h Lin Chi

Building a hospital referral expert system with a Prediction and Optimization-Based Decision Support System algorithm

This study presents a new method for constructing an expert system using a hospital referral problem as an example. Many factors, such as institutional characteristics, patient risks, traveling distance, and chances of survival and complications should be included in the hospital-selection decision. Ideally, each patient should be treated individually, with the decision process including not only their condition but also their beliefs about trade-offs among the desired hospital features. An expert system can help with this complex decision, especially when numerous factors are to be considered. We propose a new method, called the Prediction and Optimization-Based Decision Support System (PODSS) algorithm, which constructs an expert system without an explicit knowledge base. The algorithm obtains knowledge on its own by building machine learning classifiers from a collection of labeled cases. In response to a query, the algorithm gives a customized recommendation, using an optimization step to help the patient maximize the probability of achieving a desired outcome. In this case, the recommended hospital is the optimal solution that maximizes the probability of the desired outcome. With proper formulation, this expert system can combine multiple factors to give hospital-selection decision support at the individual level.

Individualized patient-centered lifestyle recommendations

We propose a proof-of-concept machine-learning expert system that learned knowledge of lifestyle and the associated 10-year cardiovascular disease (CVD) risks from individual-level data (i.e., Atherosclerosis Risk in Communities Study, ARIC). The expert system prioritizes lifestyle options and identifies the one that maximally reduce an individuals 10-year CVD risk by (1) using the knowledge learned from the ARIC data and (2) communicating for patient-specific cardiovascular risk information and personal limitations and preferences (as defined by variables used in this study). As a result, the optimal lifestyle is not only prioritized based on an individuals characteristics but is also relevant to personal circumstances. We also explored probable uses and tested the system in several examples using real-world scenarios and patient preferences. For example, the system identifies the most effective lifestyle activities as the starting point for an individuals behavior change, shows different levels of BMI changes and the associated CVD risk reductions to encourage weight loss, identifies whether weight loss or smoking cessation is the most urgent change for a diabetes patient, etc. Answers to the questions noted above vary based on an individuals characteristics. Our validation results from clinical trial simulations, which compared original with the optimal lifestyle using an independent dataset, show that the optimal individualized patient-centered lifestyle consistently reduced 10-year CVD risks.

A decision support system for cost-effective diagnosis

OBJECTIVE Speed, cost, and accuracy are three important goals in disease diagnosis. This paper proposes a machine learning-based expert system algorithm to optimize these goals and assist diagnostic decisions in a sequential decision-making setting. METHODS The algorithm consists of three components that work together to identify the sequence of diagnostic tests that attains the treatment or no test threshold probability for a query case with adequate certainty: lazy-learning classifiers, confident diagnosis, and locally sequential feature selection (LSFS). Speed-based and cost-based objective functions can be used as criteria to select tests. RESULTS Results of four different datasets are consistent. All LSFS functions significantly reduce tests and costs. Average cost savings for heart disease, thyroid disease, diabetes, and hepatitis datasets are 50%, 57%, 22%, and 34%, respectively. Average test savings are 55%, 73%, 24%, and 39%, respectively. Accuracies are similar to or better than the baseline (the classifier that uses all available tests in the dataset). CONCLUSION We have demonstrated a new approach that dynamically estimates and determines the optimal sequence of tests that provides the most information (or disease probability) based on a patients available information.

Environmental Mold and Mycotoxin Exposures Elicit Specific Cytokine and Chemokine Responses

Background Molds can cause respiratory symptoms and asthma. We sought to use isolated peripheral blood mononuclear cells (PBMCs) to understand changes in cytokine and chemokine levels in response to mold and mycotoxin exposures and to link these levels with respiratory symptoms in humans. We did this by utilizing an ex vivo assay approach to differentiate mold-exposed patients and unexposed controls. While circulating plasma chemokine and cytokine levels from these two groups might be similar, we hypothesized that by challenging their isolated white blood cells with mold or mold extracts, we would see a differential chemokine and cytokine release. Methods and Findings Peripheral blood mononuclear cells (PBMCs) were isolated from blood from 33 patients with a history of mold exposures and from 17 controls. Cultured PBMCs were incubated with the most prominent Stachybotrys chartarum mycotoxin, satratoxin G, or with aqueous mold extract, ionomycin, or media, each with or without PMA. Additional PBMCs were exposed to spores of Aspergillus niger, Cladosporium herbarum and Penicillium chrysogenum. After 18 hours, cytokines and chemokines released into the culture medium were measured by multiplex assay. Clinical histories, physical examinations and pulmonary function tests were also conducted. After ex vivo PBMC exposures to molds or mycotoxins, the chemokine and cytokine profiles from patients with a history of mold exposure were significantly different from those of unexposed controls. In contrast, biomarker profiles from cells exposed to media alone showed no difference between the patients and controls. Conclusions These findings demonstrate that chronic mold exposures induced changes in inflammatory and immune system responses to specific mold and mycotoxin challenges. These responses can differentiate mold-exposed patients from unexposed controls. This strategy may be a powerful approach to document immune system responsiveness to molds and other inflammation-inducing environmental agents.

Social Determinants and Health Disparities Associated With Outcomes of Women of Childbearing Age Who Receive Public Health Nurse Home Visiting Services

Objective: To examine the associations between social and behavioral determinants of health (SBDH), health disparities, and the outcomes of women who received public health nurse home visits for pregnancy and parenting support. Design: Observational exploratory data analysis and comparative outcome evaluation. Setting: An extant dataset from women served in a Midwestern U.S. state, including demographics and Omaha System problems, signs/symptoms, interventions, and outcome assessments. Participants: Women (N = 4,263) with an average age of 23.6 years (SD = 6.1); 21.4% were married, and 39.1% were White. Methods: An evaluation dataset was constructed that included all women of childbearing age, their demographics, and outcome assessments. A summative SBDH Index based on Institute of Medicine‐recommended instruments was computed based on sign/symptom data. Visualizations were developed using Microsoft Excel, and outcome significance statistics were computed using SPSS version 22 and SAS version 9.4. Results: Outcome evaluation showed positive, significant changes from baseline after public health nurse intervention. Visualization showed variable concentrations of problem‐specific signs/symptoms by SBDH Index subgroups. There were between‐group differences in overall outcome attainment across SBDH Index subgroups. Compared with White women, minority women had greater improvement; however, despite these gains overall minority final ratings were lower. Conclusion: An informatics approach showed that SBDH are important factors for understanding a comprehensive and holistic view of health and health care outcomes. There is potential to use large datasets to further explore intervention effectiveness and progress toward health equity related to SBDH.

A Systems Approach to Designing Effective Clinical Trials Using Simulations

Background— Pharmacogenetics in warfarin clinical trials have failed to show a significant benefit in comparison with standard clinical therapy. This study demonstrates a computational framework to systematically evaluate preclinical trial design of target population, pharmacogenetic algorithms, and dosing protocols to optimize primary outcomes. Methods and Results— We programmatically created an end-to-end framework that systematically evaluates warfarin clinical trial designs. The framework includes options to create a patient population, multiple dosing strategies including genetic-based and nongenetic clinical-based, multiple-dose adjustment protocols, pharmacokinetic/pharmacodynamics modeling and international normalization ratio prediction, and various types of outcome measures. We validated the framework by conducting 1000 simulations of the Applying Pharmacogenetic Algorithms to Individualize Dosing of Warfarin (CoumaGen) clinical trial primary end points. The simulation predicted a mean time in therapeutic range of 70.6% and 72.2% (P=0.47) in the standard and pharmacogenetic arms, respectively. Then, we evaluated another dosing protocol under the same original conditions and found a significant difference in the time in therapeutic range between the pharmacogenetic and standard arm (78.8% versus 73.8%; P=0.0065), respectively. Conclusions— We demonstrate that this simulation framework is useful in the preclinical assessment phase to study and evaluate design options and provide evidence to optimize the clinical trial for patient efficacy and reduced risk.

An approach to optimal individualized warfarin treatment through clinical trial simulations

Personalized medicine will depend on sophisticated tools, analyses, and molecular level data and clinical information to provide optimized treatment based on each patients individual characteristics such as health history, current health or disease status, and biochemical and physiological makeup. We discuss an approach to integrate clinical trial simulations with an optimization method to produce predictions of the best individualized treatment. Our objective is to optimize the treatment protocol by minimizing health risk to adverse drug reactions. This approach anticipates the era of genome-based medicine that requires sophisticated engineering, mathematical modeling and simulations to support best practice and clinical use of genetic data.

Peer Group and Text Message–Based Weight-Loss and Management Intervention for African American Women:

About 80% of African American (AA) women are overweight or obese. Accessible and effective weight management programs targeting weight loss, weight maintenance and the prevention of weight regain are needed to improve health of AA women. A feasibility study was conducted to examine the feasibility, acceptability, and potential efficacy of a 16-week intervention protocol for weight loss and management that combined daily text messages and biweekly peer group sessions. Modest but statistically significant reductions were detected in weight and body mass index from baseline to 16 weeks. At baseline, 36% of participants were in action and maintenance stages in measures of the stages of change for weight loss and management; this percent increased to 82% at 16 weeks. Findings of this feasibility study provide preliminary evidence of an educational intervention that could motivate women and lead to successful behavior change, and successful weight loss and management for AA women.

Big Data Cohort Extraction to Facilitate Machine Learning to Improve Statin Treatment

Health care Big Data studies hold substantial promise for improving clinical practice. Among analytic tools, machine learning (ML) is an important approach that has been widely used by many industries for data-driven decision support. In Big Data, thousands of variables and millions of patient records are commonly encountered, but most data elements cannot be directly used to support decision making. Although many feature-selection tools can help identify relevant data, these tools are typically insufficient to determine a patient data cohort to support learning. Therefore, domain experts with nursing or clinic knowledge play critical roles in determining value criteria or the type of variables that should be included in the patient cohort to maximize project success. We demonstrate this process by extracting a patient cohort (37,506 individuals) to support our ML work (i.e., the production of a proactive strategy to prevent statin adverse events) from 130 million de-identified lives in the OptumLabs™ Data Warehouse.

Personalized AnticoagulationCLINICAL PERSPECTIVE: Optimizing Warfarin Management Using Genetics and Simulated Clinical Trials

Background— Clinical trials testing pharmacogenomic-guided warfarin dosing for patients with atrial fibrillation have demonstrated conflicting results. Non–vitamin K antagonist oral anticoagulants are expensive and contraindicated for several conditions. A strategy optimizing anticoagulant selection remains an unmet clinical need. Methods and Results— Characteristics from 14 206 patients with atrial fibrillation were integrated into a validated warfarin clinical trial simulation framework using iterative Bayesian network modeling and a pharmacokinetic–pharmacodynamic model. Individual dose–response for patients was simulated for 5 warfarin protocols—a fixed-dose protocol, a clinically guided protocol, and 3 increasingly complex pharmacogenomic-guided protocols. For each protocol, a complexity score was calculated using the variables predicting warfarin dose and the number of predefined international normalized ratio (INR) thresholds for each adjusted dose. Study outcomes included optimal time in therapeutic range ≥65% and clinical events. A combination of age and genotype identified different optimal protocols for various subpopulations. A fixed-dose protocol provided well-controlled INR only in normal responders ≥65, whereas for normal responders <65 years old, a clinically guided protocol was necessary to achieve well-controlled INR. Sensitive responders ≥65 and <65 and highly sensitive responders ≥65 years old required pharmacogenomic-guided protocols to achieve well-controlled INR. However, highly sensitive responders <65 years old did not achieve well-controlled INR and had higher associated clinical events rates than other subpopulations. Conclusions— Under the assumptions of this simulation, patients with atrial fibrillation can be triaged to an optimal warfarin therapy protocol by age and genotype. Clinicians should consider alternative anticoagulation therapy for patients with suboptimal outcomes under any warfarin protocol.