Model-Informed Precision Dosing: Background, Requirements, Validation, Implementation, and Forward Trajectory of Individualizing Drug Therapy.

Model-informed precision dosing (MIPD) has become synonymous with modern approaches for individualizing drug therapy, in which the characteristics of each patient are considered as opposed to applying a one-size-fits-all alternative. This review provides a brief account of the current knowledge, practices, and opinions on MIPD while defining an achievable vision for MIPD in clinical care based on available evidence. We begin with a historical perspective on variability in dose requirements and then discuss technical aspects of MIPD, including the need for clinical decision support tools, practical validation, and implementation of MIPD in health care. We also discuss novel ways to characterize patient variability beyond the common perceptions of genetic control. Finally, we address current debates on MIPD from the perspectives of the new drug development, health economics, and drug regulations.

Standardizing digital biobanks: integrating imaging, genomic, and clinical data for precision medicine.

Advancements in data acquisition and computational methods are generating a large amount of heterogeneous biomedical data from diagnostic domains such as clinical imaging, pathology, and next-generation sequencing (NGS), which help characterize individual differences in patients. However, this information needs to be available and suitable to promote and support scientific research and technological development, supporting the effective adoption of the precision medicine approach in clinical practice. Digital biobanks can catalyze this process, facilitating the sharing of curated and standardized imaging data, clinical, pathological and molecular data, crucial to enable the development of a comprehensive and personalized data-driven diagnostic approach in disease management and fostering the development of computational predictive models. This work aims to frame this perspective, first by evaluating the state of standardization of individual diagnostic domains and then by identifying challenges and proposing a possible solution towards an integrative approach that can guarantee the suitability of information that can be shared through a digital biobank. Our analysis of the state of the art shows the presence and use of reference standards in biobanks and, generally, digital repositories for each specific domain. Despite this, standardization to guarantee the integration and reproducibility of the numerical descriptors generated by each domain, e.g. radiomic, pathomic and -omic features, is still an open challenge. Based on specific use cases and scenarios, an integration model, based on the JSON format, is proposed that can help address this problem. Ultimately, this work shows how, with specific standardization and promotion efforts, the digital biobank model can become an enabling technology for the comprehensive study of diseases and the effective development of data-driven technologies at the service of precision medicine.

Trust and stakeholder perspectives on the implementation of AI tools in clinical radiology.

OBJECTIVES: To define requirements that condition trust in artificial intelligence (AI) as clinical decision support in radiology from the perspective of various stakeholders and to explore ways to fulfil these requirements. METHODS: Semi-structured interviews were conducted with twenty-five respondents-nineteen directly involved in the development, implementation, or use of AI applications in radiology and six working with AI in other areas of healthcare. We designed the questions to explore three themes: development and use of AI, professional decision-making, and management and organizational procedures connected to AI. The transcribed interviews were analysed in an iterative coding process from open coding to theoretically informed thematic coding. RESULTS: We identified four aspects of trust that relate to reliability, transparency, quality verification, and inter-organizational compatibility. These aspects fall under the categories of substantial and procedural requirements. CONCLUSIONS: Development of appropriate levels of trust in AI in healthcare is complex and encompasses multiple dimensions of requirements. Various stakeholders will have to be involved in developing AI solutions for healthcare and radiology to fulfil these requirements. CLINICAL RELEVANCE STATEMENT: For AI to achieve advances in radiology, it must be given the opportunity to support, rather than replace, human expertise. Support requires trust. Identification of aspects and conditions for trust allows developing AI implementation strategies that facilitate advancing the field. KEY POINTS: • Dimensions of procedural and substantial demands that need to be fulfilled to foster appropriate levels of trust in AI in healthcare are conditioned on aspects related to reliability, transparency, quality verification, and inter-organizational compatibility. •Creating the conditions for trust to emerge requires the involvement of various stakeholders, who will have to compensate the problem's inherent complexity by finding and promoting well-defined solutions.

Selecting postoperative adjuvant systemic therapy for early-stage breast cancer: An updated assessment and systematic review of leading commercially available gene expression assays.

Gene expression assays (GEAs) can guide treatment for early-stage breast cancer. Several large prospective randomized clinical trials, and numerous additional studies, now provide new information for selecting an appropriate GEA. This systematic review builds upon prior reviews, with a focus on five widely commercialized GEAs (Breast Cancer Index®, EndoPredict®, MammaPrint®, Oncotype DX®, and Prosigna®). The comprehensive dataset available provides a contemporary opportunity to assess each GEA's utility as a prognosticator and/or predictor of adjuvant therapy benefit.

Clinician views on how clinical decision support systems can help diagnose asthma in primary care: a qualitative study.

OBJECTIVE: Asthma can be difficult to diagnose in primary care. Clinical decision support systems (CDSS) can assist clinicians when making diagnostic decisions, but the perspectives of intended users need to be incorporated into the software if the CDSS is to be clinically useful. Therefore, we aimed to understand health professional views on the value of an asthma diagnosis CDSS and the barriers and facilitators for use in UK primary care. METHODS: We recruited doctors and nurses working in UK primary care who had experience of assessing respiratory symptoms and diagnosing asthma. Qualitative interviews were used to explore clinicians' experiences of making a diagnosis of asthma and understand views on a CDSS to support asthma diagnosis. Interviews were audio-recorded, transcribed verbatim and analyzed thematically. RESULTS: 16 clinicians (nine doctors, seven nurses) including 13 participants with over 10 years experience, contributed interviews. Participants saw the potential for a CDSS to support asthma diagnosis in primary care by structuring consultations, identifying relevant information from health records, and having visuals to communicate findings to patients. Being evidence based, regularly updated, integrated with software, quick and easy to use were considered important for a CDSS to be successfully implemented. Experienced clinicians were unsure a CDSS would help their routine practice, particularly in straightforward diagnostic scenarios, but thought a CDSS would be useful for trainees or less experienced colleagues. CONCLUSIONS: To be adopted into clinical practice, clinicians were clear that a CDSS must be validated, integrated with existing software, and quick and easy to use.

What Are Humans Doing in the Loop? Co-Reasoning and Practical Judgment When Using Machine Learning-Driven Decision Aids.

Within the ethical debate on Machine Learning-driven decision support systems (ML_CDSS), notions such as "human in the loop" or "meaningful human control" are often cited as being necessary for ethical legitimacy. In addition, ethical principles usually serve as the major point of reference in ethical guidance documents, stating that conflicts between principles need to be weighed and balanced against each other. Starting from a neo-Kantian viewpoint inspired by Onora O'Neill, this article makes a concrete suggestion of how to interpret the role of the "human in the loop" and to overcome the perspective of rivaling ethical principles in the evaluation of AI in health care. We argue that patients should be perceived as "fellow workers" and epistemic partners in the interpretation of ML_CDSS outputs. We further highlight that a meaningful process of integrating (rather than weighing and balancing) ethical principles is most appropriate in the evaluation of medical AI.

Evaluating clinical decision support software (CDSS): challenges for robust evidence generation.

OBJECTIVES: Computerized clinical decision support software (CDSS) are digital health technologies that have been traditionally categorized as medical devices. However, the evaluation frameworks for traditional medical devices are not well adapted to assess the value and safety of CDSS. In this study, we identified a range of challenges associated with CDSS evaluation as a medical device and investigated whether and how CDSS are evaluated in Australia. METHODS: Using a qualitative approach, we interviewed 11 professionals involved in the implementation and evaluation of digital health technologies at national and regional levels. Data were thematically analyzed using both data-driven (inductive) and theory-based (deductive) approaches. RESULTS: Our results suggest that current CDSS evaluations have an overly narrow perspective on the risks and benefits of CDSS due to an inability to capture the impact of the technology on the sociotechnical environment. By adopting a static view of the CDSS, these evaluation frameworks are unable to discern how rapidly evolving technologies and a dynamic clinical environment can impact CDSS performance. After software upgrades, CDSS can transition from providing information to specifying diagnoses and treatments. Therefore, it is not clear how CDSS can be monitored continuously when changes in the software can directly affect patient safety. CONCLUSION: Our findings emphasize the importance of taking a living health technology assessment approach to the evaluation of digital health technologies that evolve rapidly. There is a role for observational (real-world) evidence to understand the impact of changes to the technology and the sociotechnical environment on CDSS performance.

Towards proactive palliative care in oncology: developing an explainable EHR-based machine learning model for mortality risk prediction.

BACKGROUND: Ex-ante identification of the last year in life facilitates a proactive palliative approach. Machine learning models trained on electronic health records (EHR) demonstrate promising performance in cancer prognostication. However, gaps in literature include incomplete reporting of model performance, inadequate alignment of model formulation with implementation use-case, and insufficient explainability hindering trust and adoption in clinical settings. Hence, we aim to develop an explainable machine learning EHR-based model that prompts palliative care processes by predicting for 365-day mortality risk among patients with advanced cancer within an outpatient setting. METHODS: Our cohort consisted of 5,926 adults diagnosed with Stage 3 or 4 solid organ cancer between July 1, 2017, and June 30, 2020 and receiving ambulatory cancer care within a tertiary center. The classification problem was modelled using Extreme Gradient Boosting (XGBoost) and aligned to our envisioned use-case: "Given a prediction point that corresponds to an outpatient cancer encounter, predict for mortality within 365-days from prediction point, using EHR data up to 365-days prior." The model was trained with 75% of the dataset (n = 39,416 outpatient encounters) and validated on a 25% hold-out dataset (n = 13,122 outpatient encounters). To explain model outputs, we used Shapley Additive Explanations (SHAP) values. Clinical characteristics, laboratory tests and treatment data were used to train the model. Performance was evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC), while model calibration was assessed using the Brier score. RESULTS: In total, 17,149 of the 52,538 prediction points (32.6%) had a mortality event within the 365-day prediction window. The model demonstrated an AUROC of 0.861 (95% CI 0.856-0.867) and AUPRC of 0.771. The Brier score was 0.147, indicating slight overestimations of mortality risk. Explanatory diagrams utilizing SHAP values allowed visualization of feature impacts on predictions at both the global and individual levels. CONCLUSION: Our machine learning model demonstrated good discrimination and precision-recall in predicting 365-day mortality risk among individuals with advanced cancer. It has the potential to provide personalized mortality predictions and facilitate earlier integration of palliative care.

Appropriate medication use in Dutch terminal care: study protocol of a multicentre stepped-wedge cluster randomized controlled trial (the AMUSE study).

BACKGROUND: Polypharmacy is common among patients with a limited life expectancy, even shortly before death. This is partly inevitable, because these patients often have multiple symptoms which need to be alleviated. However, the use of potentially inappropriate medications (PIMs) in these patients is also common. Although patients and relatives are often willing to deprescribe medication, physicians are sometimes reluctant due to the lack of evidence on appropriate medication management for patients in the last phase of life. The aim of the AMUSE study is to investigate whether the use of CDSS-OPTIMED, a software program that gives weekly personalized medication recommendations to attending physicians of patients with a limited life expectancy, improves patients' quality of life. METHODS: A multicentre stepped-wedge cluster randomized controlled trial will be conducted among patients with a life expectancy of three months or less. The stepped-wedge cluster design, where the clusters are the different study sites, involves sequential crossover of clusters from control to intervention until all clusters are exposed. In total, seven sites (4 hospitals, 2 general practices and 1 hospice from the Netherlands) will participate in this study. During the control period, patients will receive 'care as usual'. During the intervention period, CDSS-OPTIMED will be activated. CDSS-OPTIMED is a validated software program that analyses the use of medication based on a specific set of clinical rules for patients with a limited life expectancy. The software program will provide the attending physicians with weekly personalized medication recommendations. The primary outcome of this study is patients' quality of life two weeks after baseline assessment as measured by the EORTC QLQ-C15-PAL questionnaire, quality of life question. DISCUSSION: This will be the first study investigating the effect of weekly personalized medication recommendations to attending physicians on the quality of life of patients with a limited life expectancy. We hypothesize that the CDSS-OPTIMED intervention could lead to improved quality of life in patients with a life expectancy of three months or less. TRIAL REGISTRATION: This trial is registered at ClinicalTrials.gov (NCT05351281, Registration Date: April 11, 2022).

Clinical Decision Support System Used in Spinal Disorders: Scoping Review.

BACKGROUND: Spinal disorders are highly prevalent worldwide with high socioeconomic costs. This cost is associated with the demand for treatment and productivity loss, prompting the exploration of technologies to improve patient outcomes. Clinical decision support systems (CDSSs) are computerized systems that are increasingly used to facilitate safe and efficient health care. Their applications range in depth and can be found across health care specialties. OBJECTIVE: This scoping review aims to explore the use of CDSSs in patients with spinal disorders. METHODS: We used the Joanna Briggs Institute methodological guidance for this scoping review and reported according to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) statement. Databases, including PubMed, Embase, Cochrane, CINAHL, Web of Science, Scopus, ProQuest, and PsycINFO, were searched from inception until October 11, 2022. The included studies examined the use of digitalized CDSSs in patients with spinal disorders. RESULTS: A total of 4 major CDSS functions were identified from 31 studies: preventing unnecessary imaging (n=8, 26%), aiding diagnosis (n=6, 19%), aiding prognosis (n=11, 35%), and recommending treatment options (n=6, 20%). Most studies used the knowledge-based system. Logistic regression was the most commonly used method, followed by decision tree algorithms. The use of CDSSs to aid in the management of spinal disorders was generally accepted over the threat to physicians' clinical decision-making autonomy. CONCLUSIONS: Although the effectiveness was frequently evaluated by examining the agreement between the decisions made by the CDSSs and the health care providers, comparing the CDSS recommendations with actual clinical outcomes would be preferable. In addition, future studies on CDSS development should focus on system integration, considering end user's needs and preferences, and external validation and impact studies to assess effectiveness and generalizability. TRIAL REGISTRATION: OSF Registries osf.io/dyz3f; https://osf.io/dyz3f.

Pharmacogenetics Clinical Decision Support Systems for Primary Care in England: Co-Design Study.

BACKGROUND: Pharmacogenetics can impact patient care and outcomes through personalizing the selection of medicines, resulting in improved efficacy and a reduction in harmful side effects. Despite the existence of compelling clinical evidence and international guidelines highlighting the benefits of pharmacogenetics in clinical practice, implementation within the National Health Service in the United Kingdom is limited. An important barrier to overcome is the development of IT solutions that support the integration of pharmacogenetic data into health care systems. This necessitates a better understanding of the role of electronic health records (EHRs) and the design of clinical decision support systems that are acceptable to clinicians, particularly those in primary care. OBJECTIVE: Explore the needs and requirements of a pharmacogenetic service from the perspective of primary care clinicians with a view to co-design a prototype solution. METHODS: We used ethnographic and think-aloud observations, user research workshops, and prototyping. The participants for this study included general practitioners and pharmacists. In total, we undertook 5 sessions of ethnographic observation to understand current practices and workflows. This was followed by 3 user research workshops, each with its own topic guide starting with personas and early ideation, through to exploring the potential of clinical decision support systems and prototype design. We subsequently analyzed workshop data using affinity diagramming and refined the key requirements for the solution collaboratively as a multidisciplinary project team. RESULTS: User research results identified that pharmacogenetic data must be incorporated within existing EHRs rather than through a stand-alone portal. The information presented through clinical decision support systems must be clear, accessible, and user-friendly as the service will be used by a range of end users. Critically, the information should be displayed within the prescribing workflow, rather than discrete results stored statically in the EHR. Finally, the prescribing recommendations should be authoritative to provide confidence in the validity of the results. Based on these findings we co-designed an interactive prototype, demonstrating pharmacogenetic clinical decision support integrated within the prescribing workflow of an EHR. CONCLUSIONS: This study marks a significant step forward in the design of systems that support pharmacogenetic-guided prescribing in primary care settings. Clinical decision support systems have the potential to enhance the personalization of medicines, provided they are effectively implemented within EHRs and present pharmacogenetic data in a user-friendly, actionable, and standardized format. Achieving this requires the development of a decoupled, standards-based architecture that allows for the separation of data from application, facilitating integration across various EHRs through the use of application programming interfaces (APIs). More globally, this study demonstrates the role of health informatics and user-centered design in realizing the potential of personalized medicine at scale and ensuring that the benefits of genomic innovation reach patients and populations effectively.

Predictors of Health Care Practitioners' Intention to Use AI-Enabled Clinical Decision Support Systems: Meta-Analysis Based on the Unified Theory of Acceptance and Use of Technology.

BACKGROUND: Artificial intelligence-enabled clinical decision support systems (AI-CDSSs) offer potential for improving health care outcomes, but their adoption among health care practitioners remains limited. OBJECTIVE: This meta-analysis identified predictors influencing health care practitioners' intention to use AI-CDSSs based on the Unified Theory of Acceptance and Use of Technology (UTAUT). Additional predictors were examined based on existing empirical evidence. METHODS: The literature search using electronic databases, forward searches, conference programs, and personal correspondence yielded 7731 results, of which 17 (0.22%) studies met the inclusion criteria. Random-effects meta-analysis, relative weight analyses, and meta-analytic moderation and mediation analyses were used to examine the relationships between relevant predictor variables and the intention to use AI-CDSSs. RESULTS: The meta-analysis results supported the application of the UTAUT to the context of the intention to use AI-CDSSs. The results showed that performance expectancy (r=0.66), effort expectancy (r=0.55), social influence (r=0.66), and facilitating conditions (r=0.66) were positively associated with the intention to use AI-CDSSs, in line with the predictions of the UTAUT. The meta-analysis further identified positive attitude (r=0.63), trust (r=0.73), anxiety (r=-0.41), perceived risk (r=-0.21), and innovativeness (r=0.54) as additional relevant predictors. Trust emerged as the most influential predictor overall. The results of the moderation analyses show that the relationship between social influence and use intention becomes weaker with increasing age. In addition, the relationship between effort expectancy and use intention was stronger for diagnostic AI-CDSSs than for devices that combined diagnostic and treatment recommendations. Finally, the relationship between facilitating conditions and use intention was mediated through performance and effort expectancy. CONCLUSIONS: This meta-analysis contributes to the understanding of the predictors of intention to use AI-CDSSs based on an extended UTAUT model. More research is needed to substantiate the identified relationships and explain the observed variations in effect sizes by identifying relevant moderating factors. The research findings bear important implications for the design and implementation of training programs for health care practitioners to ease the adoption of AI-CDSSs into their practice.

Resilient Artificial Intelligence in Health: Synthesis and Research Agenda Toward Next-Generation Trustworthy Clinical Decision Support.

Artificial intelligence (AI)-based clinical decision support systems are gaining momentum by relying on a greater volume and variety of secondary use data. However, the uncertainty, variability, and biases in real-world data environments still pose significant challenges to the development of health AI, its routine clinical use, and its regulatory frameworks. Health AI should be resilient against real-world environments throughout its lifecycle, including the training and prediction phases and maintenance during production, and health AI regulations should evolve accordingly. Data quality issues, variability over time or across sites, information uncertainty, human-computer interaction, and fundamental rights assurance are among the most relevant challenges. If health AI is not designed resiliently with regard to these real-world data effects, potentially biased data-driven medical decisions can risk the safety and fundamental rights of millions of people. In this viewpoint, we review the challenges, requirements, and methods for resilient AI in health and provide a research framework to improve the trustworthiness of next-generation AI-based clinical decision support.

Integrating Text and Image Analysis: Exploring GPT-4V's Capabilities in Advanced Radiological Applications Across Subspecialties.

This study demonstrates that GPT-4V outperforms GPT-4 across radiology subspecialties in analyzing 207 cases with 1312 images from the Radiological Society of North America Case Collection.

Adolescent, parent, and provider attitudes toward a machine learning based clinical decision support system for selecting treatment for youth depression.

BACKGROUND: Machine learning based clinical decision support systems (CDSSs) have been proposed as a means of advancing personalized treatment planning for disorders, such as depression, that have a multifaceted etiology, course, and symptom profile. However, machine learning based models for treatment selection are rare in the field of psychiatry. They have also not yet been translated for use in clinical practice. Understanding key stakeholder attitudes toward machine learning based CDSSs is critical for developing plans for their implementation that promote uptake by both providers and families. METHODS: In Study 1, a prototype machine learning based Clinical Decision Support System for Youth Depression (CDSS-YD) was demonstrated to focus groups of adolescents with a diagnosis of depression (n = 9), parents (n = 11), and behavioral health providers (n = 8). Qualitative analysis was used to assess their attitudes towards the CDSS-YD. In Study 2, behavioral health providers were trained in the use of the CDSS-YD and they utilized the CDSS-YD in a clinical encounter with 6 adolescents and their parents as part of their treatment planning discussion. Following the appointment, providers, parents, and adolescents completed a survey about their attitudes regarding the use of the CDSS-YD. RESULTS: All stakeholder groups viewed the CDSS-YD as an easy to understand and useful tool for making personalized treatment decisions, and families and providers were able to successfully use the CDSS-YD in clinical encounters. Parents and adolescents viewed their providers as having a critical role in the use the CDSS-YD, and this had implications for the perceived trustworthiness of the CDSS-YD. Providers reported that clinic productivity metrics would be the primary barrier to CDSS-YD implementation, with the creation of protected time for training, preparation, and use as a key facilitator. CONCLUSIONS: Machine learning based CDSSs, if proven effective, have the potential to be widely accepted tools for personalized treatment planning. Successful implementation will require addressing the system-level barrier of having sufficient time and energy to integrate it into practice.

Straight to the point: evaluation of a Point of Care Information (POCI) resource in answering disease-related questions.

Objective: To evaluate the ability of DynaMedex, an evidence-based drug and disease Point of Care Information (POCI) resource, in answering clinical queries using keyword searches. Methods: Real-world disease-related questions compiled from clinicians at an academic medical center, DynaMedex search query data, and medical board review resources were categorized into five clinical categories (complications & prognosis, diagnosis & clinical presentation, epidemiology, prevention & screening/monitoring, and treatment) and six specialties (cardiology, endocrinology, hematology-oncology, infectious disease, internal medicine, and neurology). A total of 265 disease-related questions were evaluated by pharmacist reviewers based on if an answer was found (yes, no), whether the answer was relevant (yes, no), difficulty in finding the answer (easy, not easy), cited best evidence available (yes, no), clinical practice guidelines included (yes, no), and level of detail provided (detailed, limited details). Results: An answer was found for 259/265 questions (98%). Both reviewers found an answer for 241 questions (91%), neither found the answer for 6 questions (2%), and only one reviewer found an answer for 18 questions (7%). Both reviewers found a relevant answer 97% of the time when an answer was found. Of all relevant answers found, 68% were easy to find, 97% cited best quality of evidence available, 72% included clinical guidelines, and 95% were detailed. Recommendations for areas of resource improvement were identified. Conclusions: The resource enabled reviewers to answer most questions easily with the best quality of evidence available, providing detailed answers and clinical guidelines, with a high level of replication of results across users.

Effectiveness of Artificial Intelligence (AI) in Clinical Decision Support Systems and Care Delivery.

This review aims to assess the effectiveness of AI-driven CDSSs on patient outcomes and clinical practices. A comprehensive search was conducted across PubMed, MEDLINE, and Scopus. Studies published from January 2018 to November 2023 were eligible for inclusion. Following title and abstract screening, full-text articles were assessed for methodological quality and adherence to inclusion criteria. Data extraction focused on study design, AI technologies employed, reported outcomes, and evidence of AI-CDSS impact on patient and clinical outcomes. Thematic analysis was conducted to synthesise findings and identify key themes regarding the effectiveness of AI-CDSS. The screening of the articles resulted in the selection of 26 articles that satisfied the inclusion criteria. The content analysis revealed four themes: early detection and disease diagnosis, enhanced decision-making, medication errors, and clinicians' perspectives. AI-based CDSSs were found to improve clinical decision-making by providing patient-specific information and evidence-based recommendations. Using AI in CDSSs can potentially improve patient outcomes by enhancing diagnostic accuracy, optimising treatment selection, and reducing medical errors.

The influence of explainable vs non-explainable clinical decision support systems on rapid triage decisions: a mixed methods study.

BACKGROUND: During the COVID-19 pandemic, a variety of clinical decision support systems (CDSS) were developed to aid patient triage. However, research focusing on the interaction between decision support systems and human experts is lacking. METHODS: Thirty-two physicians were recruited to rate the survival probability of 59 critically ill patients by means of chart review. Subsequently, one of two artificial intelligence systems advised the physician of a computed survival probability. However, only one of these systems explained the reasons behind its decision-making. In the third step, physicians reviewed the chart once again to determine the final survival probability rating. We hypothesized that an explaining system would exhibit a higher impact on the physicians' second rating (i.e., higher weight-on-advice). RESULTS: The survival probability rating given by the physician after receiving advice from the clinical decision support system was a median of 4 percentage points closer to the advice than the initial rating. Weight-on-advice was not significantly different (p = 0.115) between the two systems (with vs without explanation for its decision). Additionally, weight-on-advice showed no difference according to time of day or between board-qualified and not yet board-qualified physicians. Self-reported post-experiment overall trust was awarded a median of 4 out of 10 points. When asked after the conclusion of the experiment, overall trust was 5.5/10 (non-explaining median 4 (IQR 3.5-5.5), explaining median 7 (IQR 5.5-7.5), p = 0.007). CONCLUSIONS: Although overall trust in the models was low, the median (IQR) weight-on-advice was high (0.33 (0.0-0.56)) and in line with published literature on expert advice. In contrast to the hypothesis, weight-on-advice was comparable between the explaining and non-explaining systems. In 30% of cases, weight-on-advice was 0, meaning the physician did not change their rating. The median of the remaining weight-on-advice values was 50%, suggesting that physicians either dismissed the recommendation or employed a "meeting halfway" approach. Newer technologies, such as clinical reasoning systems, may be able to augment the decision process rather than simply presenting unexplained bias.

The combined effect of BMI and age on ART outcomes.

STUDY QUESTION: For a woman with infertility and overweight/obesity, can infertility treatment be postponed to first promote weight loss? SUMMARY ANSWER: Advice regarding a delay in IVF treatment to optimize female weight should consider female age, particularly in women over 38 years for whom only substantial weight loss in a short period of time (3 months) seems to provide any benefit. WHAT IS KNOWN ALREADY: Body weight excess and advanced age are both common findings in infertile patients, creating the dilemma of whether to promote weight loss first or proceed to fertility treatment immediately. Despite their known impact on fertility, studies assessing the combined effect of female age and BMI on cumulative live birth rates (CLBRs) are still scarce and conflicting. STUDY DESIGN, SIZE, DURATION: We performed a multicentre retrospective cohort study including 14 213 patients undergoing their first IVF/ICSI cycle with autologous oocytes and subsequent embryo transfers, between January 2013 and February 2018 in 18 centres of a multinational private fertility clinic. BMI was subdivided into the following subgroups: underweight (<18.5 kg/m2), normal weight (18.5-24.9 kg/m2), overweight (25.0-29.9 kg/m2), and obesity (≥30.0 kg/m2). PARTICIPANTS/MATERIALS, SETTING, METHODS: The primary outcome was CLBR. The secondary outcome was time to pregnancy. To assess the influence of female age and BMI on CLBR, two multivariable regression models were developed with BMI being added in the models as either an ordinal categorical variable (Model 1) or a continuous variable (Model 2) using the best-fitting fractional polynomials. CLBR was estimated over 1-year periods (Model 1) and shorter timeframes of 3 months (Model 2). We then compared the predicted CLBRs according to BMI and age. MAIN RESULTS AND THE ROLE OF CHANCE: When compared to normal weight, CLBRs were lower in women who were overweight (adjusted odds ratio (aOR) 0.86, 95% CI 0.77-0.96) and obese (aOR 0.74, 95% CI 0.62-0.87). A reduction of BMI within 1 year, from obesity to overweight or overweight to normal weight would be potentially beneficial up to 35 years old, while only a substantial reduction (i.e. from obesity to normal BMI) would be potentially beneficial in women aged 36-38 years. Above 38 years of age, even considerable weight loss did not compensate for the effect of age over a 1-year span but may be beneficial in shorter time frames. In a timeframe of 3 months, there is a potential benefit in CLBR if there is a loss of 1 kg/m2 in BMI for women up to 33.25 years and 2 kg/m2 in women aged 33.50-35.50 years. Older women would require more challenging weight loss to achieve clinical benefit, specifically 3 kg/m2 in women aged 35.75-37.25 years old, 4 kg/m2 in women aged 37.50-39.00 years old, and 5 kg/m2 or more in women over 39.25 years old. LIMITATIONS, REASONS FOR CAUTION: This study is limited by its retrospective design and lower number of women in the extreme BMI categories. The actual effect of individual weight loss on patient outcomes was also not evaluated, as this was a retrospective interpatient comparison to estimate the combined effect of weight loss and ageing in a fixed period on CLBR. WIDER IMPLICATIONS OF THE FINDINGS: Our findings suggest that there is potential benefit in weight loss strategies within 1 year prior to ART, particularly in women under 35 years with BMI ≥25 kg/m2. For those over 35 years of age, weight loss should be considerable or occur in a shorter timeframe to avoid the negative effect of advancing female age on CLBR. A tailored approach for weight loss, according to age, might be the best course of action. STUDY FUNDING/COMPETING INTEREST(S): No specific funding was obtained for this study. All authors have no conflicts to declare. TRIAL REGISTRATION NUMBER: N/A.

Inappropriate CT examinations: how much, who and where? Insights from a clinical decision support system (CDSS) analysis.

OBJECTIVE: To assess the appropriateness of Computed Tomography (CT) examinations, using the ESR-iGuide. MATERIAL AND METHODS: A retrospective study was conducted in 2022 in a medium-sized acute care teaching hospital. A total of 278 consecutive cases of CT referral were included. For each imaging referral, the ESR-iGuide provided an appropriateness score using a scale of 1-9 and the Relative Radiation Level using a scale of 0-5. These were then compared with the appropriateness score and the radiation level of the recommended ESR-iGuide exam. DATA ANALYSIS: Pearson's chi-square test or Fisher exact test was used to explore the correlation between ESR-iGuide appropriateness level and physician, patients, and shift characteristics. A stepwise logistic regression model was used to capture the contribution of each of these factors. RESULTS: Most of exams performed were CT head (63.67%) or CT abdominal pelvis (23.74%). Seventy percent of the actual imaging referrals resulted in an ESR-iGuide score corresponding to "usually appropriate." The mean radiation level for actual exam was 3.2 ± 0.45 compared with 2.16 ± 1.56 for the recommended exam. When using a stepwise logistic regression for modeling the probability of non-appropriate score, both physician specialty and status were significant (p = 0.0011, p = 0.0192 respectively). Non-surgical and specialist physicians were more likely to order inappropriate exams than surgical physicians. CONCLUSIONS: ESR-iGuide software indicates a substantial rate of inappropriate exams of CT head and CT abdominal-pelvis and unnecessary radiation exposure mainly in the ED department. Inappropriate exams were found to be related to physicians' specialty and seniority. CLINICAL RELEVANCE STATEMENT: These findings underscore the urgent need for improved imaging referral practices to ensure appropriate healthcare delivery and effective resource management. Additionally, they highlight the potential benefits and necessity of integrating CDSS as a standard medical practice. By implementing CDSS, healthcare providers can make more informed decisions, leading to enhanced patient care, optimized resource allocation, and improved overall healthcare outcomes. KEY POINTS: • The overall mean of appropriateness for the actual exam according to the ESR-iGuide was 6.62 ± 2.69 on a scale of 0-9. • Seventy percent of the actual imaging referrals resulted in an ESR-iGuide score corresponding to "usually appropriate." • Inappropriate examination is related to both the specialty of the physician who requested the exam and the seniority status of the physician.