Patient Factors That Matter in Predicting Hip Arthroplasty Outcomes: A Machine-Learning Approach.

BACKGROUND: Despite the success of total hip arthroplasty (THA), approximately 10%-15% of patients will be dissatisfied with their outcome. Identifying patients at risk of not achieving meaningful gains postoperatively is critical to pre-surgical counseling and clinical decision support. Machine learning has shown promise in creating predictive models. This study used a machine-learning model to identify patient-specific variables that predict the postoperative functional outcome in THA. METHODS: A prospective longitudinal cohort of 160 consecutive patients undergoing total hip replacement for the treatment of degenerative arthritis completed self-reported measures preoperatively and at 3 months postoperatively. Using four types of independent variables (patient demographics, patient-reported health, cognitive appraisal processes and surgical approach), a machine-learning model utilizing Least Absolute Shrinkage Selection Operator (LASSO) was constructed to predict postoperative Hip Disability and Osteoarthritis Outcome Score (HOOS) at 3 months. RESULTS: The most predictive independent variables of postoperative HOOS were cognitive appraisal processes. Variables that predicted a worse HOOS consisted of frequent thoughts of work (ß = -0.34), frequent comparison to healthier peers (ß = -0.26), increased body mass index (ß = -0.17), increased medical comorbidities (ß = -0.19), and the anterior surgical approach (ß = -0.15). Variables that predicted a better HOOS consisted of employment at the time of surgery (ß = 0.17), and thoughts related to family interaction (ß = 0.12), trying not to complain (ß = 0.13), and helping others (ß = 0.22). CONCLUSIONS: This clinical prediction model in THA revealed that the factors most predictive of outcome were cognitive appraisal processes, demonstrating their importance to outcome-based research. LEVEL OF EVIDENCE: Prognostic Level 1.

Ex vivo HIV entry into blood CD4+ T cells does not predict heterosexual HIV acquisition in women.

BACKGROUND: A blood-based assay that could quantify HIV susceptibility would be very valuable for HIV prevention research. Previously, we developed and validated an ex vivo, flow-based, HIV entry assay to assess genital HIV susceptibility in endocervical CD4+ T cells. METHODS: Here we assessed whether this tool could be used to predict HIV risk using blood-derived CD4+ T cells in a rigorously-blinded, nested case-control study using blood samples collected from high-risk, HIV-uninfected South African women enrolled in the CAPRISA 004 clinical trial. Cases, subsequently acquiring HIV were sampled prior to HIV infection and compared with controls, who remained HIV-uninfected. The primary endpoint was ex vivo entry of a CCR5-tropic HIV founder virus into blood CD4+ T cells. Secondary endpoints included HIV entry into CD4+ central (TCM) and effector (TEM) memory T cells, and into CD4+ T cell subsets expressing CCR5, CD69, CCR6, α4ß1 or α4ß7. RESULTS: Compared to bulk CD4+ T cells (4.9% virus entry), CD4+ T cells expressing CCR5, CCR6 or α4ß1 and TEM were highly susceptible (15.5%, 8.8%, 8.2% and 10.8% entry, respectively, all p<0.0001), while TCM, CD69+ or α4ß7+ CD4+ cells were moderately susceptible (6.4%, 6.0% and 5.8% respectively, p ≤ 0.003). While the proportion of the aforementioned highly susceptible cells correlated with overall virus entry into CD4+ T cells within an individual (r = 0.68, 0.47, 0.67, and 0.60 respectively, p<0.0001), blood virus entry did not predict subsequent mucosal HIV acquisition after controlling for sexual behaviour and condom use (OR 0.92, 95% CI 0.77-1.11, p = 0.40). CONCLUSIONS: Although virus entry identified several previously known highly susceptible cellular HIV targets, blood HIV entry did not predict subsequent heterosexual HIV acquisition. Assessment of mucosal HIV susceptibility may require sampling at the site of HIV exposure.