Irish journal of medical science · 2026
Artificial intelligence improved efficiency of the computed tomography program.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wertheim Ofir, Ben-Zakai Itiel, Rabl Yaniv, Jerdev Michael, Blum Arnon
Аннотация
BACKGROUND: Precious imaging tools like computed tomography (CT) are high-demand, time-limited resources that must serve both inpatients and outpatients. It is therefore essential to use them efficiently and accurately. We aimed to enhance accuracy, reduce administrative burden, and expedite patient care - while ensuring rigorous clinical oversight through human review of artificial intelligence (AI) outputs, including optical character recognition (OCR) and natural language processing (NLP).
METHODS: At Tzafon Medical Center, we implemented a hybrid AI workflow consisting of: (1) optical character recognition (OCR) with provider-specific pattern matching for automated extraction of patient and referral data; (2) natural language processing (NLP) via the DigitalOwl service for structured clinical concept extraction (diagnoses, comorbidities, negated findings) with human-in-the-loop validation; (3) a deterministic rule-based engine that matched clinical requirements with scanner availability to recommend CT protocols, schedule appointments, and generate patient preparation instructions.
RESULTS: Integration of AI-powered document analysis using OCR, NLP, and a statistical decision engine increased annual CT examinations by 20% (from 10,000 to 12,000), saved approximately 10 staff hours per week, reduced patient waiting times by 30%, and improved patient satisfaction by 12%. Complaint rates fell from 5% in 2022 to 1% in 2024.
DISCUSSION: AI-assisted workflow integration proved to be a cost-effective and efficient approach that improved safety, reduced staff workload, and enhanced satisfaction for both to patients and medical staff.
METHODS: At Tzafon Medical Center, we implemented a hybrid AI workflow consisting of: (1) optical character recognition (OCR) with provider-specific pattern matching for automated extraction of patient and referral data; (2) natural language processing (NLP) via the DigitalOwl service for structured clinical concept extraction (diagnoses, comorbidities, negated findings) with human-in-the-loop validation; (3) a deterministic rule-based engine that matched clinical requirements with scanner availability to recommend CT protocols, schedule appointments, and generate patient preparation instructions.
RESULTS: Integration of AI-powered document analysis using OCR, NLP, and a statistical decision engine increased annual CT examinations by 20% (from 10,000 to 12,000), saved approximately 10 staff hours per week, reduced patient waiting times by 30%, and improved patient satisfaction by 12%. Complaint rates fell from 5% in 2022 to 1% in 2024.
DISCUSSION: AI-assisted workflow integration proved to be a cost-effective and efficient approach that improved safety, reduced staff workload, and enhanced satisfaction for both to patients and medical staff.