Machine learning-based outcome prediction and novel hypotheses generation for substance use disorder treatment

OBJECTIVE

Substance use disorder is a critical public health issue. Discovering the synergies among factors impacting treatment program success can help governments and treatment facilities develop effective policies. In this work, we propose a novel data analytics approach using machine learning models to discover interaction effects that might be neglected by traditional hypothesis-generating approaches.

MATERIALS AND METHODS

A patient-episode-level substance use treatment discharge dataset and a Federal Bureau of Investigation crime dataset were joined using core-based statistical area codes. Random forests, artificial neural networks, and extreme gradient boosting were applied with a nested cross-validation methodology. Interaction effects were identified based on the machine learning model with the best performance. These interaction effects were analyzed and tested using traditional logistic regression models on unseen data.

RESULTS

In predicting patient completion of a treatment program, extreme gradient boosting performed the best with an area under the curve of 89.31%. Based on our procedure, 73 interaction effects were identified. Among these, 14 were tested using traditional logistic regression models where 12 were statistically significant (P<.05).

CONCLUSIONS

We identified new interaction effects among the length of stay, frequency of substance use, changes in self-help group attendance frequency, and other factors. This work provides insights into the interactions between factors impacting treatment completion. Further traditional statistical analysis can be employed by practitioners and policy makers to test the effects discovered by our novel machine learning approach.

COVID-19 Patient Health Prediction Using Boosted Random Forest Algorithm

Integration of artificial intelligence (AI) techniques in wireless infrastructure, real-time collection, and processing of end-user devices is now in high demand. It is now superlative to use AI to detect and predict pandemics of a colossal nature. The Coronavirus disease 2019 (COVID-19) pandemic, which originated in Wuhan China, has had disastrous effects on the global community and has overburdened advanced healthcare systems throughout the world. Globally; over 4,063,525 confirmed cases and 282,244 deaths have been recorded as of 11th May 2020, according to the European Centre for Disease Prevention and Control agency. However, the current rapid and exponential rise in the number of patients has necessitated efficient and quick prediction of the possible outcome of an infected patient for appropriate treatment using AI techniques. This paper proposes a fine-tuned Random Forest model boosted by the AdaBoost algorithm. The model uses the COVID-19 patient's geographical, travel, health, and demographic data to predict the severity of the case and the possible outcome, recovery, or death. The model has an accuracy of 94% and a F1 Score of 0.86 on the dataset used. The data analysis reveals a positive correlation between patients' gender and deaths, and also indicates that the majority of patients are aged between 20 and 70 years.

A Survey of Healthcare Internet-of-Things (HIoT): A Clinical Perspective

In combination with current sociological trends, the maturing development of IoT devices is projected to revolutionize healthcare. A network of body-worn sensors, each with a unique ID, can collect health data that is orders-of-magnitude richer than what is available today from sporadic observations in clinical/hospital environments. When databased, analyzed, and compared against information from other individuals using data analytics, HIoT data enables the personalization and modernization of care with radical improvements in outcomes and reductions in cost. In this paper, we survey existing and emerging technologies that can enable this vision for the future of healthcare, particularly in the clinical practice of healthcare. Three main technology areas underlie the development of this field: (a) sensing, where there is an increased drive for miniaturization and power efficiency; (b) communications, where the enabling factors are ubiquitous connectivity, standardized protocols, and the wide availability of cloud infrastructure, and (c) data analytics and inference, where the availability of large amounts of data and computational resources is revolutionizing algorithms for individualizing inference and actions in health management. Throughout the paper, we use a case study to concretely illustrate the impact of these trends. We conclude our paper with a discussion of the emerging directions, open issues, and challenges.

A decision tree-based classifier for E-visit service provision

This study proposes a decision tree-based e-visit classification approach (DTEVCA) to determine clinic visits qualified as e-visits using clinics' medical records and patients' demographic data. This study assumes that health care insurance will subsidise e-visit service costs, in which case, identifying patients who benefit most from e-visit service is essential. Using a large data set from Taiwan's National Health Insurance, this study verifies the efficiency and validity of the DTEVCA. Results indicate that this approach can accurately classify in-office clinic visits that could switch to e-visit services. The straightforward rules of this decision tree also give insurance agencies a clear guideline to understand the circumstances of using e-visits and predict the effects of implementing e-visits in Taiwan. Result of this study can help countries improve the policy formulation process for physicians' use, or for academic research. The DTEVCA can update classification rules using new data to correct biases and ensure the stability of the e-visit system. In addition, the concept of this approach is feasible not only for e-visit service but also for other 'new services' such as new products or new policies.

Preference-Sensitive Management of Post-Mammography Decisions in Breast Cancer Diagnosis

Decision models representing the clinical situations where treatment options entail a significant risk of morbidity or mortality should consider the variations in risk preferences of individuals. In this study, we develop a stochastic modeling framework that optimizes risk-sensitive diagnostic decisions after a mammography exam. For a given patient, our objective is to find the utility maximizing diagnostic decisions where we define the utility over quality-adjusted survival duration. We use real data from a private mammography database to numerically solve our model for various utility functions. Our choice of utility functions for the numerical analysis is driven by actual patient behavior encountered in clinical practice. We find that invasive diagnostic procedures such as biopsies are more aggressively used than what the optimal risk-neutral policy would suggest, implying a far-sighted (or equivalently risk-seeking) behavior. When risk preferences are incorporated into the clinical practice, policy makers should bear in mind that a welfare loss in terms of survival duration is inevitable as evidenced by our structural and empirical results.

Distributed data networks: a blueprint for Big Data sharing and healthcare analytics

This paper defines the attributes of distributed data networks and outlines the data and analytic infrastructure needed to build and maintain a successful network. We use examples from one successful implementation of a large-scale, multisite, healthcare-related distributed data network, the U.S. Food and Drug Administration-sponsored Sentinel Initiative. Analytic infrastructure-development concepts are discussed from the perspective of promoting six pillars of analytic infrastructure: consistency, reusability, flexibility, scalability, transparency, and reproducibility. This paper also introduces one use case for machine learning algorithm development to fully utilize and advance the portfolio of population health analytics, particularly those using multisite administrative data sources.

IBM's Health Analytics and Clinical Decision Support

OBJECTIVES

This survey explores the role of big data and health analytics developed by IBM in supporting the transformation of healthcare by augmenting evidence-based decision-making.

METHODS

Some problems in healthcare and strategies for change are described. It is argued that change requires better decisions, which, in turn, require better use of the many kinds of healthcare information. Analytic resources that address each of the information challenges are described. Examples of the role of each of the resources are given.

RESULTS

There are powerful analytic tools that utilize the various kinds of big data in healthcare to help clinicians make more personalized, evidenced-based decisions. Such resources can extract relevant information and provide insights that clinicians can use to make evidence-supported decisions. There are early suggestions that these resources have clinical value. As with all analytic tools, they are limited by the amount and quality of data.

CONCLUSION

Big data is an inevitable part of the future of healthcare. There is a compelling need to manage and use big data to make better decisions to support the transformation of healthcare to the personalized, evidence-supported model of the future. Cognitive computing resources are necessary to manage the challenges in employing big data in healthcare. Such tools have been and are being developed. The analytic resources, themselves, do not drive, but support healthcare transformation.