Medicine Package Recommendation via Dual-Level Interaction Aware Heterogeneous Graph.

Medicine package recommendation aims to assist doctors in clinical decision-making by recommending appropriate packages of medicines for patients. Current methods model this task as a multi-label classification or sequence generation problem, focusing on learning relationships between individual medicines and other medical entities. However, these approaches uniformly overlook the interactions between medicine packages and other medical entities, potentially resulting in a lack of completeness in recommended medicine packages. Furthermore, medicine commonsense knowledge considered by current methods is notably limited, making it challenging to delve into the decision-making processes of doctors. To solve these problems, we propose DIAGNN, a Dual-level Interaction Aware heterogeneous Graph Neural Network for medicine package recommendation. Specifically, DIAGNN explicitly models interactions of medical entities within electronic health records(EHRs) at two levels, individual medicine and medicine package, leveraging a heterogeneous graph. A dual-level interaction aware graph convolutional network is utilized to capture semantic information in the medical heterogeneous graph. Additionally, we incorporate medication indications into the medical heterogeneous graph as medicine commonsense knowledge. Extensive experimental results on real-world datasets validate the effectiveness of the proposed method.

Harnessing artificial intelligence for prostate cancer management.

Prostate cancer (PCa) is a common malignancy in males. The pathology review of PCa is crucial for clinical decision-making, but traditional pathology review is labor intensive and subjective to some extent. Digital pathology and whole-slide imaging enable the application of artificial intelligence (AI) in pathology. This review highlights the success of AI in detecting and grading PCa, predicting patient outcomes, and identifying molecular subtypes. We propose that AI-based methods could collaborate with pathologists to reduce workload and assist clinicians in formulating treatment recommendations. We also introduce the general process and challenges in developing AI pathology models for PCa. Importantly, we summarize publicly available datasets and open-source codes to facilitate the utilization of existing data and the comparison of the performance of different models to improve future studies.

Estimation of Kinetics Using IMUs to Monitor and Aid in Clinical Decision-Making during ACL Rehabilitation: A Systematic Review.

After an ACL injury, rehabilitation consists of multiple phases, and progress between these phases is guided by subjective visual assessments of activities such as running, hopping, jump landing, etc. Estimation of objective kinetic measures like knee joint moments and GRF during assessment can help physiotherapists gain insights on knee loading and tailor rehabilitation protocols. Conventional methods deployed to estimate kinetics require complex, expensive systems and are limited to laboratory settings. Alternatively, multiple algorithms have been proposed in the literature to estimate kinetics from kinematics measured using only IMUs. However, the knowledge about their accuracy and generalizability for patient populations is still limited. Therefore, this article aims to identify the available algorithms for the estimation of kinetic parameters using kinematics measured only from IMUs and to evaluate their applicability in ACL rehabilitation through a comprehensive systematic review. The papers identified through the search were categorized based on the modelling techniques and kinetic parameters of interest, and subsequently compared based on the accuracies achieved and applicability for ACL patients during rehabilitation. IMUs have exhibited potential in estimating kinetic parameters with good accuracy, particularly for sagittal movements in healthy cohorts. However, several shortcomings were identified and future directions for improvement have been proposed, including extension of proposed algorithms to accommodate multiplanar movements and validation of the proposed techniques in diverse patient populations and in particular the ACL population.

Advancing forensic-based investigation incorporating slime mould search for gene selection of high-dimensional genetic data.

Modern medicine has produced large genetic datasets of high dimensions through advanced gene sequencing technology, and processing these data is of great significance for clinical decision-making. Gene selection (GS) is an important data preprocessing technique that aims to select a subset of feature information to improve performance and reduce data dimensionality. This study proposes an improved wrapper GS method based on forensic-based investigation (FBI). The method introduces the search mechanism of the slime mould algorithm in the FBI to improve the original FBI; the newly proposed algorithm is named SMA_FBI; then GS is performed by converting the continuous optimizer to a binary version of the optimizer through a transfer function. In order to verify the superiority of SMA_FBI, experiments are first executed on the 30-function test set of CEC2017 and compared with 10 original algorithms and 10 state-of-the-art algorithms. The experimental results show that SMA_FBI is better than other algorithms in terms of finding the optimal solution, convergence speed, and robustness. In addition, BSMA_FBI (binary version of SMA_FBI) is compared with 8 binary algorithms on 18 high-dimensional genetic data from the UCI repository. The results indicate that BSMA_FBI is able to obtain high classification accuracy with fewer features selected in GS applications. Therefore, SMA_FBI is considered an optimization tool with great potential for dealing with global optimization problems, and its binary version, BSMA_FBI, can be used for GS tasks.

Prediction of outcomes for rescue cerclage in cervical insufficiency: A multicenter retrospective study.

Purpose: Cervical insufficiency is a significant risk factor for preterm birth and miscarriage during the second trimester; cervical cerclage is a treatment option. This study seeks to evaluate the predictive roles of various clinical factors and to develop predictive models for immediate and long-term outcomes after rescue cerclage. Methods: We conducted a multicenter retrospective study on patients who underwent rescue cerclage at 14 to 26 weeks of gestation. Data were collected from the Electronic Medical Record systems of participating hospitals. Outcomes were dichotomized into immediate failure (inability to maintain pregnancy for at least 48 hours post-cerclage, gestational latency < 2 days) and long-term success (maintenance of pregnancy until at least 28 weeks of gestation). Clinical factors influencing these outcomes were analyzed. Results: The study included 98 patients. Immediate failure correlated with longer prolapsed membrane lengths, elevated C-reactive protein levels at admission, and extended operation time. The successful maintenance of pregnancy until at least 28 weeks was associated with earlier gestational age at diagnosis, negative AmniSure test results, longer lengths of the functional cervix, and smaller cervical dilatation at the time of cerclage. Binary logistic regression models for immediate failure and long-term success exhibited excellent and good predictive abilities, respectively (AUROC = 0.912, 95% CI: 0.834-0.989; and AUROC = 0.872, 95% CI: 0.788-0.956). Conclusion: The developed logistic regression models offer a valuable tool for the prognostic assessment of patients undergoing rescue cerclage, enabling informed clinical decision-making.

Prognostic factors and predictive models for patients with lung large cell neuroendocrine carcinoma: Based on SEER database.

BACKGROUND: Lung Large cell neuroendocrine carcinoma (LCNEC) is a rare, aggressive, high-grade neuroendocrine carcinoma with a poor prognosis, mainly seen in elderly men. To date, we have found no studies on predictive models for LCNEC. METHODS: We extracted data from the Surveillance, Epidemiology, and End Results (SEER) database of confirmed LCNEC from 2010 to 2018. Univariate and multivariate Cox proportional risk regression analyses were used to identify independent risk factors, and then we constructed a novel nomogram and assessed the predictive effectiveness by receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). RESULTS: A total of 2546 patients with LCNEC were included, excluding those diagnosed with autopsy or death certificate, tumor, lymph node, metastasis (TNM) stage, tumor grade deficiency, etc., and finally, a total of 743 cases were included in the study. After univariate and multivariate analyses, we concluded that the independent risk factors were N stage, intrapulmonary metastasis, bone metastasis, brain metastasis, and surgical intervention. The results of ROC curves, calibration curves, and DCA in the training and validation groups confirmed that the nomogram could accurately predict the prognosis. CONCLUSIONS: The nomogram obtained from our study is expected to be a useful tool for personalized prognostic prediction of LCNEC patients, which may help in clinical decision-making.

De-imFAR phase II project: a study protocol for a cluster randomised implementation trial to evaluate the effectiveness of de-implementation strategies to reduce low-value statin prescribing in the primary prevention of cardiovascular disease.

INTRODUCTION: This study aims to reduce potentially inappropriate prescribing (PIP) of statins and foster healthy lifestyle promotion in cardiovascular disease (CVD) primary prevention in low-risk patients. To this end, we will compare the effectiveness and feasibility of several de-implementation strategies developed following the structured design process of the Behaviour Change Wheel targeting key determinants of the clinical decision-making process in CVD prevention. METHODS AND ANALYSIS: A cluster randomised implementation trial, with an additional control group, will be launched, involving family physicians (FPs) from 13 Integrated Healthcare Organisations (IHOs) of Osakidetza-Basque Health Service with non-zero incidence rates of PIP of statins in 2021. All FPs will be exposed to a non-reflective decision assistance strategy based on reminders and decision support tools. Additionally, FPs from two of the IHOs will be randomly assigned to one of two increasingly intensive de-implementation strategies: adding a decision information strategy based on knowledge dissemination and a reflective decision structure strategy through audit/feedback. The target population comprises women aged 45-74 years and men aged 40-74 years with moderately elevated cholesterol levels but no diagnosed CVD and low cardiovascular risk (REGICOR<7.5%), who attend at least one appointment with any of the participating FPs (May 2022-May 2023), and will be followed until May 2024. We use the Reach, Effectiveness, Adoption, Implementation and Maintenance (RE-AIM) framework to evaluate outcomes. The main outcome will be the change in the incidence rate of PIP of statins and healthy lifestyle counselling in the study population 12 and 24 months after FPs' exposure to the strategies. Moreover, FPs' perception of their feasibility and acceptability, and patient experience regarding the quality of care received will be evaluated. ETHICS AND DISSEMINATION: The study was approved by the Basque Country Clinical Research Ethics Committee and was registered in ClinicalTrials.gov (NCT04022850). Results will be disseminated in scientific peer-reviewed journals. TRIAL REGISTRATION NUMBER: NCT04022850.

Causal machine learning for predicting treatment outcomes.

Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes including efficacy and toxicity, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that it allows for estimating individualized treatment effects, so that clinical decision-making can be personalized to individual patient profiles. Causal ML can be used in combination with both clinical trial data and real-world data, such as clinical registries and electronic health records, but caution is needed to avoid biased or incorrect predictions. In this Perspective, we discuss the benefits of causal ML (relative to traditional statistical or ML approaches) and outline the key components and steps. Finally, we provide recommendations for the reliable use of causal ML and effective translation into the clinic.

Integrating Patient Preferences with Guideline-Based Care in Neurogenic Lower Urinary Tract Dysfunction After Spinal Cord Injury.

Individual and social factors are important for clinical decision-making in patients with neurogenic bladder secondary to spinal cord injury (SCI). These factors include the availability of caregivers, social infrastructure, and personal preferences, which all can drive bladder management decisions. These elements can be overlooked in clinical decision-making; therefore, there is a need to elicit and prioritize patient preferences and values into neurogenic bladder care to facilitate personalized bladder management choices. For the purposes of this article, we review the role of guideline-based care and shared decision-making in the SCI population with neurogenic lower urinary tract dysfunction.

Prediction Under Interventions: Evaluation of Counterfactual Performance Using Longitudinal Observational Data.

Predictions under interventions are estimates of what a person's risk of an outcome would be if they were to follow a particular treatment strategy, given their individual characteristics. Such predictions can give important input to medical decision-making. However, evaluating the predictive performance of interventional predictions is challenging. Standard ways of evaluating predictive performance do not apply when using observational data, because prediction under interventions involves obtaining predictions of the outcome under conditions that are different from those that are observed for a subset of individuals in the validation dataset. This work describes methods for evaluating counterfactual performance of predictions under interventions for time-to-event outcomes. This means we aim to assess how well predictions would match the validation data if all individuals had followed the treatment strategy under which predictions are made. We focus on counterfactual performance evaluation using longitudinal observational data, and under treatment strategies that involve sustaining a particular treatment regime over time. We introduce an estimation approach using artificial censoring and inverse probability weighting that involves creating a validation dataset mimicking the treatment strategy under which predictions are made. We extend measures of calibration, discrimination (c-index and cumulative/dynamic AUCt) and overall prediction error (Brier score) to allow assessment of counterfactual performance. The methods are evaluated using a simulation study, including scenarios in which the methods should detect poor performance. Applying our methods in the context of liver transplantation shows that our procedure allows quantification of the performance of predictions supporting crucial decisions on organ allocation.

Clinical decision making when cytology indicates a Warthin tumor.

Warthin tumor (WT) is a benign tumor usually affecting the parotid gland. The main diagnostic tool remains ultrasound combined with fine-needle aspiration cytology (FNAC). This study aims to examine how reliably FNAC indicates WT for clinical decision making regarding surgical versus conservative management. We included all patients who underwent FNAC from a parotid gland lesion between 2016 and 2018 at our institution, and whose FNAC revealed WT suspicion. The FNACs were divided into three groups based on the cytology report: certain, likely, and possible WT. The patients were divided into two groups based on having had either surgery or follow-up. We sent a questionnaire to patients who had not undergone surgery in order to obtain follow-up for a minimum of four years. Altogether, 135 FNAC samples, from 133 tumors and 125 patients, showed signs of WT. Of the 125 patients, 44 (35%) underwent surgery, and 81 (65%) were managed conservatively. Preoperative misdiagnosis in FNAC occurred in three (7%) surgically treated tumors. Their FNACs were reported as possible WTs, but histopathology revealed another benign lesion. In the conservatively treated group, two patients underwent surgery later during the follow-up. Cytological statements of WT were seldom false, and none were malignant. The majority of the patients were only followed-up and rarely required further treatment. A certain or likely diagnosis of WT in the FNAC report by an experienced head and neck pathologist is highly reliable in selecting patients for conservative surveillance.

Decision discovery using clinical decision support system decision log data for supporting the nurse decision-making process.

BACKGROUND: Decision-making in healthcare is increasingly complex; notably in hospital environments where the information density is high, e.g., emergency departments, oncology departments, and psychiatry departments. This study aims to discover decisions from logged data to improve the decision-making process. METHODS: The Design Science Research Methodology (DSRM) was chosen to design an artifact (algorithm) for the discovery and visualization of decisions. The DSRM's different activities are explained, from the definition of the problem to the evaluation of the artifact. During the design and development activities, the algorithm itself is created. During the demonstration and evaluation activities, the algorithm was tested with an authentic synthetic dataset. RESULTS: The results show the design and simulation of an algorithm for the discovery and visualization of decisions. A fuzzy classifier algorithm was adapted for (1) discovering decisions from a decision log and (2) visualizing the decisions using the Decision Model and Notation standard. CONCLUSIONS: In this paper, we show that decisions can be discovered from a decision log and visualized for the improvement of the decision-making process of healthcare professionals or to support the periodic evaluation of protocols and guidelines.

Perspectives in the validation of DEFASE: a paradigm shift in food allergy management.

PURPOSE OF REVIEW: To explore the groundbreaking international consensus on the DEFASE (DEfinition of Food Allergy Severity) project as a revolutionary grading system for IgE-mediated food allergy severity. Against the backdrop of the growing public health challenge posed by food allergy, this article delves into the importance of validating and implementing DEFASE in real-world clinical settings. RECENT FINDINGS: With new therapeutic options available for food allergy, including biologics alongside immunotherapy, it is urgent to properly support clinical decision-making in the management of the disease. The DEFASE score is the first international consensus-based grading system of severity associated with food allergy as a whole disease embracing multidisciplinary perspectives from different stakeholders involved. In its current version, this comprehensive scoring system has been developed to be used in research settings. SUMMARY: The review emphasizes the potential impact of DEFASE on patient outcomes, healthcare management, and resource allocation, underscoring its significance for the allergy scientific community. Future research should focus on internal and external validation of the scoring system, targeting these models to various food allergenic sources, populations, and settings.

Study on decision-making for orthodontic treatment plans based on analytic hierarchy process.

BACKGROUND: Orthodontics is a common treatment for malocclusion and is essential for improving the oral health and aesthetics of patients. Currently, patients often rely on the clinical expertise and professional knowledge of doctors to select orthodontic programs. However, they lack their own objective and systematic evaluation methods to quantitatively compare different programs. Therefore, there is a need for a more comprehensive and quantitative approach to selecting orthodontic treatment plans, aiming to enhance their scientific validity and effectiveness. METHODS: In this study, a combination of the analytic hierarchy process (AHP) and semantic analysis was used to evaluate and compare different orthodontic treatment options. An AHP model and evaluation matrix were established through thorough research and semantic analysis of patient requirements. This model considered various treatment factors. Expert panels were invited to rate these factors using a 1-9 scale. The optimal solution was determined by ranking and comparing different orthodontic treatment plans using the geometric mean method to calculate the weights of each criterion. RESULTS: The research indicates a higher preference for invisible correction compared to other orthodontic solutions, with a weight score that is 0.3923 higher. Factors such as comfort and difficulty of cleaning have been given significant attention. CONCLUSION: The Analytic Hierarchy Process (AHP) method can be utilized to effectively develop orthodontic treatment plans, making the treatment process more objective, scientific, and personalized. The design of this study offers strong decision support for orthodontic treatment, potentially improving orthodontic treatment outcomes in clinical practice and ultimately enhancing oral health and patients' quality of life.

Clinical decision making for VA ECMO weaning in patients with cardiogenic shock A formative qualitative study.

Weaning and liberation from VA ECMO in cardiogenic shock patients comprises a complex process requiring a continuous trade off between multiple clinical parameters. In the absence of dedicated international guidelines, we hypothesized a great heterogeneity in weaning practices among ECMO centers due to a variety in local preferences, logistics, case load and individual professional experience. This qualitative study focused on the appraisal of clinicians' preferences in decision processes towards liberation from VA ECMO after cardiogenic shock while using focus group interviews in 4 large hospitals. The goal was to provide novel and unique insights in daily clinical weaning practices. As expected, we found we a great heterogeneity of weaning strategies among centers and professionals, although participants appeared to find common ground in a clinically straightforward approach to assess the feasibility of ECMO liberation at the bedside. This was shown in a preference for robust, easily accessible parameters such as arterial pulse pressure, stable cardiac index ≥2.1 L/min, VTI LVOT and 'eyeballing' LVEF.

High throughput screening aids clinical decision-making in refractory acute myeloid leukaemia.

BACKGROUND: Despite advances in therapeutics for adverse-risk acute myeloid leukaemia (AML), overall survival remains poor, especially in refractory disease. Comprehensive tumour profiling and pre-clinical drug testing can identify effective personalised therapies. CASE: We describe a case of ETV6-MECOM fusion-positive refractory AML, where molecular analysis and in vitro high throughput drug screening identified a tolerable, novel targeted therapy and provided rationale for avoiding what could have been a toxic treatment regimen. Ruxolitinib combined with hydroxyurea led to disease control and enhanced quality-of-life in a patient unsuitable for intensified chemotherapy or allogeneic stem cell transplantation. CONCLUSION: This case report demonstrates the feasibility and role of combination pre-clinical high throughput screening to aid decision making in high-risk leukaemia. It also demonstrates the role a JAK1/2 inhibitor can have in the palliative setting in select patients with AML.

Modelo de riesgo de mortalidad a largo plazo en pacientes con infección atendidos por servicios de emergencias prehospitalarios / Long-term risk of death in patients with infection attended by prehospital emergency services

Objetivo: Diseñar y validar un modelo de riesgo con variables determinadas a nivel prehospitalario para predecir el riesgo de mortalidad a largo plazo (1 año) en pacientes con infección. Métodos: Estudio multicéntrico, observacional prospectivo, sin intervención, en pacientes adultos con sospecha infección atendidos por unidades de soporte vital avanzado y trasladados a 4 hospitales españoles entre el 1 de junio de 2020 y el 30 de junio de 2022. Se recogieron variables demográficas, fisiológicas, clínicas y analíticas. Se construyó y validó un modelo de riesgo para la mortalidad a un año usando una regresión de Cox.Resultados: Se incluyeron 410 pacientes, con una tasa de mortalidad acumulada al año del 49%. La tasa de diagnóstico de sepsis (infección e incremento sobre el SOFA basal $ 2 puntos) fue del 29,2% en supervivientes frente a un 56,7% en no supervivientes. El modelo predictivo obtuvo un área bajo la curva de la característica operativa del receptor para la mortalidad a un año fue de 0,89, e incluyó: edad, institucionalización, índice de comorbilidad de Charlson ajustado por edad, presión parcial de dióxido de carbono, potasio, lactato, nitrógeno ureico en sangre, creatinina, saturación en relación con fracción inspirada de oxígeno y diagnóstico de sepsis.Conclusiones: El modelo desarrollado con variables epidemiológicas, analíticas y clínicas mostró una excelente capacidad predictiva, y permitió identificar desde el primer contacto del paciente con el sistema sanitario, a modo de evento centinela, casos de alto riesgo.(AU)

Objectives: To develop and validate a risk model for 1-year mortality based on variables available from earlyprehospital emergency attendance of patients with infection. Methods: Prospective, observational, noninterventional multicenter study in adults with suspected infection transferred to 4 Spanish hospitals by advanced life-support ambulances from June 1, 2020, through June 30, 2022. We collected demographic, physiological, clinical, and analytical data. Cox regression analysis was used to develop and validate a risk model for 1-year mortality. Results: Four hundred ten patients were enrolled (development cohort, 287; validation cohort, 123). Cumulative mortality was 49% overall. Sepsis (infection plus a Sepsis-related Organ Failure Assessment score of 2 or higher) was diagnosed in 29.2% of survivors vs 56.7% of nonsurvivors. The risk model achieved an area under the receiver operating characteristic curve of 0.89 for 1-year mortality. The following predictors were included in the model: age; institutionalization; age-adjusted Charlson comorbidity index; PaCO2; potassium, lactate, urea nitrogen, and creatinine levels; fraction of inspired oxygen; and diagnosed sepsis. Conclusions: The model showed excellent ability to predict 1-year mortality based on epidemiological, analytical, andclinical variables, identifying patients at high risk of death soon after their first contact with the health care system.(AU)