Generative artificial intelligence in primary care: an online survey of UK general practitioners.

OBJECTIVES: Following the launch of ChatGPT in November 2022, interest in large language model-powered chatbots has soared with increasing focus on the clinical potential of these tools. We sought to measure general practitioners' (GPs) current use of this new generation of chatbots to assist with any aspect of clinical practice in the UK. METHODS: An online survey was distributed to a non-probability sample of GPs registered with the clinician marketing service Doctors.net.uk. The study was launched as a monthly 'omnibus survey' which has a predetermined sample size of 1000 participants. RESULTS: 531 (53%) respondents were men, 544 (54%) were 46 years or older. 20% (205) reported using generative artificial intelligence (AI) tools in clinical practice; of those who answered affirmatively and were invited to clarify further, 29% (47) reported using these tools to generate documentation after patient appointments and 28% (45) to suggest a differential diagnosis. DISCUSSION: Administered a year after ChatGPT was launched, this is the largest survey we know of conducted into doctors' use of generative AI in clinical practice. Findings suggest that GPs may derive value from these tools, particularly with administrative tasks and to support clinical reasoning. CONCLUSION: Despite a lack of guidance about these tools and unclear work policies, GPs report using generative AI to assist with their job. The medical community will need to find ways to both educate physicians and trainees and guide patients about the safe adoption of these tools.

Towards inclusive biodesign and innovation: lowering barriers to entry in medical device development through large language model tools.

In the following narrative review, we discuss the potential role of large language models (LLMs) in medical device innovation, specifically examples using generative pretrained transformer-4. Throughout the biodesign process, LLMs can offer prompt-driven insights, aiding problem identification, knowledge assimilation and decision-making. Intellectual property analysis, regulatory assessment and market analysis emerge as key LLM applications. Through case examples, we underscore LLMs' transformative ability to democratise information access and expertise, facilitating inclusive innovation in medical devices as well as its effectiveness with providing real-time, individualised feedback for innovators of all experience levels. By mitigating entry barriers, LLMs accelerate transformative advancements, fostering collaboration among established and emerging stakeholders.

Making Drug Approval Decisions in the Face of Uncertainty: Cumulative Evidence versus Value of Information.

BACKGROUND: The COVID-19 pandemic underscored the criticality and complexity of decision making for novel treatment approval and further research. Our study aims to assess potential decision-making methodologies, an evaluation vital for refining future public health crisis responses. METHODS: We compared 4 decision-making approaches to drug approval and research: the Food and Drug Administration's policy decisions, cumulative meta-analysis, a prospective value-of-information (VOI) approach (using information available at the time of decision), and a reference standard (retrospective VOI analysis using information available in hindsight). Possible decisions were to reject, accept, provide emergency use authorization, or allow access to new therapies only in research settings. We used monoclonal antibodies provided to hospitalized COVID-19 patients as a case study, examining the evidence from September 2020 to December 2021 and focusing on each method's capacity to optimize health outcomes and resource allocation. RESULTS: Our findings indicate a notable discrepancy between policy decisions and the reference standard retrospective VOI approach with expected losses up to $269 billion USD, suggesting suboptimal resource use during the wait for emergency use authorization. Relying solely on cumulative meta-analysis for decision making results in the largest expected loss, while the policy approach showed a loss up to $16 billion and the prospective VOI approach presented the least loss (up to $2 billion). CONCLUSION: Our research suggests that incorporating VOI analysis may be particularly useful for research prioritization and treatment implementation decisions during pandemics. While the prospective VOI approach was favored in this case study, further studies should validate the ideal decision-making method across various contexts. This study's findings not only enhance our understanding of decision-making strategies during a health crisis but also provide a potential framework for future pandemic responses. HIGHLIGHTS: This study reviews discrepancies between a reference standard (retrospective VOI, using hindsight information) and 3 conceivable real-time approaches to research-treatment decisions during a pandemic, suggesting suboptimal use of resources.Of all prospective decision-making approaches considered, VOI closely mirrored the reference standard, yielding the least expected value loss across our study timeline.This study illustrates the possible benefit of VOI results and the need for evidence accumulation accompanied by modeling in health technology assessment for emerging therapies.

"You just have to be careful how you do it": A qualitative study of the Healthwise decision aid for older drivers.

OBJECTIVE: Decisions about driving retirement are difficult for older adults, their families, and health care providers. A large randomized trial found that an existing online Healthwise decision aid decreased decision conflict and increased knowledge about driving decisions. This study sought to discover how, when, and where the tool might be most effective for older drivers, their family members, and their health care providers. METHODS: We used one-on-one, semistructured interviews (June-December 2023) to explore perspectives on the content of the Healthwise online driving decision aid and its potential use. Participants were health care providers or subject matter experts in older driver research or policy. Transcribed interviews were coded and analyzed with a team-based approach to identify emerging themes. RESULTS: Across interviews (16 health care providers; 15 experts), emerging themes related to considerations (barriers, benefits, and settings for use) that were (1) individual or interpersonal or (2) institutional or cultural, as well as feedback on (3) decision aid content and structure. Findings included concerns over agism and damaging provider-patient relationships, along with identified benefits of integrating tools into electronic health records and a need for consolidated, easy-to-access resources for both providers and patients. CONCLUSION: Attention to individual, interpersonal, institutional, and cultural factors may enhance the use and dissemination of an online decision aid about driving, as well as its effectiveness in decision making. Future work should include views of additional stakeholders and studies on implementation of decision aids into real-world settings.

The Variable Definition of "Negative Appendicitis" Remains a Surgical Challenge.

AIM: Acute appendicitis (AA) is treated primarily surgically with histopathology being the gold standard for confirmation of appendicitis and reported rates of negative appendicectomies (NA) ranging between 3.2% and 19% worldwide and 15.9-20.6% in the UK. NA rates are frequently used to identify poor performing centers as part of a Model Health System and form an integral part of appendicitis scoring systems. This study aims to evaluate the prevalence of negative appendicectomies within our institution and critically analyze the appropriateness of its use as a quality metric and its impact on clinical practice and research. PATIENTS AND METHODS: Data analysis from a prospective dataset of pediatric appendicitis patients between 2015 and 2021 in a tertiary center in the UK was performed. Detailed analysis of negative appendicectomies was performed and further stratified by two distinct age and gender groups looking at the incidence of NA and the classification of non-histologically normal appendix specimens. RESULTS: In our series, 819 patients met inclusion criteria, 736 (89.9%) had acute appendicitis. Our overall institutional negative appendicectomy rate was 10.1% (83 patients) with the breakdown as follows: 65 histologically normal appendix (7.9%), 10 Enterobius vermicularis, 3 eosinophilic appendicitis, 2 neoplasms, 1 isolated faecolith, 1 fibrous obliteration of the lumen, and 1 peri-appendiceal inflammation. CONCLUSION: Our negative appendicectomy rate is below established UK pediatric NA rates. This rate ranges from 7.9% to 10.1% depending on the definition of NA utilized. A single standard pathological definition for histological acute appendicitis is required when being used as a comparative quality metric. Centers engaged in clinical research should be aware of variations in NA definitions both in scoring systems and individual centers to avoid skewing derived results.

Insights into Predicting Tooth Extraction from Panoramic Dental Images: Artificial Intelligence vs. Dentists.

OBJECTIVES: Tooth extraction is one of the most frequently performed medical procedures. The indication is based on the combination of clinical and radiological examination and individual patient parameters and should be made with great care. However, determining whether a tooth should be extracted is not always a straightforward decision. Moreover, visual and cognitive pitfalls in the analysis of radiographs may lead to incorrect decisions. Artificial intelligence (AI) could be used as a decision support tool to provide a score of tooth extractability. MATERIAL AND METHODS: Using 26,956 single teeth images from 1,184 panoramic radiographs (PANs), we trained a ResNet50 network to classify teeth as either extraction-worthy or preservable. For this purpose, teeth were cropped with different margins from PANs and annotated. The usefulness of the AI-based classification as well that of dentists was evaluated on a test dataset. In addition, the explainability of the best AI model was visualized via a class activation mapping using CAMERAS. RESULTS: The ROC-AUC for the best AI model to discriminate teeth worthy of preservation was 0.901 with 2% margin on dental images. In contrast, the average ROC-AUC for dentists was only 0.797. With a 19.1% tooth extractions prevalence, the AI model's PR-AUC was 0.749, while the dentist evaluation only reached 0.589. CONCLUSION: AI models outperform dentists/specialists in predicting tooth extraction based solely on X-ray images, while the AI performance improves with increasing contextual information. CLINICAL RELEVANCE: AI could help monitor at-risk teeth and reduce errors in indications for extractions.

Factors influencing the decision-making process in breast reconstruction from the perspective of reconstructive surgeons: A qualitative study involving Korean plastic surgeons.

BACKGROUND: Little research has been conducted on factors influencing the decision-making process for immediate breast reconstruction (IBR) options from the perspective of reconstructive surgeons, despite its significant impact on doctor-patient communication and shared decision-making. This study aims to explore the multiple factors and the mechanisms by which they interact using a qualitative methodology. We also address potential barriers to shared decision-making in IBR. METHODS: Semistructured interviews were conducted with a purposive sample of reconstructive surgeons. Thematic analysis was used to identify key influences on IBR decision-making process from the perspective of reconstructive surgeons. RESULTS: Four major themes were identified: 1. Patient clinical scenarios; 2. Nonclinical practice environments; 3. Reconstructive surgeon preferences; and 4. Patient consultation. Reconstructive surgeons demonstrated diverse approaches to patient clinical scenarios. High-volume centers were significantly influenced by nonclinical factors such as scheduling and operating room allocation systems. Reconstructive surgeons often had strong personal preferences for specific IBR options, shaped by their expertise, experience, and clinical environment. Based on the preliminary decision, surgeons provided information with varying degrees of neutrality. Patients varied in their knowledge and participation, resulting in variation in the final decision authority among surgeons. CONCLUSIONS: This study highlights the need to address nonclinical environmental constraints to improve shared decision-making process in IBR. Surgeons should recognize power imbalances in the doctor-patient relationship and be aware of their biases.

[OPTINOFA-Intelligent assistance service for structured assessment in the emergency department]. / OPTINOFA ­ Intelligenter Assistenzdienst zur strukturierten Ersteinschätzung in der Notaufnahme.

BACKGROUND: Case numbers in central emergency departments (EDs) have risen during the past decade in Germany, leading to recurrent overcrowding, increased risks in emergency care, and elevated costs. Particularly the fraction of outpatient emergency treatments has increased disproportionately. Within the framework of the Optimization of emergency care by structured triage with intelligent assistant service (OPTINOFA, Förderkennzeichen [FKZ] 01NVF17035) project, an intelligent assistance service was developed. PATIENTS AND METHODS: New triage algorithms were developed for the 20 most frequent leading symptoms on the basis of established triage systems (emergency severity index, ESI; Manchester triage system, MTS) and provided as web-based intelligent assistance services on mobile devices. To evaluate the validity, reliability, and safety of the new OPTINOFA triage instrument, a pilot study was conducted in three EDs after ethics committee approval. RESULTS: In the pilot study, n = 718 ED patients were included (age 59.1 ± 22 years; 349 male, 369 female). With respect to disposition (out-/inpatient), a sensitivity of 91.1% and a specificity of 40.7%, and a good correlation with the OPTINOFA triage levels were detected (Spearman's rank correlation ρ = 0.41). Furthermore, the area under the curve (AUC) for prediction of disposition according to the OPTINOFA triage level was 0.73. The in-hospital mortality rate of OPTINOFA triage levels 4 and 5 was 0%. The association between the length of ED stay and the OPTINOFA triage level was shown to be significant (p < 0.001). CONCLUSION: The results of the pilot study demonstrate the safety and validity of the new triage system OPTINOFA. By definition of both urgency and emergency care level, new customized perspectives for load reduction in German EDs via a closer cooperation between out- and inpatient sectors of emergency care could be established.

Diagnostic accuracy validation study of the M6 model without initial serum progesterone (M6NP) in triage of pregnancy of unknown location.

OBJECTIVES: The M6 prediction model stratifies the risk of development of ectopic pregnancy (EP) for women with pregnancy of unknown location (PUL) into low risk or high risk, using human chorionic gonadotrophin (hCG) and progesterone levels at the initial visit to a gynaecological emergency room and hCG level at 48 h. This study evaluated a second model, the M6NP model, which does not include the progesterone level at the initial visit. The main aim of this study was to validate the diagnostic accuracy of the M6NP model in a population of French women. STUDY DESIGN: Between January and December 2021, all women with an hCG measurement from the gynaecological emergency department of a teaching hospital were screened for inclusion in this study. Women with a pregnancy location determined before or at the second visit were excluded. The diagnostic test was based on logistic regression of the M6NP model, with classification into two groups: high risk of EP (≥5%) and low risk of EP (<5%). The reference test was the final outcome based on clinical, biological and sonographic results: failed PUL (FPUL), intrauterine pregnancy (IUP) or EP. Diagnostic performance for risk prediction of EP, and also IUP and FPUL, was calculated. RESULTS: In total, 759 women with possible PUL were identified. After screening, 341 women with PUL were included in the main analysis. Of these, 186 (54.5%) were classified as low risk, including three (1.6%) with a final outcome of EP. The remaining 155 women with PUL were classified as high risk, of whom 60 (38.7%), 66 (42.8%) and 29 (18.7%) had a final outcome of FPUL, IUP and EP, respectively. Of the 32 women with PUL with a final outcome of EP, 29 (90.6%) were classified as high risk and three (9.4%) were classified as low risk. Therefore, the performance of the M6NP model to predict EP had a negative predictive value of 98.4%, a positive predictive value of 18.7%, sensitivity of 90.6% and specificity of 59.2%. If the prediction model had been used, it is estimated that 4.5 visits per patient could have been prevented. CONCLUSION: The M6NP model could be used safely in the French population for risk stratification of PUL. Its use in clinical practice should result in a substantial reduction in the number of visits to a gynaecological emergency room.

Developing a breast cancer screening decision aid in Spanish for average-risk women: a mixed methods study.

Introduction: We aimed to develop a decision aid to support shared-decision making between physicians and women with average breast cancer risk when deciding whether to participate in breast cancer screening. Methods: We included women at average risk of breast cancer and physicians involved in supporting the decision of breast cancer screening from an Academic Hospital in Buenos Aires, Argentina. We followed the International Patient Decision Aid Standards to develop our decision aid. Guided by a steering group and a multidisciplinary consultancy group including a patient advocate, we reviewed the evidence about breast cancer screening and previous decision aids, explored the patients' information needs on this topic from the patients' and physicians' perspective using semi-structured interviews, and we alpha-tested the prototype to determine its usability, comprehensibility and applicability. Results: We developed the first prototype of a web-based decision aid to use during the clinical encounter with women aged 40 to 69 with average breast cancer risk. After a meeting with our consultancy group, we developed a second prototype that underwent alpha-testing. Physicians and patients agreed that the tool was clear, useful and applicable during a clinical encounter. We refined our final prototype according to their feedback. Conclusion: We developed the first decision aid in our region and language on this topic, developed with end-users' input and informed by the best available evidence. We expect this decision aid to help women and physicians make shared decisions during the clinical encounter when talking about breast cancer screening.

Developing a breast cancer screening decision aid in Spanish for average-risk women: a mixed methods study / Estudios originales Publicado el 14 de marzo de 2024 | http://doi.org/10.5867/medwave.2024.02.2726 Developing a breast cancer screening decision aid in Spanish for average-risk women: a mixed methods study Desarrollo de una herramienta en español para ayudar en la toma de decisiones del cribado de cáncer de mama para mujeres de riesgo promedio: un estudio de métodos mixtos

Introduction We aimed to develop a decision aid to support shared-decision making between physicians and women with average breast cancer risk when deciding whether to participate in breast cancer screening. Methods We included women at average risk of breast cancer and physicians involved in supporting the decision of breast cancer screening from an Academic Hospital in Buenos Aires, Argentina. We followed the International Patient Decision Aid Standards to develop our decision aid. Guided by a steering group and a multidisciplinary consultancy group including a patient advocate, we reviewed the evidence about breast cancer screening and previous decision aids, explored the patients' information needs on this topic from the patients' and physicians' perspective using semi-structured interviews, and we alpha-tested the prototype to determine its usability, comprehensibility and applicability. Results We developed the first prototype of a web-based decision aid to use during the clinical encounter with women aged 40 to 69 with average breast cancer risk. After a meeting with our consultancy group, we developed a second prototype that underwent alpha-testing. Physicians and patients agreed that the tool was clear, useful and applicable during a clinical encounter. We refined our final prototype according to their feedback. Conclusion We developed the first decision aid in our region and language on this topic, developed with end-users' input and informed by the best available evidence. We expect this decision aid to help women and physicians make shared decisions during the clinical encounter when talking about breast cancer screening.

Patient values in patient-provider communication about participation in early phase clinical cancer trials: a qualitative analysis before and after implementation of an online value clarification tool intervention.

BACKGROUND: Patients with advanced cancer who no longer have standard treatment options available may decide to participate in early phase clinical trials (i.e. experimental treatments with uncertain outcomes). Shared decision-making (SDM) models help to understand considerations that influence patients' decision. Discussion of patient values is essential to SDM, but such communication is often limited in this context and may require new interventions. The OnVaCT intervention, consisting of a preparatory online value clarification tool (OnVaCT) for patients and communication training for oncologists, was previously developed to support SDM. This study aimed to qualitatively explore associations between patient values that are discussed between patients and oncologists during consultations about potential participation in early phase clinical trials before and after implementation of the OnVaCT intervention. METHODS: This study is part of a prospective multicentre nonrandomized controlled clinical trial and had a between-subjects design: pre-intervention patients received usual care, while post-intervention patients additionally received the OnVaCT. Oncologists participated in the communication training between study phases. Patients' initial consultation on potential early phase clinical trial participation was recorded and transcribed verbatim. Applying a directed approach, two independent coders analysed the transcripts using an initial codebook based on previous studies. Steps of continuous evaluation and revision were repeated until data saturation was reached. RESULTS: Data saturation was reached after 32 patient-oncologist consultations (i.e. 17 pre-intervention and 15 post-intervention). The analysis revealed the values: hope, perseverance, quality or quantity of life, risk tolerance, trust in the healthcare system/professionals, autonomy, social adherence, altruism, corporeality, acceptance of one's fate, and humanity. Patients in the pre-intervention phase tended to express values briefly and spontaneously. Oncologists acknowledged the importance of patients' values, but generally only gave 'contrasting' examples of why some accept and others refuse to participate in trials. In the post-intervention phase, many oncologists referred to the OnVaCT and/or asked follow-up questions, while patients used longer phrases that combined multiple values, sometimes clearly indicating their weighing. CONCLUSIONS: While all values were recognized in both study phases, our results have highlighted the different communication patterns around patient values in SDM for potential early phase clinical trial participation before and after implementation of the OnVaCT intervention. This study therefore provides a first (qualitative) indication that the OnVaCT intervention may support patients and oncologists in discussing their values. TRIAL REGISTRATION: Netherlands Trial Registry: NL7335, registered on July 17, 2018.

Modeling chronic disease risk across equity factors using a population-based prediction model: the Chronic Disease Population Risk Tool (CDPoRT).

BACKGROUND: Predicting chronic disease incidence at a population level can help inform overall future chronic disease burden and opportunities for prevention. This study aimed to estimate the future burden of chronic disease in Ontario, Canada, using a population-level risk prediction algorithm and model interventions for equity-deserving groups who experience barriers to services and resources due to disadvantages and discrimination. METHODS: The validated Chronic Disease Population Risk Tool (CDPoRT) estimates the 10-year risk and incidence of major chronic diseases. CDPoRT was applied to data from the 2017/2018 Canadian Community Health Survey to predict baseline 10-year chronic disease estimates to 2027/2028 in the adult population of Ontario, Canada, and among equity-deserving groups. CDPoRT was used to model prevention scenarios of 2% and 5% risk reductions over 10 years targeting high-risk equity-deserving groups. RESULTS: Baseline chronic disease risk was highest among those with less than secondary school education (37.5%), severe food insecurity (19.5%), low income (21.2%) and extreme workplace stress (15.0%). CDPoRT predicted 1.42 million new chronic disease cases in Ontario from 2017/2018 to 2027/2028. Reducing chronic disease risk by 5% prevented 1500 cases among those with less than secondary school education, prevented 14 900 cases among those with low household income and prevented 2800 cases among food-insecure populations. Large reductions of 57 100 cases were found by applying a 5% risk reduction in individuals with quite a bit workplace stress. CONCLUSION: Considerable reduction in chronic disease cases was predicted across equity-defined scenarios, suggesting the need for prevention strategies that consider upstream determinants affecting chronic disease risk.

Intrapartum use of sildenafil citrate to prevent fetal compromise and emergency operative birth in term pregnancies in the United Kingdom and Australia: A preliminary cost-effectiveness analysis.

OBJECTIVE: To compare cost-effectiveness of oral sildenafil citrate, administered after onset of labor, with standard care to health system funders in the UK and Australia. METHODS: We conducted a modeled cost-effectiveness analysis, measuring costs and quality adjusted life years (QALYs), using a decision-analytic model covering onset of labor to 1 month post-birth. The relative risk of emergency cesarean section and operative vaginal birth was taken from a Phase 2 placebo controlled double blinded randomized control trial. RESULTS: Both options of care resulted in the same QALYs gained over the model time period (0.08). Sildenafil citrate was cost-saving compared with standard care, saving £92 per birth in the UK (AU$303 per birth in Australia). Sensitivity analyses did not identify any areas of uncertainty that stopped sildenafil citrate being cost saving compared with standard care. Threshold analysis revealed that sildenafil citrate would be cost saving up to a per birth drug or administration cost of £152.32 in the UK (AU$333.61 in Australia). CONCLUSION: Oral sildenafil citrate may be cost saving compared with standard care; however, the effects on neonatal outcomes still need to be demonstrated in large randomized trials.

Estimating risk of endometrial malignancy and other intracavitary uterine pathology in women without abnormal uterine bleeding using IETA-1 multinomial regression model: validation study.

OBJECTIVES: To assess the ability of the International Endometrial Tumor Analysis (IETA)-1 polynomial regression model to estimate the risk of endometrial cancer (EC) and other intracavitary uterine pathology in women without abnormal uterine bleeding. METHODS: This was a retrospective study, in which we validated the IETA-1 model on the IETA-3 study cohort (n = 1745). The IETA-3 study is a prospective observational multicenter study. It includes women without vaginal bleeding who underwent a standardized transvaginal ultrasound examination in one of seven ultrasound centers between January 2011 and December 2018. The ultrasonography was performed either as part of a routine gynecological examination, during follow-up of non-endometrial pathology, in the work-up before fertility treatment or before treatment for uterine prolapse or ovarian pathology. Ultrasonographic findings were described using IETA terminology and were compared with histology, or with results of clinical and ultrasound follow-up of at least 1 year if endometrial sampling was not performed. The IETA-1 model, which was created using data from patients with abnormal uterine bleeding, predicts four histological outcomes: (1) EC or endometrial intraepithelial neoplasia (EIN); (2) endometrial polyp or intracavitary myoma; (3) proliferative or secretory endometrium, endometritis, or endometrial hyperplasia without atypia; and (4) endometrial atrophy. The predictors in the model are age, body mass index and seven ultrasound variables (visibility of the endometrium, endometrial thickness, color score, cysts in the endometrium, non-uniform echogenicity of the endometrium, presence of a bright edge, presence of a single dominant vessel). We analyzed the discriminative ability of the model (area under the receiver-operating-characteristics curve (AUC); polytomous discrimination index (PDI)) and evaluated calibration of its risk estimates (observed/expected ratio). RESULTS: The median age of the women in the IETA-3 cohort was 51 (range, 20-85) years and 51% (887/1745) of the women were postmenopausal. Histology showed EC or EIN in 29 (2%) women, endometrial polyps or intracavitary myomas in 1094 (63%), proliferative or secretory endometrium, endometritis, or hyperplasia without atypia in 144 (8%) and endometrial atrophy in 265 (15%) women. The endometrial sample had insufficient material in five (0.3%) cases. In 208 (12%) women who did not undergo endometrial sampling but were followed up for at least 1 year without clinical or ultrasound signs of endometrial malignancy, the outcome was classified as benign. The IETA-1 model had an AUC of 0.81 (95% CI, 0.73-0.89, n = 1745) for discrimination between malignant (EC or EIN) and benign endometrium, and the observed/expected ratio for EC or EIN was 0.51 (95% CI, 0.32-0.82). The model was able to categorize the four histological outcomes with considerable accuracy: the PDI of the model was 0.68 (95% CI, 0.62-0.73) (n = 1532). The IETA-1 model discriminated very well between endometrial atrophy and all other intracavitary uterine conditions, with an AUC of 0.96 (95% CI, 0.95-0.98). Including only patients in whom the endometrium was measurable (n = 1689), the model's AUC was 0.83 (95% CI, 0.75-0.91), compared with 0.62 (95% CI, 0.52-0.73) when using endometrial thickness alone to predict malignancy (difference in AUC, 0.21; 95% CI, 0.08-0.32). In postmenopausal women with measurable endometrial thickness (n = 848), the IETA-1 model gave an AUC of 0.81 (95% CI, 0.71-0.91), while endometrial thickness alone gave an AUC of 0.70 (95% CI, 0.60-0.81) (difference in AUC, 0.11; 95% CI, 0.01-0.20). CONCLUSION: The IETA-1 model discriminates well between benign and malignant conditions in the uterine cavity in patients without abnormal bleeding, but it overestimates the risk of malignancy. It also discriminates well between the four histological outcome categories. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Factors influencing the engagement of older adults with neurocognitive disorders in the design of decision aids: A qualitative descriptive study.

OBJECTIVE: To identify factors influencing the engagement of older adults with neurocognitive disorders (NCDs) in the design of decision aids (DAs). METHODS: We conducted a qualitative descriptive study using semi-structured interviews with 23 older adults with NCDs who were accompanied by 27 caregivers. This is a secondary analysis of a published study to identify the features of DAs designed for this population and their caregivers. RESULTS: Several behaviours and attitudes of caregivers and researchers hindered the older adults' engagement in the DA design process. Specific communication strategies can be employed to support their engagement and overcome the communication challenges inherent to this population, such as memory, attention, hearing, or visual impairments. Adopting the appropriate attitude, taking the time, and providing guidance to the older person can help them focus on the topic, while developing trust between participants is a facilitator to obtain their feedback. CONCLUSION: Findings from this project could serve to inform the communication and co-design of DAs with older people with NCDs and their caregivers. PRACTICE IMPLICATIONS: Caregivers and researchers have key roles to play in facilitating communication with older persons with NCDs so they are empowered to help in co-designing DAs.

Decisional conflict in parents of children with congenital heart defect: Towards development of a model.

AIM: This study aimed to develop a model to help parents cope with decisional conflict. BACKGROUND: Parents of children with congenital heart defect experience decisional conflict when they are uncertain about treatment decisions for their child, which may lead to delay in seeking care or distress over the decision made. DESIGN: Correlational design with model building and data triangulation was used. METHODS: Data were collected through surveys and interviews with a consecutive sample of 221 parent respondents from June to December 2018. Structural equation modelling and qualitative data analysis were used. RESULTS: Lower decisional conflict was seen in parents with higher income, more nurse support and physician risk communication. Time delay for surgery was correlated with the child's age, social service coverage, and social support. Decisional conflict mediated the influence of income, nurse support and physician risk communication on satisfaction with decision. Based on model fit parameters, the emerging model is a good and parsimonious model of decisional conflict. The overall theme, 'Deciding for Surgery: What Matters Most', described the processes parents went through in making treatment decisions. CONCLUSION: Nurses may help parents feel more certain, less conflicted, and more satisfied with their decision by addressing factors including knowledge gaps, personal values, available support, and resource access.

Explaining predictors of discharge destination assessed along the patients' acute stroke journey.

INTRODUCTION: Accurate prediction of outcome destination at an early stage would help manage patients presenting with stroke. This study assessed the predictive ability of three machine learning (ML) algorithms to predict outcomes at four different stages as well as compared the predictive power of stroke scores. METHODS: Patients presenting with acute stroke to the Canberra Hospital between 2015 and 2019 were selected retrospectively. 16 potential predictors and one target variable (discharge destination) were obtained from the notes. k-Nearest Neighbour (kNN) and two ensemble-based classification algorithms (Adaptive Boosting and Bootstrap Aggregation) were employed to predict outcomes. Predictive accuracy was assessed at each of the four stages using both overall and per-class accuracy. The contribution of each variable to the prediction outcome was evaluated by the ensemble-based algorithm and using the Relief feature selection algorithm. Various combinations of stroke scores were tested using the aforementioned models. RESULTS: Of the three ML models, Adaptive Boosting demonstrated the highest accuracy (90%) at Stage 4 in predicting death while the highest overall accuracy (81.7%) was achieved by kNN (k=2/City-block distance). Feature importance analysis has shown that the most important features are the 24-hour Scandinavian Stroke Scale (SSS) and 24-hour National Institutes of Health Stroke Scale (NIHSS) scores, dyslipidaemia, hypertension and premorbid mRS score. For the initial and 24-hour scores, there was a higher correlation (0.93) between SSS scores than for NIHSS scores (0.81). Reducing the overall four scores to InitSSS/24hrNIHSS increased accuracy to 95% in predicting death (Adaptive Boosting) and overall accuracy to 85.4% (kNN). Accuracies at Stage 2 (pre-treatment, 11 predictors) were not far behind those at Stage 4. CONCLUSION: Our findings suggest that even in the early stages of management, a clinically useful prediction regarding discharge destination can be made. Adaptive Boosting might be the best ML model, especially when it comes to predicting death. The predictors' importance analysis also showed that dyslipidemia and hypertension contributed to the discharge outcome even more than expected. Further, surprisingly using mixed score systems might also lead to higher prediction accuracies.

A nomogram-based clinical tool for acute ischemic stroke screening in prehospital setting.

Background: We believe that designing a new tool which is comparable in terms of both sensitivity and specificity may play an important role in rapid and more accurate diagnosis of acute ischemic stroke (AIS) in prehospital stage. Therefore, we intended to develop a new clinical tool for the diagnosis of AIS in the prehospital stage. Methods: This was a cross-sectional diagnostic accuracy study. All patients transferred to the emergency department (ED) who underwent brain magnetic resonance imaging (MRI) with impression of AIS were evaluated by 9 clinical tools for stroke diagnosis in the pre-hospital phase including Rapid Arterial Occlusion Evaluation (RACE), Cincinnati Prehospital Stroke Scale (CPSS), Los Angeles Prehospital Stroke Screen (LAPSS), Melbourne Ambulance Stroke Screen (MASS), Medic Prehospital Assessment for Code Stroke (Med PACS), Ontario Prehospital Stroke Screening Tool (OPSS), PreHospital Ambulance Stroke Test (PreHAST), Recognition of Stroke in the Emergency Room (ROSIER), and Face Arm Speech Test (FAST), and totally 19 items were reviewed and recorded. The new clinical tool was developed based on backward method of multivariable logistic regression analysis. The discrimination power of the new clinical tool for diagnosis of AIS was assessed with the area under the receiver operating characteristic curve (AUC-ROC). Results: Data from 806 patients were analyzed; of them, 57.4% were men. The mean age of the study patients was 66.9 years [standard deviation (SD) = 13.9]. In the multivariable model, 8 items remained. The AUC-ROC of the new clinical tool was 0.893 [95% confidence interval (CI): 0.869-0.917], and its best cut-off point was score ≥ 3 for positive AIS. At this cut-off point, sensitivity and specificity were 84.42% and 79.72%, respectively. Conclusion: We introduced a new nomogram-based clinical tool for the diagnosis of AIS in the prehospital stage, which has acceptable specificity and sensitivity; moreover, it is comparable with previous tools.