| Description |
1 online resource |
| Contents |
Intro; Foreword; Big Data Is Watching You; Reference; Preface; Contents; Contributors; 1 Big Data and Machine Learning Meet the Health Sciences; 1.1 Eras of Epidemiology: Paradigms and Analytical Approach; 1.2 The Dawn of the Intelligent Therapeutic Interventions; 1.3 Devices and Patient Empowerment; References; 2 Major Challenges and Limitations of Big Data Analytics; 2.1 Challenges in Data Standardization; 2.2 Challenges in Machine Learning in Psychiatry; 2.2.1 Overview of Machine Learning in Psychiatry; 2.2.2 Feature Selection, Classification, and Validation Algorithms |
|
2.2.2.1 The Feature Selection Process2.2.2.2 The Classification Process; 2.2.2.3 Validation and Measurement of Performance; 2.2.3 Further Considerations in the Development of a Machine Learning Model; 2.2.3.1 The Over/Underfitting Problem; 2.2.3.2 Missing Data; 2.2.3.3 Imbalanced Data; 2.3 Challenges from Data to Knowledge; References; 3 A Clinical Perspective on Big Data in Mental Health; 3.1 Examples of Machine Learning Today in Psychiatry: Medication Selection; 3.2 Examples of Machine Learning Today in Psychiatry: Suicide Prediction |
|
3.3 Examples of Machine Learning Today in Psychiatry: Symptom/Outcome Monitoring3.4 Next Step and the Future of Machine Learning in Psychiatry; 3.4.1 Outsource Simple Tasks to Machines; 3.4.2 Population Level Risk Stratification and New Disease Models; 3.4.3 Better Use of Medical Records Data; 3.5 What are the Next Steps to Realize that Future; 3.5.1 A Need for High Quality Data; 3.5.2 A Need for Good and (New) Study Design; 3.5.3 A Need to Realize and Plan for Unintended Consequence; 3.6 Conclusion; References; 4 Big Data Guided Interventions: Predicting Treatment Response; 4.1 Introduction |
|
4.2 Depressive Subtypes: Unsupervised Learning Techniques in MDD4.3 Prediction of Treatment Outcome; 4.3.1 Big Data: Sociodemographic, Clinical and Genetic Predictors; 4.3.2 Supervised Learning Techniques in MDD: Towards Precision Medicine; 4.3.2.1 Supervised Learning Techniques in MDD: Clinical Predictors; 4.3.2.2 Multimodal Data: Combining Clinical, Genetic and Imaging Predictors; 4.3.2.3 Combining Supervised and Unsupervised Learning: Dealing with Heterogeneity; 4.4 Summary and Outlook; References; 5 The Role of Big Data Analytics in Predicting Suicide; 5.1 Introduction |
|
5.2 Earlier Multivariate Analyses Predicting Suicide Among Inpatients5.3 Earlier Multivariate Analyses Predicting Suicide Among Other High-Risk Patients; 5.4 Reconsidering the Rationale for Rejecting Standardized Suicide Prediction Tools; 5.5 Machine Learning Analyses Predicting Suicide Among High-Risk Patients; 5.6 Machine Learning Analyses Predicting Suicide in Total Patient Populations; 5.7 Other Machine Learning Studies Aimed at Predicting Suicidality; 5.8 Future Directions in Using ML for Suicide Risk Prediction |
| Summary |
This book integrates the concepts of big data analytics into mental health practice and research. Mental disorders represent a public health challenge of staggering proportions. According to the most recent Global Burden of Disease study, psychiatric disorders constitute the leading cause of years lost to disability. The high morbidity and mortality related to these conditions are proportional to the potential for overall health gains if mental disorders can be more effectively diagnosed and treated. In order to fill these gaps, analysis in science, industry, and government seeks to use big data for a variety of problems, including clinical outcomes and diagnosis in psychiatry. Multiple mental healthcare providers and research laboratories are increasingly using large data sets to fulfill their mission. Briefly, big data is characterized by high volume, high velocity, variety and veracity of information, and to be useful it must be analyzed, interpreted, and acted upon. As such, focus has to shift to new analytical tools from the field of machine learning that will be critical for anyone practicing medicine, psychiatry and behavioral sciences in the 21st century. Big data analytics is gaining traction in psychiatric research, being used to provide predictive models for both clinical practice and public health systems. As compared with traditional statistical methods that provide primarily average group-level results, big data analytics allows predictions and stratification of clinical outcomes at an individual subject level. Personalized Psychiatry - Big Data Analytics in Mental Health provides a unique opportunity to showcase innovative solutions tackling complex problems in mental health using big data and machine learning. It represents an interesting platform to work with key opinion leaders to document current achievements, introduce new concepts as well as project the future role of big data and machine learning in mental health |
| Bibliography |
Includes bibliographical references and index |
| Notes |
Online resource; title from PDF title page (EBSCO, viewed February 14, 2019) |
| Subject |
Psychiatry -- Data processing
|
|
Psychiatry -- Research -- Data processing
|
|
Big data.
|
|
Big Data
|
|
Mental Health
|
|
Data Mining -- methods
|
|
Precision Medicine -- methods
|
|
mental health.
|
|
HEALTH & FITNESS -- Diseases -- General.
|
|
MEDICAL -- Clinical Medicine.
|
|
MEDICAL -- Diseases.
|
|
MEDICAL -- Evidence-Based Medicine.
|
|
MEDICAL -- Internal Medicine.
|
|
Big data
|
|
Psychiatry -- Data processing
|
|
Psychiatry -- Research -- Data processing
|
| Genre/Form |
Electronic books
|
| Form |
Electronic book
|
| Author |
Kapczinski, Flávio., editor
|
|
Mwangi, Benson, editor
|
|
Passos, Ives Cavalcante, editor
|
| ISBN |
9783030035532 |
|
3030035530 |
|
9783030035549 |
|
3030035549 |
|
