Artificial intelligence and machine learning for anaphylaxis algorithms.

PURPOSE OF REVIEW: Anaphylaxis is a severe, potentially life-threatening allergic reaction that requires rapid identification and intervention. Current management includes early recognition, prompt administration of epinephrine, and immediate medical attention. However, challenges remain in accurate diagnosis, timely treatment, and personalized care. This article reviews the integration of artificial intelligence and machine learning in enhancing anaphylaxis management. RECENT FINDINGS: Artificial intelligence and machine learning can analyze vast datasets to identify patterns and predict anaphylactic episodes, improve diagnostic accuracy through image and biomarker analysis, and personalize treatment plans. Artificial intelligence-powered wearable devices and decision support systems can facilitate real-time monitoring and early intervention. The ethical considerations of artificial intelligence use, including data privacy, transparency, and bias mitigation, are also discussed. SUMMARY: Future directions include the development of predictive models, enhanced diagnostic tools, and artificial intelligence-driven educational resources. By leveraging artificial intelligence and machine learning, healthcare providers can improve the management of anaphylaxis, ensuring better patient outcomes and advancing personalized medicine.

Randomized intervention and outpatient follow-up lowers 30-d readmissions for patients with hepatic encephalopathy, decompensated cirrhosis.

BACKGROUND: We previously reported national 30-d readmission rates of 27% in patients with decompensated cirrhosis (DC). AIM: To study prospective interventions to reduce early readmissions in DC at our tertiary center. METHODS: Adults with DC admitted July 2019 to December 2020 were enrolled and randomized into the intervention (INT) or standard of care (SOC) arms. Weekly phone calls for a month were completed. In the INT arm, case managers ensured outpatient follow-up, paracentesis, and medication compliance. Thirty-day readmission rates and reasons were compared. RESULTS: Calculated sample size was not achieved due to coronavirus disease 2019; 240 patients were randomized into INT and SOC arms. 30-d readmission rate was 33.75%, 35.83% in the INT vs 31.67% in the SOC arm (P = 0.59). The top reason for 30-d readmission was hepatic encephalopathy (HE, 32.10%). There was a lower rate of 30-d readmissions for HE in the INT (21%) vs SOC arm (45%, P = 0.03). There were fewer 30-d readmissions in patients who attended early outpatient follow-up (n = 17, 23.61% vs n = 55, 76.39%, P = 0.04). CONCLUSION: Our 30-d readmission rate was higher than the national rate but reduced by interventions in patients with DC with HE and early outpatient follow-up. Development of interventions to reduce early readmission in patients with DC is needed.