Expert Physicians Research Articles

Deep Machine Learning for Automatic Segmentation of the Pancreatic Parenchyma and its hypo- and hypervascular lesions on CT Images

Objective of the study. To develop and evaluate the effectiveness of a technology for segmenting the pancreatic parenchyma and its hyper- and hypovascular lesions on abdominal computed tomography (CT) scans using deep machine learning.Materials and methods. CT scans from the database of the A.V. Vishnevsky National Medical Research Center of Surgery were used for training and testing the algorithms – a total number of approximately 150 studies (arterial and venous phases). A test dataset of 46 anonymized CT scans (arterial and venous phases) was prepared for validation of the obtained algorithms, independently assessed by expert physicians. The primary segmentation neural network used is nn-UNet (M. Antonelli et al., 2022).Results. The average accuracy of the test dataset for the model determining segmentation masks of the pancreas on CT images had an AUC of 0.8 for the venous phase and 0.85 for the arterial phase. The segmentation masks of pancreatic formations had an AUC of 0.6.Conclusion. Automated segmentation of the pancreatic parenchyma structure using deep machine learning technologies demonstrated high accuracy. However, the segmentation of hypo- and hypervascular pancreatic lesions requires improvement. The overlap of the masks showed a rather low result, but in all cases, the location of the pathological formation was correctly identified by the algorithm. Enhancing the training dataset and the algorithm used could increase the accuracy of the algorithm.No false negative results were obtained when detecting pancreatic formations; in all cases, the INS detected “suspicious” areas of the pancreatic parenchyma. This can help reduce the omission of pancreatic pathologies in CT scans, and their further assessment can be carried out by the radiologist himself.

Women's Relationships With Healthcare and Providers: The Role of Weight Stigma in Healthcare and Weight Bias Internalization.

Weight stigma (devaluation due to body weight) in healthcare is common and influences one's engagement in healthcare, health behaviors, and relationship with providers. Positive patient-provider relationships (PPR) are important for one's healthcare engagement and long-term health. To date, no research has yet investigated whether weight bias internalization (self-stigma due to weight; WBI) moderates the effect of weight stigma on the PPR. We predict that weight stigma in healthcare is negatively associated with (i) trust in physicians, (ii) physician empathy, (iii) autonomy and competence when interacting with physicians, and (iv) perceived physician expertise. We also predict that those with high levels of WBI would have the strongest relationship between experiences of weight stigma and PPR outcomes. We recruited women (N = 1,114) to complete a survey about weight stigma in healthcare, WBI and the previously cited PPR outcomes. Weight stigma in healthcare and WBI were associated with each of the PPR outcomes when controlling for age, BMI, education, income, race, and ethnicity. The only exception was that WBI was not associated with trust in physicians. The hypothesis that WBI would moderate the effect of weight stigma in healthcare on PPR outcomes was generally not supported. Overall, this research highlights how weight stigma in healthcare as well as one's own internalization negatively impact PPRs, especially how autonomous and competent one feels with their provider which are essential for one to take an active role in their health and healthcare.

Performance and Clinical Impact of Radiomics and 3D-CNN Models for the Diagnosis of Neurodegenerative Parkinsonian Syndromes on 18 F-FDOPA PET.

The aim of this study was to compare the performance and added clinical value of a semiautomated radiomics model and an automated 3-dimensinal convolutional neural network (3D-CNN) model for diagnosing neurodegenerative parkinsonian syndromes on 18 F-FDOPA PET images. This 2-center retrospective study included 687 patients with motor symptoms consistent with parkinsonian syndrome. All patients underwent 18 F-FDOPA brain PET scans, acquired on 3 PET systems from 2 different hospitals, and classified as pathological or nonpathological (by an expert nuclear physician). Artificial intelligence models were trained to replicate this medical expert's classification using 2 pipelines. The radiomics pipeline was semiautomated and involved manually segmenting the bilateral caudate and putamen nuclei; 43 radiomic features were extracted and combined using the support vector machine method. The deep learning pipeline was fully automatic and used a 3D-CNN model. Both models were trained on 417 patients and tested on an internal (n = 100) and an external (n = 170) test set. The final models' performance was evaluated using balanced accuracy and compared with that of a junior medical expert and nonexpert nuclear physician. On the internal test set, the 3D-CNN model outperformed the radiomic model with a balanced accuracy of 99% (vs 96%). It led to diagnostic performance similar to that of a junior medical expert (only 1 in 100 patients misclassified by both). On the external test set from a less experienced hospital, the 3D-CNN model allowed physicians to correctly reclassify the diagnosis of 10 out 170 patients (6%). The developed 3D-CNN model can automatically diagnose neurodegenerative parkinsonian syndromes, also reducing diagnostic errors by 6% in less-experienced hospitals.

Share If You Believe, Comment If You Doubt: The Effect of Source of Information, Trust, and Belief in Conspiracy Theories on Engagement with Facebook Posts.

This study examines the effect of one of three sources of information: a politician (authority figure), a physician (expert), and an ordinary person (non-expert) who appeared in a personal story related to a controversial issue (COVID-19 vaccination) on Facebook, on the willingness to engage with it. Using a between-subjects experiment (N = 848) conducted among Israeli adults (18 and older), we found a higher likelihood of sharing the story in interpersonal conversations than in other types of communications, regardless of the source that appeared in the story. However, respondents with high levels of institutional trust preferred sharing a politician's story, while conspiracy believers tended to comment on an ordinary person's story. The findings of the different patterns of communication behavior among conspiracy believers and people with high trust in political institutes contribute to our understanding of the mechanisms underlying the spread of misinformation in the digital age and during times of crisis.

Fractures anciennes du scaphoïde. La difficile question de l’imputabilité

Scaphoid fractures are difficult fractures to diagnose. They are often revealed at a late stage, or even at a very early stage of pseudarthrosis. Pseudarthroses may be asymptomatic and the fracture will be revealed when a new, more recent trauma occurs. For the expert physician, the question of a previous condition or pathological predisposition must be posed. Using two clinical cases of an old scaphoid fracture revealed by a recent trauma, the authors propose to study clinical and radiological elements in order to analyze imputability and discuss a possible previous condition or pathological predisposition.

Impact of text-only versus large text-and-picture alcohol warning formats: A functional magnetic resonance imaging study in French young male drinkers.

Although the World Health Organization recommends visible and clear warning labels about the risks of alcohol consumption on containers and advertising, many of the currently used labels are too small to be visible. This study investigated the brain activity (using fMRI) and alcohol consumption intentions of French young men exposed to two warning formats displayed on alcoholic beverage advertisements: a small Text-only Alcohol Warning (TAW) currently used in many countries, and a larger text-and-picture alcohol warning (PAW). Seventy-four eligible 18-25-year-old male drinkers completed a face-to-face individual visit with a physician expert in addiction medicine. This was followed by the fMRI session during which they viewed 288 stimuli [96 alcohol advertisements with TAWs, the same 96 advertisements with PAWs, and 96 water advertisements (controls)] for 3 s each. If the advertisement made participants want ("yes")/do not want ("no") to consume the product, they pressed the corresponding button (self-report responses). The number of "yes" responses was compared between advertisement types with a paired sample t-test. Whole-brain and region-of-interest (ROI) analyses of the fMRI data were performed. Whole-brain BOLD fMRI highlighted contrasting effects of PAWs and TAWs. Compared with TAWs, PAWs elicited more activation in the precuneus, angular gyrus, occipital, frontal and temporal areas, and less activation in the nucleus accumbens, ventral tegmental areas, and putamen areas (regions of the reward circuit). The ROI analysis confirmed less activation in the reward circuit (left and right ventral tegmental areas, left and right nucleus accumbens) when viewing PAWs than TAWs. Analysis of the self-report responses indicated that the desire to consume the advertised alcohol product was lower when PAWs were viewed (compared with TAWs) (T = 8.18, p < 10-11). This is the first fMRI study to assess the effect of different alcohol warning formats. Our findings show that compared with TAWs, stronger PAWs in advertisements elicited less activity in key regions of the reward system. This suggests that the effects may influence the desire to consume alcohol products (self-report response analysis). These results could help policymakers who are interested in developing more effective labeling measures that target young people.

Knowledge of Patients' Activation Level Changes Expert US Physicians' Communication in GERD Management.

Gastroesophageal reflux disease (GERD) is common. Treatment is to manage symptoms, but medication nonadherence is common. To date, little emphasis has been on understanding patient behaviors and reasons for medication nonadherence. We performed a cross-sectional survey study among expert gastroenterologists specializing in esophageal disease. Survey studies consisted of a 6-item questionnaire measuring physician knowledge of patient activation, the Clinician Support for Patient Activation Measure (CS-PAM), and an adapted 20-item Patient Assessment of Chronic Illness Care (PACIC). All question stems were specified to GERD management. Thirty-six experts participated. Most indicated hearing the term patient engagement before this survey (88.9%), but fewer were aware of the term patient activation (33.3%). Respondents were then made aware of the clinical significance of patient activation and asked, based on this knowledge, the likelihood that patients' activation level before the clinic would impact their communication. Responses varied between "to a great extent" and "not at all." Overall, CS-PAM activation scores were high, indicating a high level of support for patient activation. Lastly, respondents indicated their frequency of participating in partnership-building behaviors with patients. More than half (52.8%) of expert physicians "almost always" asked how GERD affected their lives, while less often asked patients about their health habits (22.2%), help set specific goals to improve their eating or exercise lifestyle (19.4%), or refer patients to a dietician, health educator, or counselor for their GERD (11.1%). Patient activation is an important strategy and may provide a behavioral approach to address medication adherence in GERD.

Understanding of Kaphaja Shiroroga w.s.r. to Sinusitis

Ayurveda, encompasses eight branches known as Ashtangas. Among these, Shalakya Tantra specializes in the diagnosis and treatment of diseases affecting the Urdhwajatru-head and neck. Acharya Sushruta, a revered figure in Ayurvedic medicine, meticulously detailed the management of eleven head diseases, termed Shirorogas, in the Uttara Tantra of Sushruta samhita. One of these diseases, Kaphaja Shiroroga, closely aligns with the modern medical condition of Sinusitis based on its signs and symptoms. Kaphaja Shiroroga presents with symptoms such as a sensation of heaviness, mucus accumulation, stiffness, coldness and swelling around the eyes. Sinusitis, a contemporary counterpart, involves inflammation of the sinus tissues- air-filled spaces in the forehead, cheeks and nose. This inflammation results in facial pain, nasal congestion or discharge and sometimes fever, often triggered by a common cold. However, sinusitis can also be caused by viruses, bacteria, fungi, or allergies. Classified as a Kaphaja Vyadhi (disease caused by an imbalance of the Kapha dosha), Kaphaja Shiroroga is treated through various Ayurvedic procedures, including Shirovirechana (cleansing of head), Kavala (gargling), Snehana (oiling), Swedana (sudation), Vamana (therapeutic emesis), Upanaha (poultice) and Dhumapana (medicated smoking). The choice of treatment is determined by the physician's expertise and tailored to the patient's specific needs. By following these methodologies, Ayurveda aims not only to eradicate the disease but also to minimize the likelihood of recurrence, thus promoting long-term health and well-being.

Investigating the Use of Simulated Patient Ratings in Objective Structured Clinical Examinations to Enhance Undergraduate Medical Assessments in Riyadh, Saudi Arabia.

Objective structured clinical examinations (OSCE) are the gold standard of clinical assessment, and are used to conduct undergraduate family medicine clinical assessment at King Faisal Specialist Hospital and Research Centre (KFSHRC). Some studies have suggested that simulated patient (SP) ratings could provide a better measure of empathy and communication skills than physician scores. The objective of this study is to further explore the effectiveness of simulated patient (SP) ratings inundergraduate OSCE assessments. The research employed a mixed-method approach. Three OSCE assessments for final-year students were selected. Both physicians and SPsevaluated each student, providing global ratings across four domains. The quantitative aspect involved comparing physician and SP scores and assessing correlation. The qualitative aspect involved interviewing SPs to establish what student behaviours led to higher or lower scores. Moderate correlation was found between physician ratings and SP ratings (r=0.53, p<0.01). Internal consistency of the SP ratings was lower than physician scores. SPs considered themselves to be patient advocates and were keen to give formative feedback. The ability of the trainee to truly listen was a major concern. Scoring for SPs was relatively holistic in nature. The results demonstrate that SP scores have slightly weaker reliability but are still relevant and offer a completely different perspective, enriching the assessment data. Assessment should take patientor SP perspectives into account, and not rely solely on the expert physician. Changing the assessment methods will lead to necessary changes in student approach to the OSCE and improve authenticity and validity.

Preliminary study of substantia nigra analysis by tensorial feature extraction.

Parkinson disease (PD) is a common progressive neurodegenerative disorder in our ageing society. Early-stage PD biomarkers are desired for timely clinical intervention and understanding of pathophysiology. Since one of the characteristics of PD is the progressive loss of dopaminergic neurons in the substantia nigra pars compacta, we propose a feature extraction method for analysing the differences in the substantia nigra between PD and non-PD patients. We propose a feature-extraction method for volumetric images based on a rank-1 tensor decomposition. Furthermore, we apply a feature selection method that excludes common features between PD and non-PD. We collect neuromelanin images of 263 patients: 124 PD and 139 non-PD patients and divide them into training and testing datasets for experiments. We then experimentally evaluate the classification accuracy of the substantia nigra between PD and non-PD patients using the proposed feature extraction method and linear discriminant analysis. The proposed method achieves a sensitivity of 0.72 and a specificity of 0.64 for our testing dataset of 66 non-PD and 42 PD patients. Furthermore, we visualise the important patterns in the substantia nigra by a linear combination of rank-1 tensors with selected features. The visualised patterns include the ventrolateral tier, where the severe loss of neurons can be observed in PD. We develop a new feature-extraction method for the analysis of the substantia nigra towards PD diagnosis. In the experiments, even though the classification accuracy with the proposed feature extraction method and linear discriminant analysis is lower than that of expert physicians, the results suggest the potential of tensorial feature extraction.

Intracerebral Hemorrhage Prognosis Classification via Joint-Attention Cross-Modal Network.

Intracerebral hemorrhage (ICH) is a critical condition characterized by a high prevalence, substantial mortality rates, and unpredictable clinical outcomes, which results in a serious threat to human health. Improving the timeliness and accuracy of prognosis assessment is crucial to minimizing mortality and long-term disability associated with ICH. Due to the complexity of ICH, the diagnosis of ICH in clinical practice heavily relies on the professional expertise and clinical experience of physicians. Traditional prognostic methods largely depend on the specialized knowledge and subjective judgment of healthcare professionals. Meanwhile, existing artificial intelligence (AI) methodologies, which predominantly utilize features derived from computed tomography (CT) scans, fall short of capturing the multifaceted nature of ICH. Although existing methods are capable of integrating clinical information and CT images for prognosis, the effectiveness of this fusion process still requires improvement. To surmount these limitations, the present study introduces a novel AI framework, termed the ICH Network (ICH-Net), which employs a joint-attention cross-modal network to synergize clinical textual data with CT imaging features. The architecture of ICH-Net consists of three integral components: the Feature Extraction Module, which processes and abstracts salient characteristics from the clinical and imaging data, the Feature Fusion Module, which amalgamates the diverse data streams, and the Classification Module, which interprets the fused features to deliver prognostic predictions. Our evaluation, conducted through a rigorous five-fold cross-validation process, demonstrates that ICH-Net achieves a commendable accuracy of up to 87.77%, outperforming other state-of-the-art methods detailed within our research. This evidence underscores the potential of ICH-Net as a formidable tool in prognosticating ICH, promising a significant advancement in clinical decision-making and patient care.

A Review of Artificial Intelligence in Tumor Pathology Image Analysis

Accurate diagnosis of tumors is crucial to the treatment and prognosis of patients. Pathological diagnosis is regarded as the "gold standard" of tumor diagnosis, which helps to detect the disease at an early stage and formulate precise treatment plans for patients. However, traditional pathology diagnosis relies heavily on the expertise and diagnostic experience of physicians, making the quality and accuracy of pathology diagnosis largely dependent on their individual capabilities. With the popularization of Whole Slide Image (WSI) technology, the application of AI in pathology has gained significant momentum. With its powerful analyzing ability, AI has been widely used in computational pathology, especially in pathology-assisted diagnosis, showing great potential. This paper first explores two core tasks of AI in the field of pathology image analysis - image segmentation and image classification. Finally, it looks at the challenges and opportunities facing the field.

International Multi-Specialty Expert Physician Preoperative Identification of Extranodal Extension n Oropharyngeal Cancer Patients using Computed Tomography: Prospective Blinded Human Inter-Observer Performance Evaluation.

Extranodal extension (pENE) is a critical prognostic factor in oropharyngeal cancer (OPC) that drives therapeutic disposition. Determination of pENE from radiological imaging has been associated with high inter-observer variability. However, the impact of clinician specialty on human observer performance of imaging-detected extranodal extension (iENE) remains poorly understood. To characterize the impact of clinician specialty on the accuracy of pre-operative iENE in human papillomavirus-positive (HPV+) OPC using computed tomography (CT) images. This prospective observational human performance study analyzed pre-therapy CT images from 24 HPV+ OPC patients, with duplication of 6 scans (n=30) of which 21 were pathologically confirmed pENE. Thirty-four expert observers, including 11 radiologists, 12 surgeons, and 11 radiation oncologists, independently assessed these scans for iENE and reported human-detected radiologic criteria and observer confidence. The primary outcomes included accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and Brier score for each physician, compared to ground-truth pENE. The significance of radiographic signs for prediction of pENE were determined through logistic regression analysis. Fleiss' kappa measured interobserver agreement, and Hanley-MacNeil AUC discrimination testing. Median accuracy across all specialties was 0.57 (95%CI 0.39 to 0.73), with no specialty showing discriminate performance greater than random estimation (median AUC 0.64, 95%CI 0.44 to 0.83). Significant differences between radiologists and surgeons in Brier scores (0.33 vs. 0.26, p < 0.01), radiation oncologists and surgeons in sensitivity (0.48 vs. 0.69, p > 0.1), and radiation oncologists and radiologists/surgeons in specificity (0.89 vs. 0.56, p > 0.1). Indistinct capsular contour and nodal necrosis were significant predictors of correct pENE status among all specialties. Interobserver agreement was weak for all the radiographic criteria, regardless of specialty (κ<0.6). Multiobserver testing shows physician discrimination of HPV+OPC pENE on pre-operative CT remains non-different than blind guessing, with high interrater variability and low diagnostic accuracy, regardless of clinician specialty. While minor differences in diagnostic performance among specialties are noted, they do not significantly affect the overall poor agreement and discrimination rates observed. The findings underscore the need for further research into automated detection systems or enhanced imaging techniques to improve the accuracy and reliability of iENE assessments in clinical practice.

Development and Deployment of a Pre-Planned Hospital Emergency Response Team (HERT) for EMS Augmentation: Case Report and Program Review

With the establishment and growth of the Emergency Medical Services (EMS) subspecialty, significant attention has been focused on clinical activities performed by EMS physicians in the out-of-hospital environment. An EMS fellowship includes special operations education to develop preparedness for responding to field situations requiring physician expertise. With only a thousand Board Certified EMS physicians in North America, EMS physicians may not be available 24 h per day to respond to field emergencies. Non-EMS physicians with minimal experience in prehospital or austere care may be called upon to respond to complex prehospital emergencies requiring advanced skills. The Los Angeles County EMS Agency implemented a policy in 1992 to establish Hospital Emergency Response Teams (HERT) as a regional resource to provide time-critical, specialized prehospital services within an EMS system. Activation of the HERT is rare, most frequently prompted by need for field amputation to enable extrication. We describe one such incident of a field intervention by HERT and detail the staffing, training, and equipment considerations within our large regional EMS system.

Implementation and Validation of a High-fidelity Simulation Model for Surgical Resident Training: Management of Acute Intraoperative Hemorrhage during Robot-assisted Surgery

ObjectivesTo improve our previous simulation-based training module by using sustainable material to mold an anatomically accurate terrain and reproducing major vascular injuries encountered during robot-assisted nephrectomy. MethodsThe simulator was built with a pump, gauge, and valve linked via silicone tubing. Artificial blood was made from cornstarch, water, and red dye, and pumped through 3D-Med artificial vessels with the dimensions of an average renal artery. Silicone was used to emulate the pliability of organic tissue and mold an anatomically accurate terrain. Eight urologic residents participated in the pilot simulation. We employed validated assessment tools including Non-Technical Skills for Surgeons and Objective Structured Assessment of Technical Skills forms to guide debrief sessions moderated by an expert physician after individual performance evaluations. ResultsThe apparatus demonstrated high reproducibility across all simulation scenarios, enhancing resident problem-solving skills. Residents’ pre-simulation surveys revealed significant concern regarding their acute hemorrhage management. Residents’ post-simulation survey demonstrated average realism scores increased from 4.375 to 4.75. Residents also felt the simulator enhanced learning, offering valuable practice and knowledge applicable to their surgical specialty. ConclusionsThe management of acute hemorrhage during robot-assisted surgery remains a space for additional surgical education and training. Our simulation successfully provided a reliable, reproducible training for residents to practice their technical and non-technical skills in managing acute hemorrhage.

Obesity is associated with muscle atrophy in rotator cuff tear

ObjectiveThe primary goal of this study is to evaluate the relationship between Body Mass Index (BMI) and muscle atrophy in individuals with rotator cuff tears.MethodsThis study consists of patients with...

Prevalence and Risk Factors Associated with Chronic Occupational Low Back Pain among Healthcare Professionals Working at Hospitals: Exploratory Survey Study.

Objective This study aimed to describe the methodological process for developing a questionnaire to identify the prevalence and risk factors for chronic occupational low back pain in healthcare professionals working at hospitals. Method An exploratory crossectional survey study was carried out in Belo Horizonte, MG, Brazil, and its metropolitan region, in two stages. Initially, the authors prepared a questionnaire based on the Roland Morris disability questionnaire and sent it to a committee of low back pain specialists for validation using the Delphi technique. The second stage consisted of sending the final questionnaire to health professionals working in a hospital environment for at least 2 years and presenting chronic low back pain for at least 3 months. Results Validation occurred in two rounds of questionnaire adjustments by a panel consisting of physical therapists and physician experts in the field (orthopedists with more than 3 years of experience). Both rounds had 13 participants. The questionnaire initially consisted of 27 items, and, after validation, it had 19 items. The study included 65 subjects, with an average age of 40.91 years old and an average time working at a hospital of 40 hours per week. The total sample had 76.9% of physicians, 10.8% of physical therapists, and 12.3% of nurses or nursing technicians. Most (52.3%) subjects reported staying in uncomfortable positions affecting the lower back for 5 to 10 hours per day. Conclusion We developed and validated, using the Delphi technique, a questionnaire on the prevalence and risk factors associated with chronic occupational low back pain among healthcare professionals working at hospitals. This unprecedented tool can benefit the population studied since the questionnaires currently used to evaluate chronic low back pain are not specific for investigating the occupational cause of this condition.

Diagnostic Strategy Using Color Doppler Ultrasound of Temporal Arteries in Patients With High Clinical Suspicion of Giant Cell Arteritis : A Prospective Cohort Study.

Giant cell arteritis (GCA) is the most prevalent systemic vasculitis in people older than 50 years. Any delay in diagnosis impairs patients' quality of life and can lead to permanent damage, particularly vision loss. To evaluate a diagnostic strategy for GCA using color Doppler ultrasound of the temporal artery as a first-line diagnostic test, temporal artery biopsy (TAB) as a secondary test, and physician expertise as the reference method. Prospective multicenter study with a 2-year follow-up. (ClinicalTrials.gov: NCT02703922). Patients were referred by their general practitioner or ophthalmologist to a physician with extensive experience in GCA diagnosis and management in one of the participating centers: 4 general and 2 university hospitals. 165 patients with high clinical suspicion of GCA, aged 79 years (IQR, 73 to 85 years). The diagnostic procedure was ultrasound, performed less than 7 days after initiation of corticosteroid therapy. Only ultrasound-negative patients underwent TAB. Bilateral temporal halo signs seen on ultrasound were considered positive. Ultrasound and TAB results were compared with physician-diagnosed GCA based on clinical findings and other imaging. Diagnosis of GCA was confirmed in 44%, 17%, and 21% of patients by ultrasound, TAB, and clinical expertise and/or other imaging tests, respectively. Their diagnosis remained unchanged at 1 month, and 2 years for those with available follow-up data. An alternative diagnosis was made in 18% of patients. The proportion of ultrasound-positive patients among patients with a clinical GCA diagnosis was 54% (95% CI, 45% to 62%). Small sample size, no blinding of ultrasound and TAB results, lack of an objective gold-standard comparator, and single diagnostic strategy. By using ultrasound of the temporal arteries as a first-line diagnostic tool in patients with high clinical suspicion of GCA, further diagnostic tests for patients with positive ultrasound were avoided. Tender "Recherche CH-CHU Poitou-Charentes 2014."

Diagnosis and Therapy of Atheroscerotic Renal Artery Stenosis - Update 2024

Abstract Atherosclerotic renal artery stenosis (ARAS), an increasingly recognized disorder, may cause ischemic nephropathy and renovascular hypertension, that may occur separately or together. Patients with chronic kidney disease (CKD) resulting from atherosclerotic renal artery stenosis usually have high-grade stenosis of both renal arteries or stenosis to a solitary functioning kidney. Patients at risk for bilateral renal artery stenosis are also at risk for other disorders that can present with similar clinical findings but cannot be corrected by surgery or angioplasty; these include hypertensive nephrosclerosis and atheroembolic kidney disease. In clinical decision-making about screening for and therapy of ARAS, we balance the chance of improving renal function and blood pressure with the risks of interventional procedures. In this article we provide an overview of the epidemiology, diagnosis, and treatment of ARVD based on consensus recommendations from a panel of physician experts who attended the recent KDIGO (Kidney Disease: Improving Global Outcomes) Controversies Conference on central and peripheral arterial diseases in chronic kidney disease. The rapid progress in this field necessitates an update. Most focus is provided for contentious issues, and we also outline aspects of investigation and management of ARVD that require further research.

Prospective assessment of AI-enabled cost savings, continuous support, and psychosocial enhancement (AI New Era Study).

e13615 Background: Cancer patients (pts) need extensive primary care across their treatment journey, yet the world's primary health systems struggle with patient volume and resource scarcity. This study aims to assess the effectiveness of Artificial Intelligence (AI) medical service model in primary care and clinical service pre-screening, as well as their potential impact on improving the quality of medical services and reducing medical costs. Methods: A total of 17,856 medical consultation inquiries from 7,522 pts with various types of cancer have been collected and categorized. The study employed a novel AI-driven medical service model (based on large language model), amalgamating clinical guidelines with a local oncology database, to prospectively field questions from 454 cancer-afflicted pts. Clinicians evaluated the accuracy and comprehensiveness of the responses to basic medical issues, while pts assessed the intelligibility and satisfaction. Results: Treatment-related inquiries constituted 34.44% (n = 6,149) of the total, with 81.53% of pts asking such questions. Basic medical issues were addressed in 65.56% (n = 11,707) of inquiries, raised by 59.78% of pts. Specific concerns within basic medical issues included test report explanations (20.45%), adverse reaction consultations (19.82%), and medication information requests (17.66%). In light of the prevalence of basic medical issues, the study prospectively explores the potential of AI technology to revolutionize medical models, driving the advent of a new era in healthcare research. As result, the AI model exhibited high performance across several metrics: accuracy (96.87 ± 10.29), comprehensiveness (97.40 ± 9.91), intelligibility (95.72 ± 12.62), and satisfaction (96.34 ± 11.03). Notably, the model demonstrated a proficiency in identifying queries necessitating physician expertise, with a 95.60% accuracy rate upon review. A survey of 50 outpatients indicated an enhancement in service speed (7.78%) and patient satisfaction (14.29%). This increase in satisfaction was primarily ascribed to pts' heightened sense of control and safety. When benchmarked against GPT-4, the AI model's overall performance was significantly superior (95.08 ± 10.05 vs 89.70 ± 12.85, p&lt;0.01), particularly in domestic drug knowledge and gene report analysis. Conclusions: Largely fueled by the advanced capabilities of large language model, AI has the potential to profoundly reshape the entire patient care journey. Our AI medical service model efficiently meets key healthcare needs, addressing over half of clinical issues and cutting costs. It also guides pts to the right specialists for timely care. Early surveys indicate better primary care and improved doctor-patient relations. Further research is needed to understand AI's effects on fairness, access, and outcomes across varied demographic and socioeconomic strata.