Imidazolate Framework-8.

Heparin is one of the most valuable active pharmaceutical ingredients, and it is generally isolated from porcine intestinal mucosa. Traditionally, different types of commercial resins are employed as an adsorbent for heparin uptake; however, using new, less expensive adsorbents has attracted more interest in the past few years to enhance the heparin recovery. Zeolite imidazolate framework-8 (ZIF-8), as a metal-organic framework (MOF) with a high surface area, porosity, and good stability at high temperatures, was selected to examine the heparin recovery. In this research, we demonstrate that ZIF-8 can recover up to ~70% (37 mg g-1) of heparin from porcine intestinal mucosa. A mechanistic study through kinetic and thermodynamic models on the adsorption revealed appropriate surface conditions for the adsorption of heparin molecules. The effect of different variables such as pH and temperature on heparin adsorption was also studied to optimize the recovery. This study is the first to investigate the usage of MOFs for heparin uptake.

Streamlining the KOOS Activities of Daily Living Subscale Using Machine Learning.

Background: Functional outcome scores provide valuable data, yet they can be burdensome to patients and require significant resources to administer. The Knee injury and Osteoarthritis Outcome Score (KOOS) is a knee-specific patient-reported outcome measure (PROM) and is validated for anterior cruciate ligament (ACL) reconstruction outcomes. The KOOS requires 42 questions in 5 subscales. We utilized a machine learning (ML) algorithm to determine whether the number of questions and the resultant burden to complete the survey can be lowered in a subset (activities of daily living; ADL) of KOOS, yet still provide identical data. Hypothesis: Fewer questions than the 17 currently provided are actually needed to predict KOOS ADL subscale scores with high accuracy. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: Pre- and postoperative patient-reported KOOS ADL scores were obtained from the Surgical Outcome System (SOS) data registry for patients who had ACL reconstruction. Categorical Boosting (CatBoost) ML models were built to analyze each question and its value in predicting the patient's actual functional outcome (ie, KOOS ADL score). A streamlined set of minimal essential questions were then identified. Results: The SOS registry contained 6185 patients who underwent ACL reconstruction. A total of 2525 patients between the age of 16 and 50 years had completed KOOS ADL scores presurgically and 3 months postoperatively. The data set consisted of 51.84% male patients and 48.16% female patients, with a mean age of 29 years. The CatBoost model predicted KOOS ADL scores with high accuracy when only 6 questions were asked (R2 = 0.95), similar to when all 17 questions of the subscale were asked (R2 = 0.99). Conclusion: ML algorithms successfully identified the essential questions in the KOOS ADL questionnaire. Only 35% (6/17) of KOOS ADL questions (descending stairs, ascending stairs, standing, walking on flat surface, putting on socks/stockings, and getting on/off toilet) are needed to predict KOOS ADL scores with high accuracy after ACL reconstruction. ML can be utilized successfully to streamline the burden of patient data collection. This, in turn, can potentially lead to improved patient reporting, increased compliance, and increased utilization of PROMs while still providing quality data.