Population modeling with machine learning can enhance measures of mental health

Background Biological aging is revealed by physical measures, e.g., DNA probes or brain scans. In contrast, individual differences in mental function are explained by psychological constructs, e.g., intelligence or neuroticism. These constructs are typically assessed by tailored neuropsychological tests that build on expert judgement and require careful interpretation. Could machine learning on large samples from the general population be used to build proxy measures of these constructs that do not require human intervention? Results Here, we built proxy measures by applying machine learning on multimodal MR images and rich sociodemographic information from the largest biomedical cohort to date: the UK Biobank. Objective model comparisons revealed that all proxies captured the target constructs and were as useful, and sometimes more useful, than the original measures for characterizing real-world health behavior (sleep, exercise, tobacco, alcohol consumption). We observed this complementarity of proxy measures and original measures at capturing multiple health-related constructs when modeling from, both, brain signals and sociodemographic data. Conclusion Population modeling with machine learning can derive measures of mental health from heterogeneous inputs including brain signals and questionnaire data. This may complement or even substitute for psychometric assessments in clinical populations.

A VECTOR ANALYTICAL FRAMEWORK FOR POPULATION MODELING

We propose a vector alternative to the typical raster based population modeling framework. When compared with rasters, vectors are more precise, have the ability to hold more information, and are more conducive to areal constructs such as building and parcel outlines. While rasters have traditionally provided computational efficiency, much of this efficiency is reduced at finer resolutions and computational resources are more plentiful today. Herein we describe the approach and implementation methodology. We also describe the output data stack for the United States and provide examples and applications.

Evaluating risk detection methods to uncover ontogenic-mediated adverse drug effect mechanisms in children

Background Identifying adverse drugs effects (ADEs) in children, overall and within pediatric age groups, is essential for preventing disability and death from marketed drugs. At the same time, however, detection is challenging due to dynamic biological processes during growth and maturation, called ontogeny, that alter pharmacokinetics and pharmacodynamics. As a result, methodologies in pediatric drug safety have been limited to event surveillance and have not focused on investigating adverse event mechanisms. There is an opportunity to identify drug event patterns within observational databases for evaluating ontogenic-mediated adverse event mechanisms. The first step of which is to establish statistical models that can identify temporal trends of adverse effects across childhood. Results Using simulation, we evaluated a population stratification method (the proportional reporting ratio or PRR) and a population modeling method (the generalized additive model or GAM) to identify and quantify ADE risk at varying reporting rates and dynamics. We found that GAMs showed improved performance over the PRR in detecting dynamic drug event reporting across child development stages. Moreover, GAMs exhibited normally distributed and robust ADE risk estimation at all development stages by sharing information across child development stages. Conclusions Our study underscores the opportunity for using population modeling techniques, which leverage drug event reporting across development stages, as biologically-inspired detection methods for evaluating ontogenic mechanisms.

The use of population modeling to optimize dosing of drugs used in anaesthesiology and intensive care

Effective pharmacotherapy requires an adequate drug dose that maximizes the effectiveness of therapy while minimizing adverse effects. Difficulties in dose selection arise from interindividual differences in drug pharmacokinetics and pharmacodynamics. Population modeling describes pharmacokinetic and pharmacodynamic processes in a population, taking into account the relationships in each patient, differences between patients, and the influence of covariates on drug pharmacokinetics and pharmacodynamics. The aim of this study was to develop population models for drugs used in anesthesiology and intensive care in special patient populations. The pharmacokinetics of sufentanil was described in infants and children after epidural and intravenous administration. The estimated absorption rate constant from the epidural space suggests slow systemic absorption of sufentanil and the possibility of flip-flop kinetics, which results in a slower decline in plasma concentrations at the end of drug administration compared with intravenous administration. The dependence of metabolic clearance on body weight and age was also demonstrated. A population model for the pharmacokinetics of tigecycline was developed for patients with sepsis or septic shock. No relationship between pharmacokinetic parameters and patient characteristics was detected, and the estimated interindividual and inter-occasion variability for clearance was small. This suggests that a universal dose is sufficient to achieve homogeneous drug exposure in critically ill patients. The pharmacokinetics of caspofungin was described in critically ill patients. The clearance and volume of central compartment showed systematic increase over time that was not explained by the covariates. The estimated increase in clearance values for three consecutive doses results in a clinically relevant reduction in drug exposure. The developed population models extend the knowledge of the pharmacokinetics of sufentanyl, tigecycline, and caspofungin. Simulations based on these models can aid the dosing decision-making process.

Evaluating risk detection methods to uncover ontogenic-mediated adverse drug effect mechanisms in children

BackgroundIdentifying adverse drugs effects (ADEs) in children is essential for preventing disability and death from marketed drugs. At the same time, however, detection is challenging due to dynamic biological processes during growth and maturation, called ontogeny, that alter pharmacokinetics and pharmacodynamics. As a result, current data mining methodologies have been limited to event surveillance and have not focused on investigating adverse event mechanisms. There is an opportunity to design data mining methodologies to identify and evaluate drug event patterns within observational databases for ontogenic-mediated adverse event mechanisms. The first step of which is to establish statistical models that can identify temporal trends of adverse effects across childhood.ResultsUsing simulation, we evaluated a population stratification method (the proportional reporting ratio or PRR) and a population modeling method (the generalized additive model or GAM) to identify and quantify ADE risk at varying reporting rates and dynamics. We found that GAMs showed improved performance over the PRR in detecting dynamic drug event reporting across child developmental stages. Moreover, GAMs exhibited normally distributed and robust ADE risk estimation at all development stages by sharing information across child development stages.ConclusionsOur study underscores the opportunity for using population modeling techniques, which leverages drug event reporting across development stages, to identify adverse drug effect risk resulting from ontogenic mechanisms.