Adoption of antithrombotic stewardship and utilization of clinical decision support systems-A questionnaire-based survey in Dutch hospitals.

Antithrombotics require careful monitoring to prevent adverse events. Safe use can be promoted through so-called antithrombotic stewardship. Clinical decision support systems (CDSSs) can be used to monitor safe use of antithrombotics, supporting antithrombotic stewardship efforts. Yet, previous research shows that despite these interventions, antithrombotics continue to cause harm. Insufficient adoption of antithrombotic stewardship and suboptimal use of CDSSs may provide and explanation. However, it is currently unknown to what extent hospitals adopted antithrombotic stewardship and utilize CDSSs to support safe use of antithrombotics. A semi-structured questionnaire-based survey was disseminated to 12 hospital pharmacists from different hospital types and regions in the Netherlands. The primary outcome was the degree of antithrombotic stewardship adoption, expressed as the number of tasks adopted per hospital and the degree of adoption per task. Secondary outcomes included characteristics of CDSS alerts used to monitor safe use of antithrombotics. All 12 hospital pharmacists completed the survey and report to have adopted antithrombotic stewardship in their hospital to a certain degree. The median adoption of tasks was two of five tasks (range 1-3). The tasks with the highest uptake were: drafting and maintenance of protocols (100%) and professional's education (58%), while care transition optimization (25%), medication reviews (8%) and patient counseling (8%) had the lowest uptake. All hospitals used a CDSS to monitor safe use of antithrombotics, mainly via basic alerts and less frequently via advanced alerts. The most frequently employed alerts were: identification of patients using a direct oral anticoagulant (DOAC) or a vitamin K antagonist (VKA) with one or more other antithrombotics (n = 6) and patients using a VKA to evaluate correct use (n = 6), both reflecting basic CDSS. All participating hospitals adopted antithrombotic stewardship, but the adopted tasks vary. CDSS alerts used are mainly basic in their logic.

The use of artificial intelligence to optimize medication alerts generated by clinical decision support systems: a scoping review.

OBJECTIVE: Current Clinical Decision Support Systems (CDSSs) generate medication alerts that are of limited clinical value, causing alert fatigue. Artificial Intelligence (AI)-based methods may help in optimizing medication alerts. Therefore, we conducted a scoping review on the current state of the use of AI to optimize medication alerts in a hospital setting. Specifically, we aimed to identify the applied AI methods used together with their performance measures and main outcome measures. MATERIALS AND METHODS: We searched Medline, Embase, and Cochrane Library database on May 25, 2023 for studies of any quantitative design, in which the use of AI-based methods was investigated to optimize medication alerts generated by CDSSs in a hospital setting. The screening process was supported by ASReview software. RESULTS: Out of 5625 citations screened for eligibility, 10 studies were included. Three studies (30%) reported on both statistical performance and clinical outcomes. The most often reported performance measure was positive predictive value ranging from 9% to 100%. Regarding main outcome measures, alerts optimized using AI-based methods resulted in a decreased alert burden, increased identification of inappropriate or atypical prescriptions, and enabled prediction of user responses. In only 2 studies the AI-based alerts were implemented in hospital practice, and none of the studies conducted external validation. DISCUSSION AND CONCLUSION: AI-based methods can be used to optimize medication alerts in a hospital setting. However, reporting on models' development and validation should be improved, and external validation and implementation in hospital practice should be encouraged.

Treatment patterns in older patients with myelodysplastic syndromes: A population-based analysis reflecting the real world.

INTRODUCTION: Treatment for myelodysplastic syndromes (MDS) is complex, options are limited, and insight into consecutive treatments is lacking. We performed this study to assess the outcomes in a real-world cohort of patients with MDS. MATERIALS AND METHODS: An observational population-based study was performed using the HemoBase registry. Treatment patterns and overall survival (OS) were analyzed with Kaplan-Meier analyses. RESULTS: In 144 of 280 (51.4%) patients with MDS >50 years, first-line treatment was initiated. The median age was 75.1 years (range: 52.6-92.0); the majority were male (72.2%). Hypomethylating agents (HMA), intensive chemotherapy, lenalidomide, and erythropoiesis-stimulating agents (ESA) were given as first-line treatment to 31.1% (n = 45), 12.5% (n = 18), 2.8% (n = 4), and 53.5% (n = 77) of the population, respectively. The median treatment duration was 5.8 months (95% Confidence Interval [CI]: 1.1-10.4) for HMA, 1.7 months (95%CI: 0.9-2.6) for intensive chemotherapy, 10.8 months (95%CI: 4.7-17.0) for lenalidomide, and 14.8 months (95%CI: 11.4-18.1) for ESA. Consecutive treatments were given to 27.2% of patients. The main reasons for first-line treatment discontinuation were treatment failure (45.8%), toxicity (6.9%), or death (20.1%). Median OS after termination of the initial, second, and third treatment was 5.8 months (95%CI: 3.2-8.5), 9.3 months (95%CI: 0.0-19.6), and 1.0 months (95%CI: 0.0-5.1), respectively. DISCUSSION: This study shows the treatment outcomes in a real-world population of older patients with MDS. Treatment duration and median OS after treatment discontinuation were relatively limited. There is still an urgent need for new treatment options, strategies to further optimize duration of existing treatments, and communication of realistic treatment goals and expectations, especially for older, higher-risk patients with MDS with a poor prognosis.