Wolfson, Julian

OBJECTIVES: Extracorporeal cardiopulmonary resuscitation (ECPR) has been shown to improve neurologically favorable survival in patients with refractory out-of-hospital cardiac arrest (OHCA) caused by shockable rhythms. Further refinement of patient selection is needed to focus this resource-intensive therapy on those patients likely to benefit. This study sought to create a selection model using machine learning (ML) tools for refractory cardiac arrest patients undergoing ECPR. DESIGN: Retrospective cohort study. SETTING: Cardiac ICU in a Quaternary Care Center. PATIENTS: Adults 18–75 years old with refractory OHCA caused by a shockable rhythm. METHODS: Three hundred seventy-six consecutive patients with refractory OHCA and a shockable presenting rhythm were analyzed, of which 301 underwent ECPR and cannulation for venoarterial extracorporeal membrane oxygenation. Clinical variables that were widely available at the time of cannulation were analyzed and ranked on their ability to predict neurologically favorable survival. INTERVENTIONS: ML was used to train supervised models and predict favorable neurologic outcomes of ECPR. The best-performing models were internally validated using a holdout test set. MEASUREMENTS AND MAIN RESULTS: Neurologically favorable survival occurred in 119 of 301 patients (40%) receiving ECPR. Rhythm at the time of cannulation, intermittent or sustained return of spontaneous circulation, arrest to extracorporeal membrane oxygenation perfusion time, and lactic acid levels were the most predictive of the 11 variables analyzed. All variables were integrated into a training model that yielded an in-sample area under the receiver-operating characteristic curve (AUC) of 0.89 and a misclassification rate of 0.19. Out-of-sample validation of the model yielded an AUC of 0.80 and a misclassification rate of 0.23, demonstrating acceptable prediction ability. CONCLUSIONS: ML can develop a tiered risk model to guide ECPR patient selection with tailored arrest profiles.

AbstractPurposeAccurate prediction of outcome following hip arthroscopy is challenging and machine learning has the potential to improve our predictive capability. The purpose of this study was to determine if machine learning analysis of the Danish Hip Arthroscopy Registry (DHAR) can develop a clinically meaningful calculator for predicting the probability of a patient undergoing subsequent revision surgery following primary hip arthroscopy.MethodsMachine learning analysis was performed on the DHAR. The primary outcome for the models was probability of revision hip arthroscopy within 1, 2, and/or 5 years after primary hip arthroscopy. Data were split randomly into training (75%) and test (25%) sets. Four models intended for these types of data were tested: Cox elastic net, random survival forest, gradient boosted regression (GBM), and super learner. These four models represent a range of approaches to statistical details like variable selection and model complexity. Model performance was assessed by calculating calibration and area under the curve (AUC). Analysis was performed using only variables available in the pre‐operative clinical setting and then repeated to compare model performance using all variables available in the registry.ResultsIn total, 5581 patients were included for analysis. Average follow‐up time or time‐to‐revision was 4.25 years (± 2.51) years and overall revision rate was 11%. All four models were generally well calibrated and demonstrated concordance in the moderate range when restricted to only pre‐operative variables (0.62–0.67), and when considering all variables available in the registry (0.63–0.66). The 95% confidence intervals for model concordance were wide for both analyses, ranging from a low of 0.53 to a high of 0.75, indicating uncertainty about the true accuracy of the models.ConclusionThe association between pre‐surgical factors and outcome following hip arthroscopy is complex. Machine learning analysis of the DHAR produced a model capable of predicting revision surgery risk following primary hip arthroscopy that demonstrated moderate accuracy but likely limited clinical usefulness. Prediction accuracy would benefit from enhanced data quality within the registry and this preliminary study holds promise for future model generation as the DHAR matures. Ongoing collection of high‐quality data by the DHAR should enable improved patient‐specific outcome prediction that is generalisable across the population.Level of evidenceLevel III.

AbstractPurposeExternal validation of machine learning predictive models is achieved through evaluation of model performance on different groups of patients than were used for algorithm development. This important step is uncommonly performed, inhibiting clinical translation of newly developed models. Machine learning analysis of the Norwegian Knee Ligament Register (NKLR) recently led to the development of a tool capable of estimating the risk of anterior cruciate ligament (ACL) revision (https://swastvedt.shinyapps.io/calculator_rev/). The purpose of this study was to determine the external validity of the NKLR model by assessing algorithm performance when applied to patients from the Danish Knee Ligament Registry (DKLR).MethodsThe primary outcome measure of the NKLR model was probability of revision ACL reconstruction within 1, 2, and/or 5 years. For external validation, all DKLR patients with complete data for the five variables required for NKLR prediction were included. The five variables included graft choice, femur fixation device, KOOS QOL score at surgery, years from injury to surgery, and age at surgery. Predicted revision probabilities were calculated for all DKLR patients. The model performance was assessed using the same metrics as the NKLR study: concordance and calibration.ResultsIn total, 10,922 DKLR patients were included for analysis. Average follow‐up time or time‐to‐revision was 8.4 (± 4.3) years and overall revision rate was 6.9%. Surgical technique trends (i.e., graft choice and fixation devices) and injury characteristics (i.e., concomitant meniscus and cartilage pathology) were dissimilar between registries. The model produced similar concordance when applied to the DKLR population compared to the original NKLR test data (DKLR: 0.68; NKLR: 0.68–0.69). Calibration was poorer for the DKLR population at one and five years post primary surgery but similar to the NKLR at two years.ConclusionThe NKLR machine learning algorithm demonstrated similar performance when applied to patients from the DKLR, suggesting that it is valid for application outside of the initial patient population. This represents the first machine learning model for predicting revision ACL reconstruction that has been externally validated. Clinicians can use this in‐clinic calculator to estimate revision risk at a patient specific level when discussing outcome expectations pre‐operatively. While encouraging, it should be noted that the performance of the model on patients undergoing ACL reconstruction outside of Scandinavia remains unknown.Level of evidenceIII.

Background: Several factors are associated with an increased risk of anterior cruciate ligament (ACL) reconstruction revision. However, the ability to accurately translate these factors into a quantifiable risk of revision at a patient-specific level has remained elusive. We sought to determine if machine learning analysis of the Norwegian Knee Ligament Register (NKLR) can identify the most important risk factors associated with subsequent revision of primary ACL reconstruction and develop a clinically meaningful calculator for predicting revision of primary ACL reconstruction. Methods: Machine learning analysis was performed on the NKLR data set. The primary outcome was the probability of revision ACL reconstruction within 1, 2, and/or 5 years. Data were split randomly into training sets (75%) and test sets (25%). Four machine learning models were tested: Cox Lasso, survival random forest, generalized additive model, and gradient boosted regression. Concordance and calibration were calculated for all 4 models. Results: The data set included 24,935 patients, and 4.9% underwent a revision surgical procedure during a mean follow-up (and standard deviation) of 8.1 ± 4.1 years. All 4 models were well-calibrated, with moderate concordance (0.67 to 0.69). The Cox Lasso model required only 5 variables for outcome prediction. The other models either used more variables without an appreciable improvement in accuracy or had slightly lower accuracy overall. An in-clinic calculator was developed that can estimate the risk of ACL revision (Revision Risk Calculator). This calculator can quantify risk at a patient-specific level, with a plausible range from near 0% for low-risk patients to 20% for high-risk patients at 5 years. Conclusions: Machine learning analysis of a national knee ligament registry can predict the risk of ACL reconstruction revision with moderate accuracy. This algorithm supports the creation of an in-clinic calculator for point-of-care risk stratification based on the input of only 5 variables. Similar analysis using a larger or more comprehensive data set may improve the accuracy of risk prediction, and future studies incorporating patients who have experienced failure of ACL reconstruction but have not undergone subsequent revision may better predict the true risk of ACL reconstruction failure. Level of Evidence: Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

HIV is an independent risk factor for lung disease, including chronic obstructive pulmonary disease (COPD) and emphysema. Angiotensin receptor blockers may be beneficial in COPD and emphysema through pathways that have been implicated in HIV-related lung disease. We performed a randomized comparison of the effects of losartan versus placebo on the plasma concentrations of the pneumoproteins, surfactant protein D (SPD) and club cell secretory protein (CCSP), in people living with HIV (PLWH). A total of 108 PLWH were included (52 assigned to losartan and 56 assigned to placebo). We found no difference in the change from baseline in log 2 concentrations of CCSP or SPD over 1 year of follow-up. For SPD, we found a strong interaction by CD4+ counts, where those with CD4+ counts >350 cells/mm 3 treated with losartan had more reduction (improvement) in SPD concentration than those treated with placebo ( p value for interaction <.001). In conclusion, we did not find a beneficial effect of losartan on pneumoprotein concentrations in PLWH, but PLWH with higher CD4+ counts may have improvement in SPD when treated with losartan.

Background: Persistent inflammation and incomplete immune recovery among persons with HIV (PHIV) are associated with increased disease risk. We hypothesized that the angiotensin receptor blocker (ARB) losartan would reduce inflammation by mitigating nuclear factor (NF)κB responses and promote T-cell recovery via inhibition of transforming growth factor-beta (TGFβ)-mediated fibrosis. Methods: Losartan (100 mg) versus placebo over 12 months was investigated in a randomized (1 : 1) placebo-controlled trial, among PHIV age at least 50 years, receiving antiretroviral therapy (ART), with HIV RNA less than 200 copies/ml and CD4+ cell count 600 cells/μl or less. Inflammation, fibrosis and myocardial biomarkers were measured in blood using ELISA, electrochemiluminescence and immunoturbidimetric methods, and T-cell and monocyte phenotypes were assessed with flow cytometry among a subset of participants. Changes over follow-up in (log-2 transformed) biomarkers and cell phenotypes (untransformed) were compared between losartan and placebo arms using linear mixed models. Results: Among 108 PHIV (n = 52 to losartan; n = 56 to placebo), 97% had a month 12 visit. Median age was 57 years and baseline CD4+ cell count was 408 cells/μl. Losartan treatment was not associated with an improvement in interleukin-6 levels, or other blood measures of inflammation, immune activation, fibrosis activity or myocardial function. CD4+ and CD8+ T cells also did not differ by treatment group. Losartan reduced SBP and DBP by 6 and 5 mmHg, respectively. Conclusion: Among older PHIV with viral suppression, losartan did not improve blood measures of inflammation nor T-cell immune recovery. Losartan treatment is unlikely to reduce inflammation associated comorbidities to a clinically meaningful degree, beyond the benefits from lowering blood pressure. ClinicalTrials.gov: NCT02049307.

Elderly seasonal migrators share time between homes in different states, presenting challenges for care coordination and patient attribution methods. Medicare has prioritized alternative payment models, putting health care providers at risk for quality and value of services delivered to their attributed patients, regardless of the location of care. Little research is available to guide providers and payers on the service use of seasonal migrators. The authors use claims data on fee-for-service (FFS) Medicare beneficiaries' locations throughout the year to (1) identify seasonal migrators and (2) describe the care they receive in each seasonal home, focusing on primary care and emergency department (ED) visits and the relationships between the two. In all, 5.5% of the Medicare aged FFS population were identified as seasonal migrators, with 4.1% following the traditional snowbird pattern of migration, spending warm months in the north and cold months in the south. Migrators had higher rates of ED visits and primary care treatable (PCT) ED visits than the nonmigratory groups, controlling for location, age, race, sex, Medicaid status, season, and comorbidities. They also had more visits with specialist physicians, more days with outpatient services, and more days seeing a physician in any setting. Having local primary care strongly reduced rates of both PCT ED visits and total ED visits for all migration categories, with the greatest reduction seen in PCT ED visits by migrators (local primary care was associated with a 58% reduction in PCT ED visits by snowbirds and a 65% reduction in PCT ED visits by other migrators).