Efficacy of Artificial Intelligence for Gatekeeping in Referrals to Specialized Care

Официальное название

Efficacy of an Artificial Intelligence Algorithm for Gatekeeping in Referrals From Primary Care to Specialized Care: a Randomized Controlled Trial

Обзор

In Rio Grande do Sul, Brazil, the demand for specialty care referrals has increased sharply with the adoption of the electronic regulatory system, especially in rural areas. In 2023 alone, over 79,000 referrals were submitted monthly, totaling 1.7 million annual gatekeeping decisions. Due to workforce limitations, nearly 70% of referrals are authorized automatically, often without clinical validation. This leads to delays for high-risk patients, unnecessary specialist visits, and a growing backlog, currently over 172,000 pending referrals. To address this, an AI algorithm was developed to triage referrals based on urgency and appropriateness. The investigators propose a prospective controlled study with randomized implementation of the AI tool across selected specialty queues in the electronic referral system. The population will consist of referrals from specialties waitlists from municipalities in Rio Grande do Sul. Specialties to be included will be selected by the State Health Department prospectively according to gatekeeping needs. The intervention will be an AI-based triage algorithm. The control will be a standard gatekeeping process. The primary outcome is the proportion of referrals with a final decision (authorized or redirected to primary care) within six months; secondary outcomes include time to decision and appointment, system-level performance metrics. Referrals will be randomly assigned to algorithmic or human gatekeeping with a 1:1 ratio. The algorithm classifies referrals into two groups: not authorized (pending more data or teleconsultation), authorized. Authorization cases are further divided into routine and high-risk referrals to help the manage demand. Each AI prediction provides a probability from 0 to 1 of authorization (or deferring). The implementation threshold is set at 0.8; cases below this level will be classified as low confidence for decision and will not be included. According to the State Health Department's decisions, several referral lines are expected to be selected for the intervention. A sample size 934 (467 per arm) for each included specialty was calculated to detect a 1.2 relative risk for the primary outcome with 90% power and 5% significance.

Вмешательства

• Другое Standard gatekeeping
  Human evaluators (mostly physicians) review referrals and determine, based on established protocols, whether they should be authorized.
• Другое AI algorithm
  An AI algorithm was developed to perform the first evaluation (triaging) of the referrals inserted in the electronic referral system from the Rio Grande do Sul Health Department.
• Другое Subsequent interactions between primary care and regulation system
  After the first evaluation of a referral, several subsequent rounds of interaction between gatekeepers and primary care physicians can be conducted to further detail patient needs and urgency.

Первичные конечные точки

• Referrals with final decision [Срок оценки: 6 months]

Вторичные конечные точки (4)

• Time to final decision [Срок оценки: 6 months]
• Time to consult in high-risk patients [Срок оценки: 6 months]
• Use of remote consultations [Срок оценки: 6 months]
• Waitlist size over time [Срок оценки: 6 months]

Критерии участия

Критерии включения

• All referrals from a given specialty (waitlist) will be eligible.
• Specialties will be selected following Rio Grande do Sul Health Department priorities.

Критерии исключения

• Referrals that the AI algorithm can not evaluate. These include referrals with attachments (further information in image or PDF files) and referrals with previous rounds of discussion.
• Referrals in which the algorithm has low confidence in the decision (i.e., informed data lead to a decision with a probability below 80%) will not be included in the study.

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Нет

Дизайн исследования

Распределение

Рандомизированное

Модель

Параллельные группы

Маскирование

Открытое

Основная цель

Организация здравоохранения

Центры проведения

Бразилия · 1 центр

• Central de Regulação Ambulatorial — Porto Alegre

Идентификаторы

NCT: NCT07019116 · 2018-0589

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗