A survey of extant organizational and computational setups for deploying predictive models in health systems

ObjectiveArtificial intelligence (AI) and machine learning (ML) enabled healthcare is now feasible for many health systems, yet little is known about effective strategies of system architecture and governance mechanisms for implementation. Our objective was to identify the different computational and organizational setups that early-adopter health systems have utilized to integrate AI/ML clinical decision support (AI-CDS) and scrutinize their trade-offs.Materials and MethodsWe conducted structured interviews with health systems with AI deployment experience about their organizational and computational setups for deploying AI-CDS at point of care.ResultsWe contacted 34 health systems and interviewed 20 healthcare sites (58% response rate). Twelve (60%) sites used the native electronic health record vendor configuration for model development and deployment, making it the most common shared infrastructure. Nine (45%) sites used alternative computational configurations which varied significantly. Organizational configurations for managing AI-CDS were distinguished by how they identified model needs, built and implemented models, and were separable into 3 major types: Decentralized translation (n = 10, 50%), IT Department led (n = 2, 10%), and AI in Healthcare (AIHC) Team (n = 8, 40%).DiscussionNo singular computational configuration enables all current use cases for AI-CDS. Health systems need to consider their desired applications for AI-CDS and whether investment in extending the off-the-shelf infrastructure is needed. Each organizational setup confers trade-offs for health systems planning strategies to implement AI-CDS.ConclusionHealth systems will be able to use this framework to understand strengths and weaknesses of alternative organizational and computational setups when designing their strategy for artificial intelligence.     

Analytical techniques for quantification of amorphous/crystalline phases in pharmaceutical solids

The existence of different solid-state forms such as polymorphs, solvates, hydrates, and amorphous form in pharmaceutical drug substances and excipients, along with their downstream consequences in drug products and biological systems, is well documented. Out of these solid states, amorphous systems have attracted considerable attention of formulation scientists for their specific advantages, and their presence, either by accident or design is known to incorporate distinct properties in the drug product. Identification of different solid-state forms is crucial to anticipate changes in the performance of the material upon storage and/or handling. Quantitative analysis of physical state is imperative from the viewpoint of both the manufacturing and the regulatory control aimed at assuring safety and efficacy of drug products. Numerous analytical techniques have been reported for the quantification of amorphous/crystalline phase, and implicit in all quantitative options are issues of accuracy, precision, and suitability. These quantitative techniques mainly vary in the properties evaluated, thus yielding divergent values of crystallinity for a given sample. The present review provides a compilation of the theoretical and practical aspects of existing techniques, thereby facilitating the selection of an appropriate technique to accomplish various objectives of quantification of amorphous systems.     

Premature atherosclerotic peripheral artery disease: An underrecognized and undertreated disorder with a rising global prevalence

Premature atherosclerotic peripheral artery disease (PAD) of the lower extremities is characterized by disease diagnosis before the age of 50 years. The global prevalence of premature PAD has increased, and the disease is often underdiagnosed given heterogenous patient symptoms. Traditional cardiovascular risk factors like smoking, diabetes, hypertension, and hyperlipidemia as well as non-traditional risk factors like elevated lipoprotein(a), family history of PAD, hypercoagulability, and systemic inflammation are associated with premature PAD. Patients with premature PAD tend to have an aggressive vascular disease process, a high burden of cardiovascular risk factors, and other concomitant atherosclerotic vascular diseases like coronary artery disease. Prevention of cardiovascular events, improvement of symptoms and functional status, and prevention of adverse limb events are the main goals of patient management. In this review, we discuss the epidemiology, risk factors, clinical evaluation, and management of patients with premature PAD.     

Increased risk of colorectal polyps in patients with non-alcoholic fatty liver disease undergoing liver transplant evaluation

Background

Screening colonoscopy is a standard part of the liver transplant (LT) evaluation process. We aimed to evaluate the yield of screening colonoscopy and determine whether non-alcoholic fatty liver disease (NAFLD) was associated with an increased risk of colorectal neoplasia.

Methods

We retrospectively assessed all patients who completed LT evaluation at our center between 1/2008-12/2012. Patients <50 years old and those without records of screening colonoscopy, or with greater than average colon cancer risk were excluded.

Results

A total of 1,102 patients were evaluated, 591 met inclusion criteria and were analyzed. The mean age was 60 years, 67% were male, 12% had NAFLD and 88% had other forms of chronic liver disease. Overall, 42% of patients had a polyp found on colonoscopy: 23% with adenomas, 14% with hyperplastic polyps and with 1% inflammatory polyps. In the final multivariable model controlling for age, NAFLD [odds ratio (OR) 2.41, P=0.001] and a history of significant alcohol use (OR 1.69, P=0.004) were predictive of finding a polyp on colonoscopy. In addition, NAFLD (OR 1.95, P=0.02), significant alcohol use (OR 1.70, P=0.01) and CTP class C (OR 0.57, P=0.02) were associated with adenoma, controlling for age.

Conclusions

Screening colonoscopy in patients awaiting LT yields a high rate of polyp (43%) and adenoma (22%) detection, perhaps preventing the accelerated progression to carcinoma that can occur in immunosuppressed post-LT patients. Patients with NAFLD may be at a ~2 fold higher risk of adenomas and should be carefully evaluated prior to LT.     

Learning decision thresholds for risk stratification models from aggregate clinician behavior

Using a risk stratification model to guide clinical practice often requires the choice of a cutoff—called the decision threshold—on the model’s output to trigger a subsequent action such as an electronic alert. Choosing this cutoff is not always straightforward. We propose a flexible approach that leverages the collective information in treatment decisions made in real life to learn reference decision thresholds from physician practice. Using the example of prescribing a statin for primary prevention of cardiovascular disease based on 10-year risk calculated by the 2013 pooled cohort equations, we demonstrate the feasibility of using real-world data to learn the implicit decision threshold that reflects existing physician behavior. Learning a decision threshold in this manner allows for evaluation of a proposed operating point against the threshold reflective of the community standard of care. Furthermore, this approach can be used to monitor and audit model-guided clinical decision making following model deployment.     

Building a Learning Health System: Creating an Analytical Workflow for Evidence Generation to Inform Institutional Clinical Care Guidelines

Background  One key aspect of a learning health system (LHS) is utilizing data generated during care delivery to inform clinical care. However, institutional guidelines that utilize observational data are rare and require months to create, making current processes impractical for more urgent scenarios such as those posed by the COVID-19 pandemic. There exists a need to rapidly analyze institutional data to drive guideline creation where evidence from randomized control trials are unavailable. Objectives  This article provides a background on the current state of observational data generation in institutional guideline creation and details our institution''s experience in creating a novel workflow to (1) demonstrate the value of such a workflow, (2) demonstrate a real-world example, and (3) discuss difficulties encountered and future directions. Methods  Utilizing a multidisciplinary team of database specialists, clinicians, and informaticists, we created a workflow for identifying and translating a clinical need into a queryable format in our clinical data warehouse, creating data summaries and feeding this information back into clinical guideline creation. Results  Clinical questions posed by the hospital medicine division were answered in a rapid time frame and informed creation of institutional guidelines for the care of patients with COVID-19. The cost of setting up a workflow, answering the questions, and producing data summaries required around 300 hours of effort and $300,000 USD. Conclusion  A key component of an LHS is the ability to learn from data generated during care delivery. There are rare examples in the literature and we demonstrate one such example along with proposed thoughts of ideal multidisciplinary team formation and deployment.