Explore the vast range of titles available.

Cancer progression is driven in part by genomic alterations 1 . The genomic characterization of cancers has shown interpatient heterogeneity regarding driver alterations 2 , leading to the concept that generation of genomic profiling in patients with cancer could allow the selection of effective therapies 3 , 4 . Although DNA sequencing has been implemented in practice, it remains unclear how to use its results. A total of 1,462 patients with HER2-non-overexpressing metastatic breast cancer were enroled to receive genomic profiling in the SAFIR02-BREAST trial. Two hundred and thirty-eight of these patients were randomized in two trials (nos. NCT02299999 and NCT03386162) comparing the efficacy of maintenance treatment 5 with a targeted therapy matched to genomic alteration. Targeted therapies matched to genomics improves progression-free survival when genomic alterations are classified as level I/II according to the ESMO Scale for Clinical Actionability of Molecular Targets (ESCAT) 6 (adjusted hazards ratio (HR): 0.41, 90% confidence interval (CI): 0.27–0.61, P  < 0.001), but not when alterations are unselected using ESCAT (adjusted HR: 0.77, 95% CI: 0.56–1.06, P  = 0.109). No improvement in progression-free survival was observed in the targeted therapies arm (unadjusted HR: 1.15, 95% CI: 0.76–1.75) for patients presenting with ESCAT alteration beyond level I/II. Patients with germline BRCA1/2 mutations ( n  = 49) derived high benefit from olaparib (g BRCA1 : HR = 0.36, 90% CI: 0.14–0.89; g BRCA2 : HR = 0.37, 90% CI: 0.17–0.78). This trial provides evidence that the treatment decision led by genomics should be driven by a framework of target actionability in patients with metastatic breast cancer. Targeted therapies matched to genomics improved progression-free survival when genomic alterations were classified as level I/II (according to ESCAT), and genomics should thus be driven by target actionability in patients with metastatic breast cancer.

Axillary lymph node metastasis (ALNM) status, typically estimated using an invasive procedure with a high false-negative rate, strongly affects the prognosis of recurrence in breast cancer. However, preoperative noninvasive tools to accurately predict ALNM status and disease-free survival (DFS) are lacking. To develop and validate dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomic signatures for preoperative identification of ALNM and to assess individual DFS in patients with early-stage breast cancer. This retrospective prognostic study included patients with histologically confirmed early-stage breast cancer diagnosed at 4 hospitals in China from July 3, 2007, to September 21, 2019, randomly divided (7:3) into development and vaidation cohorts. All patients underwent preoperative MRI scans, were treated with surgery and sentinel lymph node biopsy or ALN dissection, and were pathologically examined to determine the ALNM status. Data analysis was conducted from February 15, 2019, to March 20, 2020. Clinical and DCE-MRI radiomic signatures. The primary end points were ALNM and DFS. This study included 1214 women (median [IQR] age, 47 [42-55] years), split into development (849 [69.9%]) and validation (365 [30.1%]) cohorts. The radiomic signature identified ALNM in the development and validation cohorts with areas under the curve (AUCs) of 0.88 and 0.85, respectively, and the clinical-radiomic nomogram accurately predicted ALNM in the development and validation cohorts (AUC, 0.92 and 0.90, respectively) based on a least absolute shrinkage and selection operator (LASSO)-logistic regression model. The radiomic signature predicted 3-year DFS in the development and validation cohorts (AUC, 0.81 and 0.73, respectively), and the clinical-radiomic nomogram could discriminate high-risk from low-risk patients in the development cohort (hazard ratio [HR], 0.04; 95% CI, 0.01-0.11; P < .001) and the validation cohort (HR, 0.04; 95% CI, 0.004-0.32; P < .001) based on a random forest-Cox regression model. The clinical-radiomic nomogram was associated with 3-year DFS in the development and validation cohorts (AUC, 0.89 and 0.90, respectively). The decision curve analysis demonstrated that the clinical-radiomic nomogram displayed better clinical predictive usefulness than the clinical or radiomic signature alone. This study described the application of MRI-based machine learning in patients with breast cancer, presenting novel individualized clinical decision nomograms that could be used to predict ALNM status and DFS. The clinical-radiomic nomograms were useful in clinical decision-making associated with personalized selection of surgical interventions and therapeutic regimens for patients with early-stage breast cancer.

PurposeThe aim of this study was to assess whether coaching doctors to enhance ethical decision-making in teams improves (1) goal-oriented care operationalized via written do-not-intubate and do-not attempt cardiopulmonary resuscitation (DNI-DNACPR) orders in adult patients potentially receiving excessive treatment (PET) during their first hospital stay and (2) the quality of the ethical climate.MethodsWe carried out a stepped-wedge cluster randomized controlled trial in the medical intensive care unit (ICU) and 9 referring internal medicine departments of Ghent University Hospital between February 2022 and February 2023. Doctors and nurses in charge of hospitalized patients filled out the ethical decision-making climate questionnaire (ethical decision-making climate questionnaire, EDMCQ) before and after the study, and anonymously identified PET via an electronic alert during the entire study period. All departments were randomly assigned to a 4-month coaching. At least one month of coaching was compared to less than one month coaching and usual care. The first primary endpoint was the incidence of written DNI-DNACPR decisions. The second primary endpoint was the EDMCQ before and after the study period. Because clinicians identified less PET than required to detect a difference in written DNI-DNACPR decisions, a post-hoc analysis on the overall population was performed. To reduce type I errors, we further restricted the analysis to one of our predefined secondary endpoints (mortality up to 1 year).ResultsOf the 442 and 423 clinicians working before and after the study period, respectively 270 (61%) and 261 (61.7%) filled out the EDMCQ. Fifty of the 93 (53.7%) doctors participated in the coaching for a mean (standard deviation [SD]) of 4.36 (2.55) sessions. Of the 7254 patients, 125 (1.7%) were identified as PET, with 16 missing outcome data. Twenty-six of the PET and 624 of the overall population already had a written DNI-DNACPR decision at study entry, resulting in 83 and 6614 patients who were included in the main and post hoc analysis, respectively. The estimated incidence of written DNI-DNACPR decisions in the intervention vs. control arm was, respectively, 29.7% vs. 19.6% (odds ratio 4.24, 95% confidence interval 4.21–4.27; P < 0.001) in PET and 3.4% vs. 1.9% (1.65, 1.12–2.43; P = 0.011) in the overall study population. The estimated mortality at one year was respectively 85% vs. 83.7% (hazard ratio 2.76, 1.26–6.04; P = 0.011) and 14.5% vs. 15.1% (0.89, 0.72–1.09; P = 0.251). The mean difference in EDMCQ before and after the study period was 0.02 points (− 0.18 to 0.23; P = 0.815).ConclusionThis study suggests that coaching doctors regarding ethical decision-making in teams safely improves goal-oriented care operationalized via written DNI-DNACPR decisions in hospitalized patients, however without concomitantly improving the quality of the ethical climate.

BackgroundArtificial intelligence (AI) tools could assist emergency doctors interpreting chest X-rays to inform urgent care. However, the impact of AI assistance on clinical decision-making, a precursor to enhanced care and patient outcomes, remains understudied. This study evaluates the effect of AI assistance on clinical decisions of emergency doctors interpreting chest X-rays.MethodJunior and senior residents, emergency registrars and consultants working in Australian emergency departments were eligible. Doctors completed 18 clinical vignettes involving chest X-ray interpretation, representative of typical patient presentations. Vignettes were randomly selected from a bank of 49 based on the emergency medicine curriculum and contained a chest X-ray, presenting complaint, relevant symptoms and observations. Of the 18 vignettes, each doctor was randomly assigned to have half assisted by a commercial AI tool capable of detecting 124 different chest X-ray findings. Four vignettes contained X-rays known to produce incorrect AI findings. Primary outcomes were correct diagnosis and patient management. X-ray interpretation time, confidence of diagnosis, perceptions about the AI tool and the differential impact of AI assistance by seniority were also examined.Results200 doctors participated. AI assistance increased correct diagnosis by 5.9% (95% CI 2.7 to 9.2%) compared with unassisted vignettes, with the largest increase among senior residents (11.8%; 95% CI 5.2% to 18.3%). Patient management increased by 3.2% (95% CI 0.1% to 6.4%). Confidence in diagnosis increased by 5% (95% CI 3.4% to 6.6%; p<0.001) and interpretation time increased by 4.9 s (p=0.08). Incorrect AI findings decreased correct diagnosis by 1% for false-positive (p=0.9) and 9% for false-negative findings (p=0.1). Participants found the AI tool helpful for interpreting chest X-rays, highlighting missed findings, but were neutral on its accuracy.ConclusionImprovements in diagnosis and patient management without meaningful increases in interpretation time suggest AI assistance could benefit clinical decisions involving chest X-ray interpretation. Further studies are required to ascertain if such improvements translate to improved patient care.

SummaryGiven the widespread practice of recommending drug holidays, we reviewed the impact of medication discontinuation of two common anti-osteoporosis therapies (bisphosphonates and denosumab). Trial evidence suggests the risk of new clinical fractures, and vertebral fracture increases when osteoporosis treatment with bisphosphonates or denosumab is stopped.IntroductionThe aim of this paper was to review the available literature to assess what evidence exists to inform clinical decision-making with regard to drug holidays following treatment with bisphosphonates (BiP) or denosumab.MethodsSystematic review.ResultsDiffering pharmacokinetics lead to varying outcomes on stopping therapy. Prospective and retrospective analyses report that the risk of new clinical fractures was 20–40% higher in subjects who stopped BiP treatment, and vertebral fracture risk was approximately doubled. Rapid bone loss has been well described following denosumab discontinuation with an incidence of multiple vertebral fractures around 5%. Studies have not identified risk factors for fracture after stopping treatment other than those that provide an indication for treatment (e.g. prior fracture and low BMD). Studies that considered long-term continuation did not identify increased fracture risk, and reported only very low rates of adverse skeletal events such as atypical femoral fracture.ConclusionsThe view that patients on long-term treatment with bisphosphonates or denosumab should always be offered a drug holiday is not supported by the existing evidence. Different pharmacokinetic properties for different therapies require different strategies to manage drug intermission. In contrast, long-term treatment with anti-resorptives is not associated with increased risk of fragility fractures and skeletal adverse events remain rare.

The predictions from an accurate prognostic model can be of great interest to patients and clinicians. When predictions are reported to individuals, they may decide to take action to improve their health or they may simply be comforted by the knowledge. However, if there is a clearly defined space of actions in the clinical context, a formal decision rule based on the prediction has the potential to have a much broader impact. The use of a prediction-based decision rule should be formalized and preferably compared with the standard of care in a randomized trial to assess its clinical utility; however, evidence is needed to motivate such a trial. We outline how observational data can be used to propose a decision rule based on a prognostic prediction model. We then propose a framework for emulating a prediction driven trial to evaluate the clinical utility of a prediction-based decision rule in observational data. A split-sample structure is often feasible and useful to develop the prognostic model, define the decision rule, and evaluate its clinical utility. See video abstract at, http://links.lww.com/EDE/B656.

Clinical work-up for suspected cardiac chest pain is resource intensive. Despite expectations, high-sensitivity cardiac troponin assays have not made decision making easier. The impact of recently validated rapid triage protocols including the 0-hour/1-hour hs-cTn protocols on care and outcomes may be limited by the heterogeneity in interpretation of troponin profiles by clinicians. We have developed machine learning (ML) models which digitally phenotype myocardial injury and infarction with a high predictive performance and provide accurate risk assessment among patients presenting to EDs with suspected cardiac symptoms. The use of these models may support clinical decision-making and allow the synthesis of an evidence base particularly in non-T1MI patients however prospective validation is required. We propose that integrating validated real-time artificial intelligence (AI) methods into clinical care may better support clinical decision-making and establish the foundation for a self-learning health system. This prospective, multicenter, open-label, cluster-randomized clinical trial within blinded endpoint adjudication across 12 hospitals (n = 20,000) will randomize sites to the clinical decision-support tool or continue current standard of care. The clinical decision support tool will utilize ML models to provide objective patient-specific diagnostic probabilities (ie, likelihood for Type 1 myocardial infarction [MI] versus Type 2 MI/Acute Myocardial Injury versus Chronic Myocardial Injury etc.) and prognostic assessments. The primary outcome is the composite of cardiovascular mortality, new or recurrent MI and unplanned hospital re-admission at 12 months post index presentation. Supporting clinicians with a decision support tool that utilizes AI has the potential to provide better diagnostic and prognostic assessment thereby improving clinical efficiency and establish a self-learning health system continually improving risk assessment, quality and safety. ANZCTR, Registration Number: ACTRN12620001319965, https://www.anzctr.org.au/.

Artificial intelligence (AI)-based decision support systems (DSS) are utilized in medicine but underlying decision-making processes are usually unknown. Explainable AI (xAI) techniques provide insight into DSS, but little is known on how to design xAI for clinicians. Here we investigate the impact of various xAI techniques on a clinician's interaction with an AI-based DSS in decision-making tasks as compared to a general population. We conducted a randomized, blinded study in which members of the Child Neurology Society and American Academy of Neurology were compared to a general population. Participants received recommendations from a DSS via a random assignment of an xAI intervention (decision tree, crowd sourced agreement, case-based reasoning, probability scores, counterfactual reasoning, feature importance, templated language, and no explanations). Primary outcomes included test performance and perceived explainability, trust, and social competence of the DSS. Secondary outcomes included compliance, understandability, and agreement per question. We had 81 neurology participants with 284 in the general population. Decision trees were perceived as the more explainable by the medical versus general population (P < 0.01) and as more explainable than probability scores within the medical population (P < 0.001). Increasing neurology experience and perceived explainability degraded performance (P = 0.0214). Performance was not predicted by xAI method but by perceived explainability. xAI methods have different impacts on a medical versus general population; thus, xAI is not uniformly beneficial, and there is no one-size-fits-all approach. Further user-centered xAI research targeting clinicians and to develop personalized DSS for clinicians is needed.

To compare the effects of traditional and platform-based case-based learning (CBL) on undergraduate nursing students’ academic performance, self-efficacy, clinical decision-making and critical thinking abilities. Traditional CBL can improve students’ academic performance but faces challenges in the era of “Internet + education.” It is unclear whether platform-based CBL is as effective as traditional CBL. Cluster randomized controlled trial. A total of 88 undergraduate nursing students from two classes were recruited using cluster sampling and separated into two groups by class. The control group (n = 45) received traditional CBL, and the experimental group (n = 43) received platform-based CBL. Academic performance, self-efficacy, clinical decision-making, critical thinking disposition and experimental group’s learning records from the online platform were evaluated. No difference was found between the two groups in overall academic performance, but formative evaluation and final examination scores in the course differed. Compared with the control group, the experimental group presented significant differences in self-efficacy and clinical decision-making. There was no difference between the total clinical thinking disposition scores; however, truth-seeking, systematicity and self-confidence exhibited significant differences. Concerning student progression, all experimental students advanced from “Grade I” to “Grade V” or “Grade IV”. The usability questionnaire’s average score regarding the platform was 77.03 (SD 7.43) and the top dimension was teaching utility. Compared with traditional CBL, platform-based CBL may better enhance self-efficacy and clinical decision-making abilities in nursing undergraduate students.

Background and objective Trauma is one of the leading causes of mortality worldwide, especially in developing countries. Accurate clinical decision-making ability among nurses plays a crucial role in reducing trauma-related mortality and complications. Strengthening such skills during nursing education can better prepare students to effectively address clinical challenges they may face in real-world trauma care. This study aimed to determine the effect of an Advanced Trauma Life Support (ATLS) simulation program on the clinical decision-making abilities of nursing students. Methods This quasi-experimental study with a pre-test/post-test control group design was conducted in 2025 on 66 final-year nursing students at Shahid Beheshti University of Medical Sciences. Participants were assigned to intervention ( n  = 31) and control ( n  = 35) groups. The intervention group received advanced trauma life support simulation training. Data were collected using a validated clinical decision-making questionnaire and analyzed with paired t-tests, repeated measures ANOVA, and interaction effects tests. Results The mean clinical decision-making score in the intervention group increased from 40.81 ± 3.22 before the intervention to 52.24 ± 2.04 after the intervention. In the control group, the mean scores were 39.06 ± 2.27 before and 48.09 ± 1.97 after the study period. Repeated measures ANOVA indicated that time (F = 601.08, p  < 0.001), group (F = 47.26, p  < 0.001), and the interaction of time and group (F = 8.23, p  = 0.006) had significant effects on clinical decision-making ability. The improvement in the intervention group was significantly greater than in the control group. Conclusions These findings suggest that ATLS-based simulation programs can significantly improve nursing students’ readiness for real-life trauma situations and should be integrated into nursing curricula.