RESUMO
The integration of Clinical Decision Support Systems (CDSS) based on artificial intelligence (AI) in healthcare is groundbreaking evolution with enormous potential, but its development and ethical implementation, presents unique challenges, particularly in critical care, where physicians often deal with life-threating conditions requiring rapid actions and patients unable to participate in the decisional process. Moreover, development of AI-based CDSS is complex and should address different sources of bias, including data acquisition, health disparities, domain shifts during clinical use, and cognitive biases in decision-making. In this scenario algor-ethics is mandatory and emphasizes the integration of 'Human-in-the-Loop' and 'Algorithmic Stewardship' principles, and the benefits of advanced data engineering. The establishment of Clinical AI Departments (CAID) is necessary to lead AI innovation in healthcare, ensuring ethical integrity and human-centered development in this rapidly evolving field.
Assuntos
Algoritmos , Inteligência Artificial , Cuidados Críticos , Sistemas de Apoio a Decisões Clínicas , Humanos , Inteligência Artificial/ética , Cuidados Críticos/ética , Sistemas de Apoio a Decisões Clínicas/ética , Tomada de Decisão Clínica/éticaRESUMO
This study evaluated the economic burden of metastatic non-small cell lung cancer patients before and after the availability of an immuno-oncology (IO) regimen as a first-line (1L) treatment. Patients from 2014 to 2020 were categorized according to mutational status into mutation-positive and negative/unknown groups, which were further divided into pre-1L IO and post-1L IO sub-groups depending on the availability of pembrolizumab monotherapy in 1L. Healthcare costs and HCRU for a 1L treatment and overall follow-up were reported as the mean total and per-month cost per patient by groups. Of 644 patients, 125were mutation-positive and 519 negative/unknown (229 and 290 in pre- and post-1L IO, respectively). The mean total per-patient cost in 1L was lower in pre- (EUR 7804) and post-1L IO (EUR 19,301) than the mutation-positive group (EUR 45,247), persisting throughout overall disease follow-up. However, this difference was less when analyzing monthly costs. Therapy costs were the primary driver in 1L, while hospitalization costs rose during follow-up. In both mutation-positive and post-IO 1L groups, the 1L costs represented a significant portion (70.1% and 66.3%, respectively) of the total costs in the overall follow-up. Pembrolizumab introduction increased expenses but improved survival. Higher hospitalisation and emergency room occupation rates during follow-up reflected worsening clinical conditions of the negative/unknown group than the mutation-positive population.
RESUMO
AIMS: To assess the effectiveness of the intermittent-scanned continuous glucose monitoring (isCGM) system in preventing severe hypoglycemic episodes and in improving glucose parameters and quality of life. METHODS: Four hundred T1D individuals were enrolled in a prospective real-word study with an intermittently scanned continuous glucose monitoring device during the 12-months follow-up. The primary endpoint was the incidence of severe hypoglycemic events. RESULTS: 82% of subjects were naïve to the use of the device (group A) and 18% were already wearing the system (group B). The cumulative incidence of severe hypoglycemia (SH) at 12 months was 12.06 per 100 person-year (95% CI: 8.35-16.85) in group A and 10.14 (95% CI: 4.08-20.90) in group B without inter-group differences. In group A there was a significant decrease in SH at 12 months compared to 3 months period (p = 0.005). Time in glucose range significantly increased in both groups accompanied with a significant decrease in glucose variability. HbA1c showed a progressive significant time-dependent decrease in group A. The use of the device significantly improved the perceived quality of life. CONCLUSION: This study confirmed the effectiveness of the isCGM in reducing hypoglycemic risk without glucose deterioration, with potential benefits on adverse outcomes in T1D individuals. TRIAL REGISTRATION: ClinicalTrials.gov registration no. NCT04060732.