Development of Predictive Models to Inform a Novel Risk Categorization Framework for Antibiotic Resistance in E. coli-Causing Uncomplicated Urinary Tract Infection.

BACKGROUND: In clinical practice, challenges in identifying patients with uncomplicated urinary tract infections (uUTIs) at risk of antibiotic non-susceptibility may lead to inappropriate prescribing and contribute to antibiotic resistance. We developed predictive models to quantify risk of non-susceptibility to four commonly prescribed antibiotic classes for uUTI, identify predictors of non-susceptibility to each class, and construct a corresponding risk categorization framework for non-susceptibility. METHODS: Eligible females aged ≥12 years with E. coli-caused uUTI were identified from Optum's de-identified Electronic Health Record dataset (10/1/2015‒2/29/2020). Four predictive models were developed to predict non-susceptibility to each antibiotic class and a risk categorization framework was developed to classify patients' isolates as low, moderate, and high risk of non-susceptibility to each antibiotic class. RESULTS: Predictive models were developed among 87487 patients. Key predictors of having a non-susceptible isolate to ≥3 antibiotic classes included number of previous UTI episodes, prior ß-lactam non-susceptibility, prior fluoroquinolone treatment, census bureau region, and race. The risk categorization framework classified 8.1%, 14.4%, 17.4%, and 6.3% of patients as having isolates at high risk of non-susceptibility to nitrofurantoin, trimethoprim-sulfamethoxazole, ß-lactams, and fluoroquinolones, respectively. Across classes, the proportion of patients categorized as having high-risk isolates was 3-12 folds higher among patients with non-susceptible isolates versus susceptible isolates. CONCLUSIONS: Our predictive models highlight factors that increase risk of non-susceptibility to antibiotics for uUTIs, while the risk categorization framework contextualizes risk of non-susceptibility to these treatments. Our findings provide valuable insight to clinicians treating uUTIs and may help inform empiric prescribing in this population.

Tree-Based Machine Learning to Identify Predictors of Psoriasis Incidence at the Neighborhood Level: A Populational Study from Quebec, Canada.

BACKGROUND: Psoriasis is a major global health burden affecting ~ 60 million people worldwide. Existing studies on psoriasis focused on individual-level health behaviors (e.g. diet, alcohol consumption, smoking, exercise) and characteristics as drivers of psoriasis risk. However, it is increasingly recognized that health behavior arises in the context of larger social, cultural, economic and environmental determinants of health. We aimed to identify the top risk factors that significantly impact the incidence of psoriasis at the neighborhood level using populational data from the province of Quebec (Canada) and advanced tree-based machine learning (ML) techniques. METHODS: Adult psoriasis patients were identified using International Classification of Disease (ICD)-9/10 codes from Quebec (Canada) populational databases for years 1997-2015. Data on environmental and socioeconomic factors 1 year prior to psoriasis onset were obtained from the Canadian Urban Environment Health Consortium (CANUE) and Statistics Canada (StatCan) and were input as predictors into the gradient boosting ML. Model performance was evaluated using the area under the curve (AUC). Parsimonious models and partial dependence plots were determined to assess directionality of the relationship. RESULTS: The incidence of psoriasis varied geographically from 1.6 to 325.6/100,000 person-years in Quebec. The parsimonious model (top 9 predictors) had an AUC of 0.77 to predict high psoriasis incidence. Amongst top predictors, ultraviolet (UV) radiation, maximum daily temperature, proportion of females, soil moisture, urbanization, and distance to expressways had a negative association with psoriasis incidence. Nighttime light brightness had a positive association, whereas social and material deprivation indices suggested a higher psoriasis incidence in the middle socioeconomic class neighborhoods. CONCLUSION: This is the first study to highlight highly variable psoriasis incidence rates on a jurisdictional level and suggests that living environment, notably climate, vegetation, urbanization and neighborhood socioeconomic characteristics may have an association with psoriasis incidence.

Predicting Clinical Remission of Chronic Urticaria Using Random Survival Forests: Machine Learning Applied to Real-World Data.

INTRODUCTION: The time required to reach clinical remission varies in patients with chronic urticaria (CU). The objective of this study is to develop a predictive model using a machine learning methodology to predict time to clinical remission for patients with CU. METHODS: Adults with ≥ 2 ICD-9/10 relevant CU diagnosis codes/CU-related treatment > 6 weeks apart were identified in the Optum deidentified electronic health record dataset (January 2007 to June 2019). Clinical remission was defined as ≥ 12 months without CU diagnosis/CU-related treatment. A random survival forest was used to predict time from diagnosis to clinical remission for each patient based on clinical and demographic features available at diagnosis. Model performance was assessed using concordance, which indicates the degree of agreement between observed and predicted time to remission. To characterize clinically relevant groups, features were summarized among cohorts that were defined based on quartiles of predicted time to remission. RESULTS: Among 112,443 patients, 73.5% reached clinical remission, with a median of 336 days from diagnosis. From 1876 initial features, 176 were retained in the final model, which predicted a median of 318 days to remission. The model showed good performance with a concordance of 0.62. Patients with predicted longer time to remission tended to be older with delayed CU diagnosis, and have more comorbidities, more laboratory tests, higher body mass index, and polypharmacy during the 12-month period before the first CU diagnosis. CONCLUSIONS: Applying machine learning to real-world data enabled accurate prediction of time to clinical remission and identified multiple relevant demographic and clinical variables with predictive value. Ongoing work aims to further validate and integrate these findings into clinical applications for CU management.

Development and evaluation of a predictive algorithm for unsatisfactory response among patients with pulmonary arterial hypertension using health insurance claims data.

OBJECTIVE: This study aimed to develop and validate a predictive algorithm for unsatisfactory response to initial pulmonary arterial hypertension (PAH) therapy using health insurance claims. METHODS: Adult patients with PAH initiated on a first PAH therapy (index date) were identified from Optum's de-identified Clinformatics Data Mart Database (1/1/2010-12/31/2019). A random survival forest algorithm was developed using patient-month data and predicted the "survival function" (i.e. risk of not having unsatisfactory response) over time. For each patient-month observation, risk factors were assessed in the 12 months prior. Unsatisfactory response was defined as the first instance of (1) new PAH therapy, (2) PAH-related hospitalization or emergency room visit, (3) lung transplant or atrial septostomy, (4) PAH-related death or (5) chronic oxygen therapy initiation. To facilitate use in clinical practice, a simplified risk score was also developed based on a linear combination of the most important risk factors identified in the algorithm. RESULTS: In total, 4781 patients were included (median age = 69.0 years; 58.6% female). Over a median follow-up of 14.0 months, 3169 (66.3%) had an unsatisfactory response. The most important risk factors included in the algorithm were healthcare resource use (i.e. PAH-related outpatient visits, pulmonologist visits, cardiologist visits, all-cause hospitalizations), time since first PAH diagnosis, time since index date, Charlson Comorbidity Index, dyspnea, and age. Predictive accuracy was good for the full algorithm (C-statistic: 0.732) but was slightly lower for the simplified risk score (C-statistic: 0.668). CONCLUSION: The present claims-based algorithm performed well in predicting time to unsatisfactory response following initial PAH therapy.

Beyond multidrug resistance: Leveraging rare variants with machine and statistical learning models in Mycobacterium tuberculosis resistance prediction.

BACKGROUND: The diagnosis of multidrug resistant and extensively drug resistant tuberculosis is a global health priority. Whole genome sequencing of clinical Mycobacterium tuberculosis isolates promises to circumvent the long wait times and limited scope of conventional phenotypic antimicrobial susceptibility, but gaps remain for predicting phenotype accurately from genotypic data especially for certain drugs. Our primary aim was to perform an exploration of statistical learning algorithms and genetic predictor sets using a rich dataset to build a high performing and fast predicting model to detect anti-tuberculosis drug resistance. METHODS: We collected targeted or whole genome sequencing and conventional drug resistance phenotyping data from 3601 Mycobacterium tuberculosis strains enriched for resistance to first- and second-line drugs, with 1228 multidrug resistant strains. We investigated the utility of (1) rare variants and variants known to be determinants of resistance for at least one drug and (2) machine and statistical learning architectures in predicting phenotypic drug resistance to 10 anti-tuberculosis drugs. Specifically, we investigated multitask and single task wide and deep neural networks, a multilayer perceptron, regularized logistic regression, and random forest classifiers. FINDINGS: The highest performing machine and statistical learning methods included both rare variants and those known to be causal of resistance for at least one drug. Both simpler L2 penalized regression and complex machine learning models had high predictive performance. The average AUCs for our highest performing model was 0.979 for first-line drugs and 0.936 for second-line drugs during repeated cross-validation. On an independent validation set, the highest performing model showed average AUCs, sensitivities, and specificities, respectively, of 0.937, 87.9%, and 92.7% for first-line drugs and 0.891, 82.0% and 90.1% for second-line drugs. Our method outperforms existing approaches based on direct association, with increased sum of sensitivity and specificity of 11.7% on first line drugs and 3.2% on second line drugs. Our method has higher predictive performance compared to previously reported machine learning models during cross-validation, with higher AUCs for 8 of 10 drugs. INTERPRETATION: Statistical models, especially those that are trained using both frequent and less frequent variants, significantly improve the accuracy of resistance prediction and hold promise in bringing sequencing technologies closer to the bedside.

The economic impact of a partnership-measurement model of disease management: Improving Cardiovascular Outcomes in Nova Scotia (ICONS).

Improving Cardiovascular Outcomes in Nova Scotia (ICONS) was a five-year, community partnership-based disease-management project that sought, as a primary goal, to improve the care and outcomes of patients with heart disease in Nova Scotia. This program, based on a broad stakeholder partnership, provided repeated measurement and feedback on practices and outcomes as well as widespread communication and education among all partners. From a clinical viewpoint, ICONS was successful. For example, use of proven therapies for the target diseases improved and re-hospitalization rates decreased. Stakeholders also perceived a sense of satisfaction because of their involvement in the partnership. However, the universe of health stakeholders is large, and not many have had an experience similar to ICONS. These other health stakeholders, such as decision-makers concerned with the cost of care and determining the value for cost, might, nonetheless, benefit from knowledge of the ICONS concepts and results, particularly economic analyses, as they determine future health policy. Using budgetary data on actual dollars spent and a robust input-output methodology, we assessed the economic impact of ICONS, including trickle-down effects on the Canadian and Nova Scotian economies. The analysis revealed that the $6.22 million invested in Nova Scotia by the private sector donor generated an initial net increase in total Canadian wealth of $5.32 million and a global net increase in total Canadian wealth of $10.23 million, including $2.27 million returned to the different governments through direct and indirect taxes. Thus, the local, provincial and federal governments are important beneficiaries of health project investments such as ICONS. The various government levels benefit from the direct influx of private funds into the publicly funded healthcare sector, from direct and indirect tax revenues and from an increase in knowledge-related employment. This, of course, is in addition to the clinical benefits associated with the partnership-measurement disease-management model. Because of their uniquely simultaneous roles as beneficiary and major resource provider, the public payer can play an early and active role in such partnerships to enhance its efficiencies and increase the likelihood of sustainability if the original concepts are proven of value.

The value of antihypertensive drugs: a perspective on medical innovation.

Using national survey data and risk equations from the Framingham Heart Study, we quantify the impact of antihypertensive therapy changes on blood pressures and the number and cost of heart attacks, strokes, and deaths. Antihypertensive therapy has had a major impact on health. Without it, 1999-2000 average blood pressures (at age 40+) would have been 10-13 percent higher, and 86,000 excess premature deaths from cardiovascular disease would have occurred in 2001. Treatment has generated a benefit-to-cost ratio of at least 6:1, but much more can be achieved. More effective use of antihypertensive medication would have an impact on mortality akin to eliminating all deaths from medical errors or accidents.