Clinical Tasks Research Articles

Physician barriers and dilemmas in the execution of clinical trials impacting decision-making in the DAHANCA 35 proton therapy trial for head and neck cancer

BackgroundPhysicians manage multiple obligations, providing best-practice treatment and patient- centred care in the standard treatment pathway while contributing to clinical trials simultaneously. These multifaceted responsibilities may introduce barriers and dilemmas to clinical trial execution, potentially impacting the clinical trial decision- making process. This study explores physicians’ barriers and dilemmas in executing clinical trials and the impact on clinical trial decision-making. MethodQualitative semi-structured interviews were conducted with experienced oncologists. Moreover, participant observations were performed during clinical encounters involving discussions about clinical trials. The analysis followed a structured approach: (1) transcription of data, (2) inductive text coding, (3) exploration of patterns, and (4) interpretation, leading to the results. The results were discussed and validated by the study participants. ResultsThe results comprise (1) a description of the clinical practice, which presents the setting of clinical trial execution; (2) results regarding physicians’ barriers and dilemmas in executing clinical trials, leading to (3) the impact on clinical trial decision- making. The results involve barriers to time constraints for clinical trial tasks, dilemmas emerging from trial requirements or deviations from standard guidelines, and challenges with providing sufficient trial communication and adequate decision-making support, balancing between a paternalistic approach and respecting patient autonomy. ConclusionThe demanding obligations of clinical practice constitute a complex setting for executing clinical trials, resulting in numerous barriers and dilemmas that impact the decision-making process in clinical trials. The study emphasises the need for tailored clinical trial decision-making interventions to facilitate supportive, informed, and non-directive clinical trial decision-making.

A multi-center study on the adaptability of a shared foundation model for electronic health records

Foundation models are transforming artificial intelligence (AI) in healthcare by providing modular components adaptable for various downstream tasks, making AI development more scalable and cost-effective. Foundation models for structured electronic health records (EHR), trained on coded medical records from millions of patients, demonstrated benefits including increased performance with fewer training labels, and improved robustness to distribution shifts. However, questions remain on the feasibility of sharing these models across hospitals and their performance in local tasks. This multi-center study examined the adaptability of a publicly accessible structured EHR foundation model (FMSM), trained on 2.57 M patient records from Stanford Medicine. Experiments used EHR data from The Hospital for Sick Children (SickKids) and Medical Information Mart for Intensive Care (MIMIC-IV). We assessed both adaptability via continued pretraining on local data, and task adaptability compared to baselines of locally training models from scratch, including a local foundation model. Evaluations on 8 clinical prediction tasks showed that adapting the off-the-shelf FMSM matched the performance of gradient boosting machines (GBM) locally trained on all data while providing a 13% improvement in settings with few task-specific training labels. Continued pretraining on local data showed FMSM required fewer than 1% of training examples to match the fully trained GBM’s performance, and was 60 to 90% more sample-efficient than training local foundation models from scratch. Our findings demonstrate that adapting EHR foundation models across hospitals provides improved prediction performance at less cost, underscoring the utility of base foundation models as modular components to streamline the development of healthcare AI.

Prospective Memory in People With Chronic Respiratory Diseases

Goal: The efficiency of the respiratory system determines patients’ good physical condition and proper functioning of the brain. The failure of this system is associated with the processes of physiological aging or diseases such as chronic obstructive pulmonary disease (COPD). Reducing the transport of oxygen to the brain directly impairs mental performance. Prospective memory (PM) is a set of processes or abilities that enable the formulation, storage and implementation of goals and intentions in the future. It’s assumed that the type of disease and the degree of respiratory failure affect mental functions. Therefore the main aim of the study was to determine the general characteristics of PM functioning in people with selected respiratory diseases. Method: The study involved 116 adults (mean age = 52.4 years; SD = 6.41) diagnosed with asthma (N = 30), COPD (N = 32), controls with allergic rhinitis (N = 27) and healthy controls (N = 27). There were no statistically significant differences in education and age between the groups. The following methods were used: Prospective-Retrospective Memory Questionnaire, Rey-Osterrieth Complex Figure Test, WAIS-R Digit Span, Trail Making Test, Beck Depression Inventory and a clinical task based on The Cambridge Prospective Memory Test (CAMPROMPT). Results: People with COPD, compared to control groups and patients with asthma, scored lower on tests assessing cognitive functioning, including prospective memory (PM). Respiratory efficiency has been identified as the strongest predictor of PM dysfunction in patients with COPD and asthma. Conclusion: Respiratory failure poses a risk of serious cognitive disorders associated with respiratory indicators. Patients diagnosed with asthma or COPD are required to actively engage in therapy, including anticipating situations that may lead to exacerbations. However, the results suggest that individuals with COPD may struggle to meet the therapeutic demands placed upon them.

Value-led participatory design approach for improving public health clinic services

IMPACT This study details how to drive transformative collaboration with a health bureau to implement transformative tasks in public health clinic (PHC) using service design. Value-led participatory design is adopted to identify and address key challenges, enhance decision-making processes, and generate a new elevation model for public health service delivery. The article highlights the importance of continuous evaluation and adaptation of services based on stakeholder feedback and evolving community needs, emphasising the dynamic nature of healthcare service improvement. The insights gained from this collaboration provide practical solutions for common challenges faced by public health systems in various contexts.

Revealing the hidden vulnerabilities of psychiatrists: Insights from the Romanian health system. A sociological and empirical study

It is well known that the medical and sociological literature abounds in materials that present a whole series of categories of patients as being part of vulnerable population categories. Medical professionals, and doctors, in particular, are seen as parts of the therapeutic relationship holding power, also leading to an image of a 'privileged' social group. Although this idea is a predominant one within classical sociological theories, but also within the traditional image of the doctor, if we look in a certain context, such as the functional one of the Romanian health system, we can reveal another social image of today's psychiatrist. The present work wants to outline such a picture, starting from theoretical landmarks of medical sociology and observing a whole series of social realities identified through empirical research based on ethnographic evidence, but also on analyses of publicly available secondary data. The conceptualization of the vulnerability of psychiatrists will be highlighted within the complex interactions within the health system, which is in a problematic relationship with the entire social system. Finally, we want to undertake exploratory research on the specific vulnerabilities of psychiatrists (some vulnerabilities characterizing the entire professional body of doctors): complex clinical tasks, limited collaboration with other categories of doctors, limitation of resources specific to the profession (paraclinical and laboratory examinations), rigid control, extensive and overlapping of different control bodies, geographical isolation from other medical institutions and the emotional impact in the face of patients' suffering. The vulnerability of doctors overlaps, but also inverts, that of patients, accentuating a whole series of already existing problems. Defining the group of psychiatrists as a vulnerable social group generates the need to identify answers for a problem that we consider fundamental: difficulties arising in the complex of mental health care can lead to a real social problem.

TDC-2: Multimodal Foundation for Therapeutic Science.

Therapeutics Data Commons (tdcommons.ai) is an open science initiative with unified datasets, AI models, and benchmarks to support research across therapeutic modalities and drug discovery and development stages. The Commons 2.0 (TDC-2) is a comprehensive overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new multimodal tasks and model frameworks, and comprehensive benchmarks. TDC-2 introduces over 1,000 multimodal datasets spanning approximately 85 million cells, pre-calculated embeddings from 5 state-of-the-art single-cell models, and a biomedical knowledge graph. TDC-2 drastically expands the coverage of ML tasks across therapeutic pipelines and 10+ new modalities, spanning but not limited to single-cell gene expression data, clinical trial data, peptide sequence data, peptidomimetics protein-peptide interaction data regarding newly discovered ligands derived from AS-MS spectroscopy, novel 3D structural data for proteins, and cell-type-specific protein-protein interaction networks at single-cell resolution. TDC-2 introduces multimodal data access under an API-first design using the model-view-controller paradigm. TDC-2 introduces 7 novel ML tasks with fine-grained biological contexts: contextualized drug-target identification, single-cell chemical/genetic perturbation response prediction, protein-peptide binding affinity prediction task, and clinical trial outcome prediction task, which introduce antigen-processing-pathway-specific, cell-type-specific, peptide-specific, and patient-specific biological contexts. TDC-2 also releases benchmarks evaluating 15+ state-of-the-art models across 5+ new learning tasks evaluating models on diverse biological contexts and sampling approaches. Among these, TDC-2 provides the first benchmark for context-specific learning. TDC-2, to our knowledge, is also the first to introduce a protein-peptide binding interaction benchmark.

Improving clinical abbreviation sense disambiguation using attention-based Bi-LSTM and hybrid balancing techniques in imbalanced datasets.

Clinical abbreviations pose a challenge for clinical decision support systems due to their ambiguity. Additionally, clinical datasets often suffer from class imbalance, hindering the classification of such data. This imbalance leads to classifiers with low accuracy and high error rates. Traditional feature-engineered models struggle with this task, and class imbalance is a known factor that reduces the performance of neural network techniques. This study proposes an attention-based bidirectional long short-term memory (Bi-LSTM) model to improve clinical abbreviation disambiguation in clinical documents. We aim to address the challenges of limited training data and class imbalance by employing data generation techniques like reverse substitution and data augmentation with synonym substitution. We utilise a Bi-LSTM classification model with an attention mechanism to disambiguate each abbreviation. The model's performance is evaluated based on accuracy for each abbreviation. To address the limitations of imbalanced data, we employ data generation techniques to create a more balanced dataset. The evaluation results demonstrate that our data balancing technique significantly improves the model's accuracy by 2.08%. Furthermore, the proposed attention-based Bi-LSTM model achieves an accuracy of 96.09% on the UMN dataset, outperforming state-of-the-art results. Deep neural network methods, particularly Bi-LSTM, offer promising alternatives to traditional feature-engineered models for clinical abbreviation disambiguation. By employing data generation techniques, we can address the challenges posed by limited-resource and imbalanced clinical datasets. This approach leads to a significant improvement in model accuracy for clinical abbreviation disambiguation tasks.

Ketogenic Diet for Type I Diabetes Mellitus. Literature Review and Clinical Experience

To date, treating type I diabetes mellitus (T1D) is a difficult clinical task that is based, from the traditional point of view, exclusively on adjusting an insulin dose and monitoring a daily carbohydrate intake. Dietary changes are not considered a type of treatment in T1D patients yet, although this autoimmune disease is accompanied by disorders of carbohydrate metabolism. The article explores the international experience in the use of a low-carbohydrate diet and the features of disease development when putting patients into ketosis on a ketogenic diet. Article discusses the clinical experience obtained during T1D patient management, including ketogenic diet and mitochondrial support, at the clinic “PlanetaMed”. In addition, the article describes the case reports and case studies. According to the clinical experience of “PlanetaMed” specialists, the use of a ketogenic diet results in a decreasing blood glucose level in almost all cases. The average dose of injected insulin was 22.8 units before the ketogenic diet and 6,625 units during the ketogenic diet. The absolute decrease was 16.205 units, and the relative decrease was 70.9%. At the same time, the concentration level of glucose decreased by 39.2%. The decrease in blood glucose level and the injected insulin dose were connected (correlation coefficient: 0.76). Therefore, the studies have shown a significant positive impact of a ketogenic diet on the treatment of T1D patients.

КЛИНИЧЕСКОЕ НАБЛЮДЕНИЕ ГАНГРЕНОЗНОЙ ПИОДЕРМИИ У ДЕВУШКИ-ПОДРОСТКА

Pyoderma gangrenosum (PG) is the most severe type of pyoderma and is extremely rare among children and adolescents. Authors represent a clinical case of PG in a 14 years old female adolescent characterized by multiple sharply painful ulcerative defects with a pronounced tendency to peripheral growth. PG had arisen and proceeded further during the postoperative period against the background of iron deficiency anemia, chronic nonspecific nonulcerative colitis and a dysfunctional state of humoral immunity. Making a diagnosis, conducting differential diagnostics, identifying provoking factors, searching for concomitant somatic pathology, using a set of therapeutic measures made possible eliminating the PG clinical manifestations completely though development of the preventive measures and determination of the prognosis of the disease are difficult clinical tasks for pediatric practitioners nowadays.

TEE4EHR: Transformer event encoder for better representation learning in electronic health records

Irregular sampling of time series in electronic health records (EHRs) is one of the main challenges for developing machine learning models. Additionally, the pattern of missing values in certain clinical variables is not at random but depends on the decisions of clinicians and the state of the patient. Point process is a mathematical framework for analyzing event sequence data consistent with irregular sampling patterns. Our model, TEE4EHR, is a transformer event encoder (TEE) with point process loss that encodes the pattern of laboratory tests in EHRs. The utility of our TEE has been investigated in various benchmark event sequence datasets. Additionally, we conduct experiments on two real-world EHR databases to provide a more comprehensive evaluation of our model. Firstly, in a self-supervised learning approach, the TEE is jointly learned with an existing attention-based deep neural network, which gives superior performance in negative log-likelihood and future event prediction. Besides, we propose an algorithm for aggregating attention weights to reveal the events’ interactions. Secondly, we transfer and freeze the learned TEE to the downstream task for the outcome prediction, where it outperforms state-of-the-art models for handling irregularly sampled time series. Furthermore, our results demonstrate that our approach can improve representation learning in EHRs and be useful for clinical prediction tasks.

End-to-end pseudonymization of fine-tuned clinical BERT models

Many state-of-the-art results in natural language processing (NLP) rely on large pre-trained language models (PLMs). These models consist of large amounts of parameters that are tuned using vast amounts of training data. These factors cause the models to memorize parts of their training data, making them vulnerable to various privacy attacks. This is cause for concern, especially when these models are applied in the clinical domain, where data are very sensitive. Training data pseudonymization is a privacy-preserving technique that aims to mitigate these problems. This technique automatically identifies and replaces sensitive entities with realistic but non-sensitive surrogates. Pseudonymization has yielded promising results in previous studies. However, no previous study has applied pseudonymization to both the pre-training data of PLMs and the fine-tuning data used to solve clinical NLP tasks. This study evaluates the effects on the predictive performance of end-to-end pseudonymization of Swedish clinical BERT models fine-tuned for five clinical NLP tasks. A large number of statistical tests are performed, revealing minimal harm to performance when using pseudonymized fine-tuning data. The results also find no deterioration from end-to-end pseudonymization of pre-training and fine-tuning data. These results demonstrate that pseudonymizing training data to reduce privacy risks can be done without harming data utility for training PLMs.

Identify and mitigate bias in electronic phenotyping: A comprehensive study from computational perspective

Electronic phenotyping is a fundamental task that identifies the special group of patients, which plays an important role in precision medicine in the era of digital health. Phenotyping provides real-world evidence for other related biomedical research and clinical tasks, e.g., disease diagnosis, drug development, and clinical trials, etc. With the development of electronic health records, the performance of electronic phenotyping has been significantly boosted by advanced machine learning techniques. In the healthcare domain, precision and fairness are both essential aspects that should be taken into consideration. However, most related efforts are put into designing phenotyping models with higher accuracy. Few attention is put on the fairness perspective of phenotyping. The neglection of bias in phenotyping leads to subgroups of patients being underrepresented which will further affect the following healthcare activities such as patient recruitment in clinical trials. In this work, we are motivated to bridge this gap through a comprehensive experimental study to identify the bias existing in electronic phenotyping models and evaluate the widely-used debiasing methods’ performance on these models. We choose pneumonia and sepsis as our phenotyping target diseases. We benchmark 9 kinds of electronic phenotyping methods spanning from rule-based to data-driven methods. Meanwhile, we evaluate the performance of the 5 bias mitigation strategies covering pre-processing, in-processing, and post-processing. Through the extensive experiments, we summarize several insightful findings from the bias identified in the phenotyping and key points of the bias mitigation strategies in phenotyping.

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry

Patient perspectives on the role of orthopedic nurse practitioners: a cross-sectional study

BackgroundThe inclusion of nurse practitioners (NPs) specializing in orthopedics shows potential for improving the quality of care for orthopedic patients. A critical aspect of assessing the feasibility and acceptance of introducing NPs into orthopedic settings involves understanding patients’ perspectives on this role. This study aims to explore the receptiveness of orthopedic patients to treatment by orthopedic Nurse Practitioners (NPs). Additionally, it investigates potential associations between patients’ willingness to engage with NPs, their familiarity with the NPs role, perceptions of nursing, and satisfaction with orthopedic nursing care.MethodsThis cross-sectional study involved patients admitted to an orthopedic department in a central Israeli hospital between January and February 2023. Data was collected using a questionnaire consisting of five sections, validated by content experts. Statistical analyses, performed using SPSS, included descriptive statistics, independent samples t-tests, Pearson correlations, and linear regression.ResultsOrthopedic patient participants demonstrated a moderate willingness to undergo treatment by orthopedic NPs, with over two-thirds expressing strong openness. Patients displayed a high willingness for NPs to engage in various clinical tasks, albeit showing lesser enthusiasm for medication management and preoperative evaluation. Positive attitudes towards nurses and familiarity with the NP’s role emerged as significant predictors of patient receptiveness to NPs’ treatment.ConclusionPatient acceptance of orthopedic NPs varies across different aspects of care. While there is overall willingness to receive care from NPs, these nuanced preferences should be considered when implementing NPs in orthopedic settings. Awareness and positive perceptions play crucial roles in shaping patients’ willingness to receive care from these NPs.Trial registrationThe research doesn’t report the results of a health care intervention.

Experiences of medical students and faculty regarding the use of long case as a formative assessment method at a tertiary care teaching hospital in a low resource setting: a qualitative study

IntroductionThe long case is used to assess medical students’ proficiency in performing clinical tasks. As a formative assessment, the purpose is to offer feedback on performance, aiming to enhance and expedite clinical learning. The long case stands out as one of the primary formative assessment methods for clinical clerkship in low-resource settings but has received little attention in the literature.ObjectiveTo explore the experiences of medical students and faculty regarding the use of the Long Case Study as a formative assessment method at a tertiary care teaching hospital in a low-resource setting.MethodologyA qualitative study design was used. The study was conducted at Makerere University, a low-resource setting. The study participants were third- and fifth-year medical students as well as lecturers. Purposive sampling was utilized to recruit participants. Data collection comprised six Focus Group Discussions with students and five Key Informant Interviews with lecturers. The qualitative data were analyzed by inductive thematic analysis.ResultsThree themes emerged from the study: ward placement, case presentation, and case assessment and feedback. The findings revealed that students conduct their long cases at patients’ bedside within specific wards/units assigned for the entire clerkship. Effective supervision, feedback, and marks were highlighted as crucial practices that positively impact the learning process. However, challenges such as insufficient orientation to the long case, the super-specialization of the hospital wards, pressure to hunt for marks, and inadequate feedback practices were identified.ConclusionThe long case offers students exposure to real patients in a clinical setting. However, in tertiary care teaching hospitals, it’s crucial to ensure proper design and implementation of this practice to enable students’ exposure to a variety of cases. Adequate and effective supervision and feedback create valuable opportunities for each learner to present cases and receive corrections.

Multi-Instance Multi-Task Learning for Joint Clinical Outcome and Genomic Profile Predictions From the Histopathological Images.

With the remarkable success of digital histopathology and the deep learning technology, many whole-slide pathological images (WSIs) based deep learning models are designed to help pathologists diagnose human cancers. Recently, rather than predicting categorical variables as in cancer diagnosis, several deep learning studies are also proposed to estimate the continuous variables such as the patients' survival or their transcriptional profile. However, most of the existing studies focus on conducting these predicting tasks separately, which overlooks the useful intrinsic correlation among them that can boost the prediction performance of each individual task. In addition, it is sill challenge to design the WSI-based deep learning models, since a WSI is with huge size but annotated with coarse label. In this study, we propose a general multi-instance multi-task learning framework (HistMIMT) for multi-purpose prediction from WSIs. Specifically, we firstly propose a novel multi-instance learning module (TMICS) considering both common and specific task information across different tasks to generate bag representation for each individual task. Then, a soft-mask based fusion module with channel attention (SFCA) is developed to leverage useful information from the related tasks to help improve the prediction performance on target task. We evaluate our method on three cancer cohorts derived from the Cancer Genome Atlas (TCGA). For each cohort, our multi-purpose prediction tasks range from cancer diagnosis, survival prediction and estimating the transcriptional profile of gene TP53. The experimental results demonstrated that HistMIMT can yield better outcome on all clinical prediction tasks than its competitors.

ChatGPT-4 Performs Clinical Information Retrieval Tasks Using Consistently More Trustworthy Resources Than Does Google Search for Queries Concerning the Latarjet Procedure

PurposeTo assess the ability for ChatGPT-4, an automated Chatbot powered by artificial intelligence (AI), to answer common patient questions concerning the Latarjet procedure for patients with anterior shoulder instability and compare this performance to Google Search Engine. MethodsUsing previously validated methods, a Google search was first performed using the query “Latarjet.” Subsequently, the top ten frequently asked questions (FAQs) and associated sources were extracted. ChatGPT-4 was then prompted to provide the top ten FAQs and answers concerning the procedure. This process was repeated to identify additional FAQs requiring discrete-numeric answers to allow for a comparison between ChatGPT-4 and Google. Discrete, numeric answers were subsequently assessed for accuracy based on the clinical judgement of two fellowship-trained sports medicine surgeons blinded to search platform. ResultsMean (±standard deviation) accuracy to numeric-based answers were 2.9±0.9 for ChatGPT-4 versus 2.5±1.4 for Google (p=0.65). ChatGPT-4 derived information for answers only from academic sources, which was significantly different from Google Search Engine (p=0.003), which used only 30% academic sources and websites from individual surgeons (50%) and larger medical practices (20%). For general FAQs, 40% of FAQs were found to be identical when comparing ChatGPT-4 and Google Search Engine. In terms of sources used to answer these questions, ChatGPT-4 again used 100% academic resources, while Google Search Engine used 60% academic resources, 20% surgeon personal websites, and 20% medical practices (p=0.087). ConclusionChatGPT-4 demonstrated the ability to provide accurate and reliable information about the Latarjet procedure in response to patient queries, using multiple academic sources in all cases. This was in contrast to Google Search Engine, which more frequently used single surgeon and large medical practice websites. Despite differences in the resources accessed to perform information retrieval tasks, the clinical relevance and accuracy of information provided did not significantly differ between ChatGPT-4 and Google Search Engine.

Skin Cancer Segmentation using CNN

This groundbreaking research introduces a comprehensive strategy for advancing medical image segmentation, merging two pivotal concepts to significantly enhance both the accuracy and efficiency of the segmentation process. The first component of our approach involves the integration of polar transformations as a preprocessing step applied to the original dataset. This transformative technique is designed to address the challenges associated with segmenting single structures of elliptical shape in medical images, such as organs (e.g., heart and kidneys), skin lesions, polyps, and various abnormalities. By centering the polar transformation on the object's focal point, a reduction in dimensionality is achieved, coupled with a distinct separation of segmentation and localization tasks. Two distinct methodologies for selecting an optimal polar origin are proposed: one involving estimation through a segmentation neural network trained on non-polar images, and the other employing a dedicated neural network trained to pre dict the optimal origin. The second key element of our approach is around the integration of the DoubleU-Net architecture, a powerful encoder-decoder model specifically designed for the task of semantic image segmentation. DoubleU- Net is a group of two U-Net architectures, each with a specific purpose. The initial U-Net is pre-trained on VGG-19 as the encoder and uses features learned from ImageNet to provide efficient information transfer. In order to store more semantic information and content, a second U-Net was added to the base to enhance the capabilities of the network. Join Atrous Spatial Pyramid Pooling (ASPP) to develop network data extraction content. The combination of DoubleU-Net architecture and joint transformation as a step forward shows good segmentation performance in different clinical tasks, including liver segmentation, polyp detection vision, skin segmentation, and epicardial fat tissue segmentation. It shows that various medical projects, including various diagnostic methods such as colonoscopy, dermoscopy, microscopy, have a positive impact on the plan. More importantly, the method performs well in difficult cases, such as the segmentation of small and flat polyps in CVC-ClinicDB and the 2015 subset of the MICCAI Automated Polyp Detection dataset. The results demonstrate the accuracy and generality of the combination, making it the best way to evaluate medical images in context; Our study has revealed a new method of skin cancer diagnosis that combines the power of deep learning with innovation. Advanced technology. The combination of dual U-Net architecture and polar coordinate transformation not only improves the accuracy of classification of lesions but also improves the robustness of the model to changes in image features. This study contributes to the development of computer-aided diagnostic systems for early diagnosis. Experimental results show that our method provides good accuracy, sensitivity, and specificity in detecting malignant and benign tumors. Additionally, we are conducting ablation studies to determine the contribution of each presentation and treatment of skin cancer to ultimately benefit patients and determine these benefits. We also apply the transformation of the joint as the first step to improve the discrimination ability of the model. This mechanical change effectively reduces the impact caused by changes in wound size, shape, and direction by displaying the original image of the polar system. By standardizing the representation of skin diseases, polar transformation improves the model's ability to generalize across different data sets and improves overall performance.

HIV Activist Identity, Commitment, and Orientation Scale (HAICOS): Psychometric Evaluation to Assess Clinician's Propensity Towards HIV Activism in Malaysia.

HIV activism has a long history of advancing HIV treatment and is critical in dismantling HIV-related stigma. This study evaluated the psychometric quality of the HIV Activist Identity, Commitment, and Orientation Scale (HAICOS) to assess clinicians' propensity towards HIV activism in Malaysia. From November 2022 to March 2023, 74 general practitioners and primary care physicians in Malaysia participated in the study. The exploratory factor analysis (EFA) extracted an internally consistent three-factor solution with 13 items: (1) HIV activist identity and commitment, orientation towards (2) day-to-day, and (3) structural activism. The Cronbach's alpha value was 0.91, and intra-class correlation coefficient for test-retest reliability was 0.86. Stigma-related (prejudice and discrimination intent) and clinical practice (comfort in performing clinical tasks with key populations and knowledge about HIV pre-exposure prophylaxis) measures supported the construct validity of the scale. The study provided concise, structurally valid, and reliable measures to evaluate HIV activism among clinicians.

Why Are Explainable AI Methods for Prostate Lesion Detection Rated Poorly by Radiologists?

Deep learning offers significant advancements in the accuracy of prostate identification and classification, underscoring its potential for clinical integration. However, the opacity of deep learning models presents interpretability challenges, critical for their acceptance and utility in medical diagnosis and detection. While explanation methods have been proposed to demystify these models, enhancing their clinical viability, the efficacy and acceptance of these methods in medical tasks are not well documented. This pilot study investigates the effectiveness of deep learning explanation methods in clinical settings and identifies the attributes that radiologists consider crucial for explainability, aiming to direct future enhancements. This study reveals that while explanation methods can improve clinical task performance by up to 20%, their perceived usefulness varies, with some methods being rated poorly. Radiologists prefer explanation methods that are robust against noise, precise, and consistent. These preferences underscore the need for refining explanation methods to align with clinical expectations, emphasizing clarity, accuracy, and reliability. The findings highlight the importance of developing explanation methods that not only improve performance but also are tailored to meet the stringent requirements of clinical practice, thereby facilitating deeper trust and a broader acceptance of deep learning in medical diagnostics.