Neural network based on adaptive resonance theory as compared to experts in suggesting treatment for schizophrenic and unipolar depressed in-patients

Screening of Mood Symptoms Using MMPI-2-RF Scales: An Application of Machine Learning Techniques

(1) Background: The MMPI-2-RF is the most widely used and most researched test among the tools for assessing psychopathology, and previous studies have established its validity. Mood disorders are the most common mental disorders worldwide; they present difficulties in early detection, go undiagnosed in many cases, and have a poor prognosis. (2) Methods: We analyzed a total of 8645 participants. We used the PHQ-9 to evaluate depressive symptoms and the MDQ to evaluate hypomanic symptoms. We used the 10 MMPI-2 Restructured Form scales and 23 Specific Problems scales for the MMPI-2-RF as predictors. We performed machine learning analysis using the k-nearest neighbor classification, linear discriminant analysis, and random forest classification. (3) Results: Through the machine learning technique, depressive symptoms were predicted with an AUC of 0.634-0.767, and the corresponding value range for hypomanic symptoms was 0.770-0.840. When using RCd to predict depressive symptoms, the AUC was 0.807, but this value was 0.840 when using linear discriminant classification. When predicting hypomanic symptoms with RC9, the AUC was 0.704, but this value was 0.767 when using the linear discriminant method. (4) Conclusions: Using machine learning analysis, we defined that participants' mood symptoms could be classified and predicted better than when using the Restructured Clinical scales.

A scoping review of machine learning in psychotherapy research

Machine learning (ML) offers robust statistical and probabilistic techniques that can help to make sense of large amounts of data. This scoping review paper aims to broadly explore the nature of research activity using ML in the context of psychological talk therapies, highlighting the scope of current methods and considerations for clinical practice and directions for future research. Using a systematic search methodology, fifty-one studies were identified. A narrative synthesis indicates two types of studies, those who developed and tested an ML model (k=44), and those who reported on the feasibility of a particular treatment tool that uses an ML algorithm (k=7). Most model development studies used supervised learning techniques to classify or predict labeled treatment process or outcome data, whereas others used unsupervised techniques to identify clusters in the unlabeled patient or treatment data. Overall, the current applications of ML in psychotherapy research demonstrated a range of possible benefits for indications of treatment process, adherence, therapist skills and treatment response prediction, as well as ways to accelerate research through automated behavioral or linguistic process coding. Given the novelty and potential of this research field, these proof-of-concept studies are encouraging, however, do not necessarily translate to improved clinical practice (yet).

Machine Learning Approaches for Clinical Psychology and Psychiatry

Machine learning approaches for clinical psychology and psychiatry explicitly focus on learning statistical functions from multidimensional data sets to make generalizable predictions about individuals. The goal of this review is to provide an accessible understanding of why this approach is important for future practice given its potential to augment decisions associated with the diagnosis, prognosis, and treatment of people suffering from mental illness using clinical and biological data. To this end, the limitations of current statistical paradigms in mental health research are critiqued, and an introduction is provided to critical machine learning methods used in clinical studies. A selective literature review is then presented aiming to reinforce the usefulness of machine learning methods and provide evidence of their potential. In the context of promising initial results, the current limitations of machine learning approaches are addressed, and considerations for future clinical translation are outlined.

Mini medical record application: annual register for flu shot vaccinations

This application is an Intranet-based system. A database has been established utilizing patient information on the basis of age, medical diagnosis and employment history. If a health care provider or support staff states that a patient is over 65 years of age or has been diagnosed with a chronic disease and this limits the patient's ability to fight off infection, the need for preventive care is activated. In this situation the preventive care is the administration of an annual flu shot. For anyone over 65 years of age or with a chronic illness, a bulk mail of reminder cards with the dates of availability of injection is generated and mailed. All health care workers are notified at work of vaccination sites that they can use. In addition, should a patient have an appointment with a provider and a preventive flu injection is indicated, a reminder appears on the registration form. This reminder indicates a flu shot is needed as well as other preventive intervention.

Information technology in the future of health care

Technology advances have changed the face of health care. This paradigm shift blurred the boundaries between public health, acute care, and prevention. Technology's role in the diagnosis, treatment assignment, follow-ups, and prevention will be reviewed and future impact projected. The understanding of shift in our expectation for each aspect of health care is critical so that levels of success are understood. Technology advances in health care delivery will be discussed. Specific applications are presented and explained and future trends discussed. Four applications are defined, and related to categories of technologies and their attributes.

Antipsychotic drugs for non-affective psychosis during pregnancy and postpartum

BACKGROUND

Antipsychotics are commonly prescribed for women suffering psychotic illnesses during pregnancy and the postpartum period. The potential adverse consequences of these different options are multiple and complex, impacting on the foetus, neonate, infant and early development of the child as well as the woman herself.

OBJECTIVES

To establish whether the benefits of taking antipsychotic drugs outweigh the risks for pregnant or post partum women.

SEARCH STRATEGY

The Cochrane Schizophrenia Group's Register (January 2003) was searched in order to identify all published trials of women during pregnancy or the postpartum period. We inspected all references of all identified studies. If any studies had been found, the first authors of each included study would have been contacted.

SELECTION CRITERIA

Randomised controlled clinical trials investigating the effects of any type of antipsychotic drug compared with any other treatment option (including standard psychosocial care, any other antipsychotic drug, or an alternative therapy such as electro-convulsive therapy or cognitive behavioural therapy) and involving pregnant women and/or women during the postpartum period diagnosed with a non-affective psychotic disorder.

DATA COLLECTION AND ANALYSIS

Citations, and where possible, abstracts were independently inspected by reviewers and the papers ordered were scrutinised and quality assessed. Data would have been extracted independently by at least two reviewers. Binary outcomes were to have been analysed using Relative Risks (RR) and their 95% Confidence Intervals (CI).

MAIN RESULTS

We found no trials that met the broad inclusion criteria.

REVIEWERS' CONCLUSIONS

Current guidelines and clinical practice for the use of antipsychotic drugs in women with non-affective disorders during pregnancy and postpartum are not based on evidence from randomised controlled trials. Although ethical concerns have to date precluded the use of randomised controlled trials to address this research topic, the continued use of antipsychotic drugs in this group of women in itself poses significant clinical and ethical problems. Evidence is required from large pragmatic trials that reflect routine clinical practice, examine a broad range of outcomes and accurately quantify risks and benefits to both mothers and their offspring, so that comparison between different treatment options can be made.

A review of evidence of health benefit from artificial neural networks in medical intervention

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rĵle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.

Technology transfer with system analysis, design, decision making, and impact (Survey-2000) in acute care hospitals in the United States

This paper provides the results of the Survey-2000 measuring technology transfer for management information systems in health care. The relationships with systems approaches, user involvement, usersatisfaction, and decision-making were measured and are presented. The survey also measured the levels Internet and Intranet presents in acute care hospitals, which will be discussed in future articles. The depth of the survey includes e-commerce for both business to business and customers. These results are compared, where appropriate, with results from survey 1997 and changes are discussed. This information will provide benchmarks for hospitals to plan their network technology position and to set goals. This is the first of three articles based upon the results of the Srvey-2000. Readers are referred to a prior article by the author that discusses the survey design and provides a tutorial on technology transfer in acute care hospitals.

Neural network based automatic diagnosis of children with brain dysfunction

This paper proposes the use of multilayer perceptron for brain dysfunction diagnosis. The performance of MLP was better than that of Discriminant Analysis and Decision Tree classifiers, with an 85% accuracy rate in an experimental test involving 332 subjects. In addition, the neural network employing Bayesian learning was able to identify the most important input variable. These two results demonstrate that the neural network can be effectively used in the diagnosis of children with brain dysfunction.

Tutorial on technology transfer and survey design and data collection for measuring Internet and Intranet existence, usage, and impact (survey-2000) in acute care hospitals in the United States

This paper provides a tutorial of technology transfer for management information systems in health care. Additionally it describes the process for a national survey of acute care hospitals using a random sample of 813 hospitals. The purpose of the survey was to measure the levels of Internet and Intranet existence and usage in acute care hospitals. The depth of the survey includes e-commerce for both business to business and with customers. The relationships with systems approaches, user involvement, user satisfaction and decision-making will be studied. Changes with results of a prior survey conducted in 1997 can be studied and enabling and inhabiting factors identified. This information will provide benchmarks for hospitals to plan their network technology position and to set goals.

Decision-making with and without information technology in acute care hospitals: survey in the United States

These survey results are from a national survey of acute care hospitals. A random sample of 813 hospitals was selected with 115 responding and 33 incorrect addresses resulting in a 15% response rate. The purpose of the study was to measure the extent of information systems integration in the financial, medical, and administrative systems of the hospitals. Decision making with and without information technology is explored based upon the survey data. The results indicate why and how meetings are held. Necessary changes in the decision-making environment are identified for decision making utilizing information technology to be successful. These results will provide a benchmark for hospitals to determine their technology transfer position and to set goals for computer assisted decision-making.

Backpropagation and adaptive resonance theory in predicting suicidal risk

The ability of backpropagation and adaptive resonance theory (ART) neural networks to predict the probability of complete suicide, within a two year span, in major psychiatric patients was investigated. Variables associated with suicide risk were collected from the files of 161 hospitalized psychiatric patients with a 10 year or greater history of illness. 84 patients were hospitalized due to suicide attempts and 77 had no previous suicide attempts or ideations. Suicide attempts were rated as medically serious suicide attempts (MSSA) or non-MSSA and used for training the systems. The ability of the neural networks was evaluated by screening the extremes of the suicidal spectrum (1) 54 records of patients who committed suicide and (2) 150 records of patients who never had suicidal thoughts. The records were taken from 3 hospitals, in various geographic regions in Israel. Neither neural network system is reliable in predicting suicide, however, records from one hospital, Gehah Hospital, were better identified than those from the two other hospitals (p < 0.05 for PPV; p < 0.01 for specificity). At present, neural networks are not reliable instruments for evaluating suicidal risk due to the significant number of false positive results. When low risk was indicated reliability was greater (NPV = 75.28%, specificity = 97.10% with ART; NPV = 91.76%, specificity = 95.12% with backpropagation). However, PPV, NPV and specificity rates of both systems achieved with Gehah Hospital records suggest that using a direct-subjective questionnaire may produce better results in the future. ART and backpropagation performed similarly in all measurements.