Identification of high-risk patients for referral through machine learning assisting the decision making to manage minor ailments in community pharmacies.

Background: Data analysis techniques such as machine learning have been used for assisting in triage and the diagnosis of health problems. Nevertheless, it has not been used yet to assist community pharmacists with services such as the Minor Ailment Services These services have been implemented to reduce the burden of primary care consultations in general medical practitioners (GPs) and to allow a better utilization of community pharmacists' skills. However, there is a need to refer high-risk patients to GPs. Aim: To develop a predictive model for high-risk patients that need referral assisting community pharmacists' triage through a minor ailment service. Method: An ongoing pragmatic type 3 effectiveness-implementation hybrid study was undertaken at a national level in Spanish community pharmacies since October 2020. Pharmacists recruited patients presenting with minor ailments and followed them 10 days after the consultation. The main outcome measured was appropriate medical referral (in accordance with previously co-designed protocols). Nine machine learning models were tested (three statistical, three black box and three tree models) to assist pharmacists in the detection of high-risk individuals in need of referral. Results: Over 14'000 patients were included in the study. Most patients were female (68.1%). With no previous treatment for the specific minor ailment (68.0%) presented. A percentage of patients had referral criteria (13.8%) however, not all of these patients were referred by the pharmacist to the GP (8.5%). The pharmacists were using their clinical expertise not to refer these patients. The primary prediction model was the radial support vector machine (RSVM) with an accuracy of 0.934 (CI95 = [0.926,0.942]), Cohen's kappa of 0.630, recall equal to 0.975 and an area under the curve of 0.897. Twenty variables (out of 61 evaluated) were included in the model. radial support vector machine could predict 95.2% of the true negatives and 74.8% of the true positives. When evaluating the performance for the 25 patient's profiles most frequent in the study, the model was considered appropriate for 56% of them. Conclusion: A RSVM model was obtained to assist in the differentiation of patients that can be managed in community pharmacy from those who are at risk and should be evaluated by GPs. This tool potentially increases patients' safety by increasing pharmacists' ability to differentiate minor ailments from other medical conditions.

Detección e intervención en personas de riesgo depadecer diabetes en farmacias comunitarias de laprovincia de Valencia (DETECTA SUCRE) / Detection and intervention of people at risk of diabetes in community pharmacies of Valencia

Objetivo: detectar personas en riesgo alto o muy alto de padecer diabetes mellitus tipo 2 (DM2) o alteraciones del metabolismo de los hidratos de carbono, derivación para posible diagnóstico al médico yrealizar una intervención educativa.Métodos: estudio observacional transversal y longitudinal prospectivo con intervención educativa en farmacias comunitarias situadas en la provincia de Valencia entre junio y noviembre de 2018. Se incluyeronusuarios de las farmacias comunitarias, mayores de 18 años, no diagnosticados de DM2 que aceptaron realizar la encuesta. Muestreo no probabilístico.Variable principal: puntuación en el test Findrisc, determinación capilar (si F≥15), intervención y número de diagnósticos de DM2 y preDM2. Las diferencias entre grupos se calcularon con el test de chi-cuadrado, t de Student o de Wilcoxon.Resultados: el estudio se realizó en 25 farmacias. La muestra incluyó a 752 usuarios. De ellos, 148 (19,7%) tenían alto o muy alto riesgo de DM2 (F≥15). Se realizaron 118 determinaciones capilares válidas (22 no aceptaron y 8 no la repitieron), 78 (10,4%) tuvieron resultados superiores a los normales y a 48 (6,4%) se les derivó al médico. 32 de estos no fueron al médico o no informaron al farmacéutico del resultado. De los 16 que conocemos el resultado, 12 (1,6%) fueron diagnosticados de diabetes o prediabetes.Conclusiones: los resultados de este estudio piloto dejan entrever la utilidad de la farmacia comunitaria como agente con un papel importante en el cribado de DM2 al detectar el presente trabajo casi un20% de usuarios con un riesgo elevado de padecer la enfermedad.

Colaboración farmacéutico-médico en la elaboración de protocolos consensuados para el tratamiento de síntomas menores: programa 'INDICA+PRO' / Collaborative care protocols for the management of minor ailments agreed between pharmacists and medical practitioners: INDICA+PRO Study

Introducción: la colaboración entre médicos y farmacéuticos es necesaria en el manejo de los síntomas menores, ya que el paciente acude a ambos profesionales sanitarios para su tratamiento. El objetivo del estudio fue elaborar protocolos de trabajo consensuados entre farmacéuticos comunitarios y médicos de atención primaria para el Servicio de Indicación Farmacéutica (SIF). Material y método: se utilizaron dos metodologías: revisión bibliográfica y grupo de expertos para el consenso. Estos protocolos se actualizaron y diseñaron a partir de un documento previo de 2008. En el grupo de expertos se incluyeron cuatro farmacéuticos comunitarios de SEFAC (2), MICOF (2) y cuatro médicos de atención primaria de semFYC (2) y SEMERGEN (2). Resultados: se consensuaron protocolos de trabajo para 31 síntomas menores distribuidos en cinco grupos: respiratorios, dolor moderado, digestivos, dermatológicos y otros. Se añadieron cinco síntomas nuevos al documento de partida. Respecto a la estructura de cada síntoma se consideró: concepto, causas más frecuentes, criterios de derivación al médico (edad, síntomas de alarma, duración de los síntomas, otros problemas de salud y/o medicamentos y situaciones especiales), recomendaciones para la prevención y tratamiento (no farmacológico y farmacológico). Conclusión: el documento desarrollado mediante colaboración entre profesionales de la medicina y la farmacia es una herramienta que contribuye a la mejora de la actuación del farmacéutico en el manejo de los síntomas menores desde la farmacia comunitaria, con énfasis en la definición de indicadores que señalan la necesidad de derivar el paciente al médico de atención primaria

Background: To increase the collaboration between community pharmacists and medical practitioners working in primary care it is critical to have collaborative protocols in place. Minor ailments could be a good example where this collaboration would benefit patient care as patients are seeking treatment in both settings. These collaborative protocols would assist in diminishing the variability of treatments in both settings. The aim of the study was to develop care protocols for minor ailments agreed between medical practitioners and pharmacists Methods: Two different methodologies were used to arrive at a consensus for the proto-cols: literature review and expert group. Some of the clinical protocols were updated from a previous document created in 2008. Expert group was composed of four community pharma-cists (SEFAC, MICOF) and four medical practitioners (SemFyC y Semergen). Results: Thirty-one protocols for minor ailments were agreed and allocated to five groups (five new minor ailments protocols were added: respiratory tract-related conditions, gastrointestinal disturbance, pain, dermatological problems and others.Protocols were structured following: definition, more frequent causes, referral criteria (pa-tient’s age, red flags, symptom’s duration, patient’s health problems and treatments and physiological situations), recommendations for management (prevention, non-pharmacological and pharmacological treatment) and references used. Conclusions: Clinical protocols agreed between health professionals of medicine and phar-macy are a tool that contribute to better management of minor ailments in community pharmacy