What is it about?
Leave Against Medical Advice (LAMA), also termed Discharge Against Medical Advice (DAMA), is a clinically important event associated with interrupted treatment, avoidable care gaps, readmission and other adverse outcomes. Existing evidence indicates that LAMA is influenced by interacting clinical, socioeconomic, behavioural, communication and health-system factors. Although recent machine-learning studies demonstrate that LAMA/DAMA can be predicted from routinely collected electronic health record (EHR) and hospital data, prediction alone does not address the modifiable reasons that precipitate premature departure.
Featured Image
Why is it important?
Leave Against Medical Advice (LAMA) should not be regarded merely as a documentationevent. It represents a clinically consequential interruption of an intended episode of care andmay reflect a mismatch between patient needs, treatment plans, communication, availableresources and health-system processes (Alfandre, 2009; Southern et al., 2012). Prior literaturehas identified a range of recurrent associations, including socioeconomic disadvantage, lack ofinsurance, substance use, mental health conditions and previous AMA discharge, although the magnitude and direction of individual predictors vary across populations and clinical settings. Recent evidence from an emergency department in New Delhi identified perceived improvement after initial treatment, intensive care unit bed unavailability, financial constraints and perceived infection risk among prominent reasons for LAMA; lack of health insurance and lower family income were independent predictors in that cohort
Perspectives
The Predict–Prevent–Protect framework addresses LAMA as a multifactorial clinical and continuity-of-care challenge rather than solely as a discharge documentation event. By combining explainable risk prediction with clinician review, patient-centred communication and interventions directed at potentially modifiable barriers, the proposed system is designed to support timely action before a decision to leave becomes irreversible. When a competent patient nevertheless chooses LAMA, the Protect pathway maintains the focus on harm reduction through medication reconciliation, return precautions, follow-up planning and appropriate post-discharge contact. The framework also places human oversight, transparency, fairness, safety monitoring and clinical governance around the use of AI. Because this manuscript presents a research protocol and conceptual implementation framework, its value must be established through prospective clinical evaluation. The key test will be whether the integrated workflow reduces avoidable LAMA and improves continuity-of-care outcomes without increasing alert burden, inequity, loss of trust or interference with patient autonomy, and whether the approach remains workable across different clinical environments.
Dr Ajit Pal Singh
Sharda University
Read the Original
This page is a summary of: Predict–Prevent–Protect: An Explainable AI-Driven Patient-Centred Early-Warning and Intervention System to Prevent Leave Against Medical Advice and Improve Continuity of Care, January 2026, Sciencedomain International,
DOI: 10.9734/bpi/kitsr/v3/8021.
You can read the full text:
Contributors
The following have contributed to this page
