A predictive index was developed using 34 intake variables from 416 alcoholic inpatient program participants at a Veterans Administration Medical Center (VAMC). Using drinking behavior as the outcome criteria, an R-squared value of 0.562 was achieved and 65% of the index-generating sample was correctly classified. The index was cross-validated on 61 inpatients at 4 months posttreatment. It achieved a point biserial correlation of 0.389 and correctly classified 66% of the sample. The index, unprecedentedly, was generalized to three other VAMCs and achieved an overall r of 0.393 and correctly classified 61% of the generalization subjects.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3109/10826088809085115 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Performance of Vasopressin Stimulated Bilateral Inferior Petrosal Sinus Sampling in Corticotropin Dependent Cushing's Syndrome with Negative or Equivocal 3 Tesla Contrast Enhanced Magnetic Resonance Imaging of Pituitary.
Indian J Endocrinol Metab
December 2024
Department of Endocrinology, Mahatma Gandhi Medical College and Hospital, Jaipur, Rajasthan, India.
Introduction: Corticotropin releasing hormone (CRH)-stimulated bilateral inferior petrosal sinus sampling (BIPSS) is the most accurate procedure in the differential diagnosis of adrenocorticotropic hormone (ACTH)-dependent Cushing's syndrome (CS) with a sensitivity of 88-100% and a specificity of 67-100%. However, CRH is not available globally currently. We undertook this study of BIPSS using lysine vasopressin (LVP) as an agent to stimulate the release of ACTH from corticotrophs.
View Article and Find Full Text PDFExplore the factors related to the death of offspring under age five and appraise the hazard of child mortality using machine learning techniques in Bangladesh.
BMC Public Health
January 2025
Department of Statistics and Data Science, Jahangirnagar University, Dhaka, 1342, Bangladesh.
Background: Child mortality is a reliable and significant indicator of a nation's health. Although the child mortality rate in Bangladesh is declining over time, it still needs to drop even more in order to meet the Sustainable Development Goals (SDGs). Machine Learning models are one of the best tools for making more accurate and efficient forecasts and gaining in-depth knowledge.
View Article and Find Full Text PDFThe representation of stimulus features during stable fixation and active vision.
J Neurosci
January 2025
The Department of Psychology and The Department of Cognitive and Brain Sciences, The Hebrew University of Jerusalem.
Predictive updating of an object's spatial coordinates from pre-saccade to post-saccade contributes to stable visual perception. Whether object features are predictively remapped remains contested. We set out to characterise the spatiotemporal dynamics of feature processing during stable fixation and active vision.
View Article and Find Full Text PDFStroke Triage Alpha Rescue Score (STARS): Prehospital phone-based tool to identify cerebral large vessel occlusion.
Rev Neurol (Paris)
January 2025
Unité neurovasculaire, Centre Hospitalier Métropole Savoie, Chambéry, France. Electronic address:
Introduction: Prehospital identification of stroke patients with large vessel occlusion (LVO) is crucial to optimize transport to an endovascular thrombectomy (EVT)-capable center. Existing scores require medical or paramedical expertise and specific teachings. We aimed to validate a simple prehospital phone-based score for LVO identification.
View Article and Find Full Text PDFEvaluating robustly standardized explainable anomaly detection of implausible variables in cancer data.
J Am Med Inform Assoc
January 2025
Information Systems and Business Administration, Johannes Gutenberg University, Mainz 55128, Germany.
Objectives: Explanations help to understand why anomaly detection algorithms identify data as anomalous. This study evaluates whether robustly standardized explanation scores correctly identify the implausible variables that make cancer data anomalous.
Materials And Methods: The dataset analyzed consists of 18 587 truncated real-world cancer registry records containing 8 categorical variables describing patients diagnosed with bladder and lung tumors.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!