Use of Artificial Intelligence in Triage in Hospital Emergency Departments: A Scoping Review.

The integration of artificial intelligence (AI) and machine learning (ML) in healthcare has become a major point of interest and raises the question of its impact on the emergency department (ED) triaging process. AI's capacity to emulate human cognitive processes coupled with advancements in computing has shown positive outcomes in various aspects of healthcare but little is known about the use of AI in triaging patients in ED. AI algorithms may allow for earlier diagnosis and intervention; however, overconfident answers may present dangers to patients. The purpose of this review was to explore comprehensively recently published literature regarding the effect of AI and ML in ED triage and identify research gaps. A systemized search was conducted in September 2023 using the electronic databases EMBASE, Ovid MEDLINE, and Web of Science. To meet inclusion criteria, articles had to be peer-reviewed, written in English, and based on primary data research studies published in US journals 2013-2023. Other criteria included 1) studies with patients needing to be admitted to hospital EDs, 2) AI must have been used when triaging a patient, and 3) patient outcomes must be represented. The search was conducted using controlled descriptors from the Medical Subject Headings (MeSH) that included the terms "artificial intelligence" OR "machine learning" AND "emergency ward" OR "emergency care" OR "emergency department" OR "emergency room" AND "patient triage" OR "triage" OR "triaging." The search initially identified 1,142 citations. After a rigorous, systemized screening process and critical appraisal of the evidence, 29 studies were selected for the final review. The findings indicated that 1) ML models consistently demonstrated superior discrimination abilities compared to conventional triage systems, 2) the integration of AI into the triage process yielded significant enhancements in predictive accuracy, disease identification, and risk assessment, 3) ML accurately determined the necessity of hospitalization for patients requiring urgent attention, and 4) ML improved resource allocation and quality of patient care, including predicting length of stay. The suggested superiority of ML models in prioritizing patients in the ED holds the potential to redefine triage precision.

Managing potential adverse events during treatment with enfortumab vedotin + pembrolizumab in patients with advanced urothelial cancer.

Cisplatin-based chemotherapy has been the standard of care for patients with locally advanced or metastatic urothelial cancer (la/mUC). Enfortumab vedotin, an antibody-drug conjugate directed to Nectin-4, and pembrolizumab, an immune checkpoint inhibitor, are two therapies that have individually provided a survival benefit in patients with la/mUC. The combination regimen of enfortumab vedotin plus pembrolizumab was evaluated in EV-302 (KEYNOTE-A39; NCT0422385), a phase 3 study that showed statistically significant and clinically meaningful improvement in overall survival, progression-free survival, and a key secondary endpoint of overall response rate versus chemotherapy. Based on these results and those from the EV-103 (KEYNOTE-869; NCT03288545) Dose Escalation cohort, Cohort A, and Cohort K, enfortumab vedotin plus pembrolizumab was granted approval from the US Food and Drug Administration for the treatment of adults with la/mUC. While guidelines and recommendations for the management of adverse events (AEs) have been developed for immune checkpoint inhibitor monotherapy and enfortumab vedotin monotherapy, additional guidance is needed for managing AEs that occur with enfortumab vedotin plus pembrolizumab. As monotherapies, enfortumab vedotin and pembrolizumab are both associated with some of the AEs observed with the combination, such as skin reactions, pneumonitis, and diarrhea, which may confound the attribution of the AE to a specific agent and thereby complicate clinical management. In this manuscript, we aim to provide recommendations for best practice for patient care and the management of AEs of clinical interest for patients with la/mUC receiving enfortumab vedotin plus pembrolizumab, including skin reactions, peripheral neuropathy, hyperglycemia, and pneumonitis. These recommendations were developed based on published guidelines, expert opinions, and the clinical experience of the authors, which include oncologist, advanced practice provider, nursing, and pharmacy perspectives. In addition, guidance on patient education and communication is provided. With vigilant monitoring, early detection, and prompt intervention of treatment-emergent AEs based on recommended approaches described herein, it is the authors' experience that most AEs can be managed with supportive therapy and dose modification/interruptions, allowing patients to continue treatment.

Unintended Consequences: Risk of Opportunistic Infections Associated With Long-term Glucocorticoid Therapies in Adults.

Glucocorticoids are widespread anti-inflammatory medications used in medical practice. The immunosuppressive effects of systemic glucocorticoids and increased susceptibility to infections are widely appreciated. However, the dose-dependent model frequently used may not accurately predict the risk of infection in all patients treated with long-term glucocorticoids. In this review, we examine the risks of opportunistic infections (OIs) in patients requiring glucocorticoid therapy by evaluating the influence of the glucocorticoid dose, duration, and potency, combined with biological and host clinical factors and concomitant immunosuppressive therapy. We propose strategies to prevent OIs, which involve screening, antimicrobial prophylaxis, and immunizations. While this review focuses on patients with autoimmune, inflammatory, or neoplastic diseases, the potential risks and preventative strategies are likely applicable to other populations. Clinicians should actively assess the benefit-harm ratios of systemic glucocorticoids and implement preventive efforts to decrease their associated infections complications.

Real-World Efficacy and Safety of PARP Inhibitors in Recurrent Ovarian Cancer Patients With Somatic BRCA and Other Homologous Recombination Gene Mutations.

BACKGROUND: Real-world data regarding the use of poly (ADP-ribose) polymerase (PARP) inhibitors in recurrent ovarian cancer patients with non-BRCA homologous recombination (HR) mutations or somatic BRCA mutations are lacking. OBJECTIVE: The purpose of our study is to evaluate the response rate, duration of treatment, time to progression (TTP), and toxicities of olaparib, niraparib, and rucaparib in somatic BRCAm and non-BRCA HR-mutated patients. METHODS: This was a retrospective study using the electronic medical record to identify patients across our health system who were initiated on a PARP inhibitor for ovarian cancer between December 2014 and December 2019. Patients were screened for the presence of a somatic BRCA1/2 mutation or a mutation in non-BRCA HR genes. Data were collected via chart review. RESULTS: For the efficacy analysis, 8 patients had somatic BRCA mutations and 12 patients had HR mutations. The overall response rate (ORR) was 50% for BRCA-mutated (BRCAm) patients and 9.1% for non-BRCA HR-mutated (non-BRCA HRm) patients. 72.7% of patients with non-BRCA HR mutations had stable disease. The duration of therapy ranged from 2 to 66 months. The median TTP was 9.5 months. Overall, 66.7% of patients in the entire cohort started on a reduced dose of PARP inhibitor. Dose reductions due to AEs were observed in 52.4% of patients, while AEs requiring treatment interruption occurred in 61.9%. CONCLUSION AND RELEVANCE: We found that PARP inhibitors provided stable disease in a high proportion of recurrent ovarian cancer patients who had pathogenic HR mutations, with toxicities comparable to major trials. Patients with non-BRCA HR and somatic BRCA mutations could benefit from PARP inhibitors.

A review of FLT3 inhibitors in acute myeloid leukemia.

FLT3 mutations are the most common genetic aberrations found in acute myeloid leukemia (AML) and associated with poor prognosis. Since the discovery of FLT3 mutations and their prognostic implications, multiple FLT3-targeted molecules have been evaluated. Midostaurin is approved in the U.S. and Europe for newly diagnosed FLT3 mutated AML in combination with standard induction and consolidation chemotherapy based on data from the RATIFY study. Gilteritinib is approved for relapsed or refractory FLT3 mutated AML as monotherapy based on the ADMIRAL study. Although significant progress has been made in the treatment of AML with FLT3-targeting, many challenges remain. Several drug resistance mechanisms have been identified, including clonal selection, stromal protection, FLT3-associated mutations, and off-target mutations. The benefit of FLT3 inhibitor maintenance therapy, either post-chemotherapy or post-transplant, remains controversial, although several studies are ongoing.

Direct differentiation of adult ocular progenitors into striatal dopaminergic neurons.

Parkinson's disease, characterized by motor dysfunction due to the loss of nigrostriatal dopaminergic neurons, is one of the most prevalent age-related neurodegenerative disorders. Given there is no current cure, the stem cell approach has emerged as a viable therapeutic option to replace the dopaminergic neurons that are progressively lost to the disease. The success of the approach is likely to depend upon accessible, renewable, immune compatible, and non-tumorigenic sources of neural progenitors from which stable dopaminergic neurons can be generated efficaciously. Here, we demonstrate that neural progenitors derived from limbus, a regenerative and accessible ocular tissue, represent a safe source of dopaminergic neurons. When the limbus-derived neural progenitors were subjected to a well-established protocol of directed differentiation under the influence of Shh and FGF8, they acquired the biochemical and functional phenotype of dopaminergic neurons that included the ability to synthesize dopamine. Their intrastriatal transplantation in the rat model of hemi-Parkinsonism was associated with a reduction in the amphetamine-induced rotation. No tumor formation was observed 6 weeks post-transplantation. Together, these observations posit limbus-derived neural progenitors as an accessible and safe source of dopaminergic neurons for a potential autologous ex-vivo stem cell approach to Parkinson's disease.