A machine learning framework for optimizing obesity care by simulating clinical trajectories and targeted interventions.

OBJECTIVE: This study aimed to determine the important clinical management bottlenecks that contribute to underuse of weight loss surgery (WLS) and assess risk factors for attrition at each of them. METHODS: A multistate conceptual model of progression from primary care to WLS was developed and used to study all adults who were seen by a primary care provider (PCP) and eligible for WLS from 2016 to 2017 at a large institution. Outcomes were progression from each state to each subsequent state in the model: PCP visit, endocrine weight management referral, endocrine weight management visit, WLS referral, WLS visit, and WLS. RESULTS: Beginning with an initial PCP visit, the respective 2-year Kaplan-Meier estimate for each outcome was 35% (n = 2063), 15.6% (n = 930), 6.3% (n = 400), 4.7% (n = 298), and 1.0% (n = 69) among 5876 eligible patients. Individual providers and clinics differed significantly in their referral practices. Female patients, younger patients, those with higher BMI, and those seen by trainees were more likely to progress. A simulated intervention to increase referrals among PCPs would generate about 49 additional WLS procedures over 3 years. CONCLUSIONS: This study discovered novel insights into the specific dynamics underlying low WLS use rates. This methodology permits in silico testing of interventions designed to optimize obesity care prior to implementation.

Intermittent claudication treatment patterns in the commercially insured non-Medicare population.

OBJECTIVE: Despite published guidelines and data for Medicare patients, it is uncertain how younger patients with intermittent claudication (IC) are treated. Additionally, the degree to which treatment patterns have changed over time with the expansion of endovascular interventions and outpatient centers is unclear. Our goal was to characterize IC treatment patterns in the commercially insured non-Medicare population. METHODS: The IBM MarketScan Commercial Database, which includes more than 8 billion US commercial insurance claims, was queried for patients newly diagnosed with IC from 2007 to 2016. Patient demographics, medication profiles, and open/endovascular interventions were evaluated. Time trends were modeled using simple linear regression and goodness-of-fit was assessed with coefficients of determination (R2). A patient-centered cohort sample and a procedure-focused dataset were analyzed. RESULTS: Among 152,935,013 unique patients in the database, there were 300,590 patients newly diagnosed with IC. The mean insurance coverage was 4.4 years. The median patients age was 58 years and 56% of patients were male. The prevalence of statin use was 48% among patients at the time of IC diagnosis and increased to 52% among patients after one year from diagnosis. Interventions were performed in 14.3%, of whom 20% and 6% underwent two or more and three or more interventions, respectively. The median time from diagnosis to intervention decreased from 230 days in 2008 days to 49 days in 2016 (R2 = 0.98). There were 16,406 inpatient and 102,925 ambulatory interventions for IC over the study period. Among ambulatory interventions, 7.9% were performed in office-based/surgical centers. The proportion of atherectomies performed in the ambulatory setting increased from 9.7% in 2007 to 29% in 2016 (R2 = 0.94). In office-based/surgical centers, 57.6% of interventions for IC used atherectomy in 2016. Atherectomy was used in ambulatory interventions by cardiologists in 22.6%, surgeons in 15.2%, and radiologists in 13.6% of interventions. Inpatient atherectomy rates remained stable over the study period. Open and endovascular tibial interventions were performed in 7.9% and 7.8% of ambulatory and inpatient IC interventions, respectively. Tibial bypasses were performed in 8.2% of all open IC interventions. CONCLUSIONS: There has been shorter time to intervention in the treatment of younger, commercially insured patients with IC, with many receiving multiple interventions. Statin use was low. Ambulatory procedures, especially in office-based/surgical centers, increasingly used atherectomy, which was not observed in inpatient settings.

Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery: an analysis of the MBSAQIP database.

BACKGROUND: Postoperative gastrointestinal leak and venous thromboembolism (VTE) are devastating complications of bariatric surgery. The performance of currently available predictive models for these complications remains wanting, while machine learning has shown promise to improve on traditional modeling approaches. The purpose of this study was to compare the ability of two machine learning strategies, artificial neural networks (ANNs), and gradient boosting machines (XGBs) to conventional models using logistic regression (LR) in predicting leak and VTE after bariatric surgery. METHODS: ANN, XGB, and LR prediction models for leak and VTE among adults undergoing initial elective weight loss surgery were trained and validated using preoperative data from 2015 to 2017 from Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program database. Data were randomly split into training, validation, and testing populations. Model performance was measured by the area under the receiver operating characteristic curve (AUC) on the testing data for each model. RESULTS: The study cohort contained 436,807 patients. The incidences of leak and VTE were 0.70% and 0.46%. ANN (AUC 0.75, 95% CI 0.73-0.78) was the best-performing model for predicting leak, followed by XGB (AUC 0.70, 95% CI 0.68-0.72) and then LR (AUC 0.63, 95% CI 0.61-0.65, p < 0.001 for all comparisons). In detecting VTE, ANN, and XGB, LR achieved similar AUCs of 0.65 (95% CI 0.63-0.68), 0.67 (95% CI 0.64-0.70), and 0.64 (95% CI 0.61-0.66), respectively; the performance difference between XGB and LR was statistically significant (p = 0.001). CONCLUSIONS: ANN and XGB outperformed traditional LR in predicting leak. These results suggest that ML has the potential to improve risk stratification for bariatric surgery, especially as techniques to extract more granular data from medical records improve. Further studies investigating the merits of machine learning to improve patient selection and risk management in bariatric surgery are warranted.

Untangling the Neural Circuits for Sexual Behavior.

In this issue, Ishii and colleagues identify an anatomically and genetically defined circuit by which a single compound, exocrine gland-secreted peptide-1 (ESP1), enhances reproductive behavior in female mice.

Management of civilian and military vascular trauma: lessons learned.

Management of vascular trauma has evolved tremendously since the turn of the 20(th) century. The lessons from each major military conflict over the past 100 years have refined our understanding of how to care for soldiers and civilians with vascular injuries. The recent wars in Iraq and Afghanistan have likewise improved our strategy for treating victims of vascular trauma. Understanding the principles that guide management of vascular injuries will result in preservation of life and limb.

Endovascular management of the popliteal artery: comparison of atherectomy and angioplasty.

PURPOSE: Symptomatic atherosclerotic disease of the popliteal artery presents challenges for endovascular therapy. We evaluated the technical success, complications, and midterm outcomes of atherectomy and angioplasty involving the popliteal segment. METHODS: We conducted a retrospective review of outcomes of popliteal artery intervention using atherectomy or angioplasty performed between 2003 and 2008. RESULTS: A total of 56 patients (36% women, age 72.8 +/- 12.2 years, 77% critical limb ischemia) underwent popliteal atherectomy (n = 18) or angioplasty (n = 38). These patients had similar clinical characteristics, TransAtlantic Intersociety Consensus (TASC)/ TASC II classification, mean lesion length, and runoff scores. We observed a trend toward higher rates of technical success defined as <30% residual stenosis after atherectomy compared to angioplasty (94% vs 71%, P = .08). While angioplasty was associated with a higher frequency of arterial dissection (23% vs 0%, P = .003), atherectomy was associated with a higher rate of thromboembolic events (22% vs 0%, P = 0.01). Adjunctive stenting was used more frequently following angioplasty compared to atherectomy (45% vs 6%, P = .005). Thrombolysis was used to treat embolization in 4 patients in the atherectomy group. The improvement in the ankle-brachial index (ABI) was similar between the 2 treatment groups. Primary patency of the popliteal artery at 3, 6, and 12 months was 94%, 88%, and 75% in the atherectomy group and 89%, 82%, and 73% in the angioplasty group (P = not significant [NS]). There were no significant differences in limb salvage and freedom from reintervention at 1 year between the atherectomy and angioplasty groups. CONCLUSIONS: Our experience with popliteal artery endovascular therapy indicates a distinct pattern of procedural complications with atherectomy compared to angioplasty but similar midterm patency, limb salvage, and freedom from intervention.

Predictive value of reactive hyperemia for cardiovascular events in patients with peripheral arterial disease undergoing vascular surgery.

OBJECTIVE: Reactive hyperemia is the compensatory increase in blood flow that occurs after a period of tissue ischemia, and this response is blunted in patients with cardiovascular risk factors. The predictive value of reactive hyperemia for cardiovascular events in patients with atherosclerosis and the relative importance of reactive hyperemia compared with other measures of vascular function have not been previously studied. METHODS AND RESULTS: We prospectively measured reactive hyperemia and brachial artery flow-mediated dilation by ultrasound in 267 patients with peripheral arterial disease referred for vascular surgery (age 66+/-11 years, 26% female). Median follow-up was 309 days (range 1 to 730 days). Fifty patients (19%) had an event, including cardiac death (15), myocardial infarction (18), unstable angina (8), congestive heart failure (6), and nonhemorrhagic stroke (3). Patients with an event were older and had lower hyperemic flow velocity (75+/-39 versus 95+/-50 cm/s, P=0.009). Patients with an event also had lower flow-mediated dilation (4.5+/-3.0 versus 6.9+/-4.6%, P<0.001), and when these 2 measures of vascular function were included in the same Cox proportional hazards model, lower hyperemic flow (OR 2.7, 95% CI 1.2 to 5.9, P=0.018) and lower flow-mediated dilation (OR 4.2, 95% CI: 1.8 to 9.8, P=0.001) both predicted cardiovascular events while adjusting for other risk factors. CONCLUSIONS: Thus, lower reactive hyperemia is associated with increased cardiovascular risk in patients with peripheral arterial disease. Furthermore, flow-mediated dilation and reactive hyperemia incrementally relate to cardiovascular risk, although impaired flow-mediated dilation was the stronger predictor in this population. These findings further support the clinical relevance of vascular function measured in the microvasculature and conduit arteries in the upper extremity.

Factors that predict site of outflow target artery anastomosis in infrainguinal revascularization.

INTRODUCTION: Lower extremity revascularization is indicated for limb salvage and incapacitating leg claudication. Many risk factors (age, hypertension, diabetes, tobacco use, dyslipidemia, etc) have been associated with atherosclerosis and the development of peripheral arterial occlusive disease. However, whether these risk factors or the surgical indication (claudication or limb salvage) influences the extent and location of infrainguinal disease and hence the target artery (distal anastomosis) is unclear. This study examines the risk factors and indication for infrainguinal revascularization with respect to the type of bypass performed. METHODS: Three hundred fifty-two infrainguinal revascularizations in 282 patients were retrospectively reviewed. Patient data, including demographics, cardiovascular risk factors, indications, types of revascularization, and perioperative complications and mortality, were collected. Data were analyzed with t test, chi(2) test, Fisher exact test, and multiple logistic regression. RESULTS: The indication for surgical revascularization was claudication in 70 patients and limb salvage in 282. The likelihood of a popliteal anastomosis (above or below knee) versus a tibial or pedal anastomosis was decreased with increasing age (P =.002) and diabetes (P =.0001), and smoking increased the likelihood (P =.056). However, popliteal bypass also was strongly associated with claudication as the surgical indication (odds ratio [OR], 8.7; P =.0001), and 90% of the claudicant group had undergone popliteal anastomosis. Claudication and popliteal anastomosis were both linked to smoking; 97% of subjects who underwent operation for claudication were smokers compared with 75% of subjects who underwent tibial or pedal anastomosis for limb salvage (P =.001). After adjustment for indication, the likelihood of popliteal anastomosis was still decreased with diabetes (OR, 0.46; P =.002), and age had a borderline significant effect (P =.077). When the analysis was stratified by indication for surgery, the likelihood of popliteal bypass among patients who underwent operation for claudication was not influenced by age, diabetes, or smoking. However, within the subset of patients who underwent operation for limb salvage, the likelihood of any popliteal anastomosis was diminished by diabetes (OR, 0.50; P =.007), age (OR, 0.968 per year; P =.01), and chronic renal insufficiency (OR, 0.476; P =.04). CONCLUSION: Infrainguinal peripheral arterial occlusive disease is not a homogenous disease entity. Claudication and limb salvage are associated with two distinct patterns of vascular disease with different risk factors. Patients who undergo operation for claudication are seen at an earlier age, have a high prevalence of smoking, and have proximal disease and a greater likelihood of a popliteal anastomosis. In contrast, patients for limb salvage are less likely to have a popliteal bypass, favoring a more distal target outflow anastomosis that is strongly influenced by advanced age, diabetes, and chronic renal insufficiency.