AIM-HEALTH: Artificial intelligence-mediated discharge document for accessible healthcare. A study protocol
1
Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, Università di Brescia, Brescia, Italy
2
Cardiology Unit, ASST Spedali Civili di Brescia, Brescia, Italy
3
Nephrology Unit, ASST Spedali Civili di Brescia, Brescia, Italy
4
Forensic Medicine Unit, ASST Spedali Civili di Brescia, Brescia, Italy
5
Centre of Bioethics Research, Università di Brescia, Brescia, Italy
6
Clinical Trial Center, ASST Spedali Civili di Brescia, Brescia, Italy
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
BACKGROUND:
Hospital discharge reports (HDR) support continuity of care, yet their specialised terminology may hinder patient understanding and post-discharge self-management, particularly among individuals with limited health literacy (HL)(1-3). AIM-HEALTH aims to develop and evaluate a clinician-validated, AI-powered supplementary discharge document (SDD) to support comprehension of HDR content, tailored to patients’ HL levels(4).
METHODS:
This prospective, observational, non-interventional study will enrol 200 adults from the nephrology and cardiology units at ASST Spedali Civili hospital. Following written informed consent, participants’ HL will be assessed and combined with HDR structured data and an audio-recorded discharge interview to generate two outputs using locally deployed agentic AIs powered by open-weight LLM: (i) an HL-tailored SDD for patient use and (ii) a clinical performance report (CPR) highlighting omissions and inconsistencies between the HDR and the discharge interview to support clinical safety. Clinicians will validate the SDD using a QUEST-informed tool assessing accuracy, completeness, clarity, utility, and safety domains(5). All outputs will undergo clinical assessment; only suitable outputs will be retained, while corrections and unsuitable outputs will be used to iteratively refine the system. Patients will assess SDD perceived accessibility, comprehensibility, usefulness, and engagement. Data processing follows on-premise, DPIA-defined safeguards (data minimisation, pseudonymisation, security/incident management).
RESULTS:
Expected results include: (i) technical feasibility and workflow indicators (completion and SDD withholding rates); (ii) clinician-rated accuracy, appropriateness, completeness, and safety of SDDs; (iii) perceived utility of the CPR for identifying omissions and inconsistencies between HDRs and discharge interviews; (iv) patient-reported accessibility, comprehensibility, usefulness, and engagement at ~1-month follow-up; and (v) associations between SDD readability index scores and perceived comprehensibility.
CONCLUSIONS:
AIM-HEALTH aims to streamline discharge workflow, improve post-discharge comprehension and safety, particularly for chronic conditions, and reduce avoidable readmissions linked to misunderstanding, under on-premise data protection and clinician validation. AIM-HEALTH is supported by a competitive grant awarded by Fondazione Cariplo.
Hospital discharge reports (HDR) support continuity of care, yet their specialised terminology may hinder patient understanding and post-discharge self-management, particularly among individuals with limited health literacy (HL)(1-3). AIM-HEALTH aims to develop and evaluate a clinician-validated, AI-powered supplementary discharge document (SDD) to support comprehension of HDR content, tailored to patients’ HL levels(4).
METHODS:
This prospective, observational, non-interventional study will enrol 200 adults from the nephrology and cardiology units at ASST Spedali Civili hospital. Following written informed consent, participants’ HL will be assessed and combined with HDR structured data and an audio-recorded discharge interview to generate two outputs using locally deployed agentic AIs powered by open-weight LLM: (i) an HL-tailored SDD for patient use and (ii) a clinical performance report (CPR) highlighting omissions and inconsistencies between the HDR and the discharge interview to support clinical safety. Clinicians will validate the SDD using a QUEST-informed tool assessing accuracy, completeness, clarity, utility, and safety domains(5). All outputs will undergo clinical assessment; only suitable outputs will be retained, while corrections and unsuitable outputs will be used to iteratively refine the system. Patients will assess SDD perceived accessibility, comprehensibility, usefulness, and engagement. Data processing follows on-premise, DPIA-defined safeguards (data minimisation, pseudonymisation, security/incident management).
RESULTS:
Expected results include: (i) technical feasibility and workflow indicators (completion and SDD withholding rates); (ii) clinician-rated accuracy, appropriateness, completeness, and safety of SDDs; (iii) perceived utility of the CPR for identifying omissions and inconsistencies between HDRs and discharge interviews; (iv) patient-reported accessibility, comprehensibility, usefulness, and engagement at ~1-month follow-up; and (v) associations between SDD readability index scores and perceived comprehensibility.
CONCLUSIONS:
AIM-HEALTH aims to streamline discharge workflow, improve post-discharge comprehension and safety, particularly for chronic conditions, and reduce avoidable readmissions linked to misunderstanding, under on-premise data protection and clinician validation. AIM-HEALTH is supported by a competitive grant awarded by Fondazione Cariplo.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
