Dataset Information

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

ABSTRACT: OBJECTIVE:To propose nonparametric ensemble machine learning for mental health and substance use disorders (MHSUD) spending risk adjustment formulas, including considering Clinical Classification Software (CCS) categories as diagnostic covariates over the commonly used Hierarchical Condition Category (HCC) system. DATA SOURCES:2012-2013 Truven MarketScan database. STUDY DESIGN:We implement 21 algorithms to predict MHSUD spending, as well as a weighted combination of these algorithms called super learning. The algorithm collection included seven unique algorithms that were supplied with three differing sets of MHSUD-related predictors alongside demographic covariates: HCC, CCS, and HCC + CCS diagnostic variables. Performance was evaluated based on cross-validated R2 and predictive ratios. PRINCIPAL FINDINGS:Results show that super learning had the best performance based on both metrics. The top single algorithm was random forests, which improved on ordinary least squares regression by 10 percent with respect to relative efficiency. CCS categories-based formulas were generally more predictive of MHSUD spending compared to HCC-based formulas. CONCLUSIONS:Literature supports the potential benefit of implementing a separate MHSUD spending risk adjustment formula. Our results suggest there is an incentive to explore machine learning for MHSUD-specific risk adjustment, as well as considering CCS categories over HCCs.

SUBMITTER: Shrestha A

PROVIDER: S-EPMC6056578 | biostudies-other | 2018 Aug

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

Shrestha Akritee A Bergquist Savannah S Montz Ellen E Rose Sherri S

Health services research 20171215

<h4>Objective</h4>To propose nonparametric ensemble machine learning for mental health and substance use disorders (MHSUD) spending risk adjustment formulas, including considering Clinical Classification Software (CCS) categories as diagnostic covariates over the commonly used Hierarchical Condition Category (HCC) system.<h4>Data sources</h4>2012-2013 Truven MarketScan database.<h4>Study design</h4>We implement 21 algorithms to predict MHSUD spending, as well as a weighted combination of these a ...[more]

PMID: 29244202

Similar Datasets

Project description:ObjectiveIn 2014, an estimated 15 million individuals who currently do not have health insurance, including many with chronic mental illness, are expected to obtain coverage through state insurance exchanges. The authors examined how two mechanisms in the Affordable Care Act (ACA), namely, risk adjustment and reinsurance, might perform to ensure the financial solvency of health plans that have a disproportionate share of enrollees with mental health conditions. Risk adjustment is an ACA provision requiring that a federal or state exchange move funds from insurance plans with healthier enrollees to plans with sicker enrollees. Reinsurance is a provision in which all plans in the state contribute to an overall pool of money that is used to reimburse costs to individual market plans for expenditures of any individual enrollee that exceed a high predetermined level.MethodUsing 2006--2007 claims data from a sample of private and public health plans, the authors compared expected health plan compensation under diagnosis-based risk adjustment with actual health care expenditures, under different assumptions for chronic mental health and medical conditions. Analyses were conducted with and without the addition of $100,000 reinsurance.ResultsRisk adjustment performed well for most plans. For some plans with a high share of enrollees with mental health conditions, underpayment was substantial enough to raise concern. Reinsurance appeared to be helpful in addressing the most serious underpayment problems remaining after risk adjustment. Risk adjustment performed similarly for health plan cohorts that had a disproportionate share of enrollees with chronic mental health and medical conditions.ConclusionsCost models indicate that the regulatory provisions in the ACA requiring risk adjustment and reinsurance can help protect health plans covering treatment for mentally ill individuals against risk selection. This model analysis may be useful for advocates for individuals with mental illness in considering their own state's insurance exchange.

Project description:BackgroundMachine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining.ObjectiveThe primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice.MethodsThis systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed.ResultsA total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform.ConclusionsMachine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.

Dataset Information

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

Publications

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets