Hasil untuk "Specialties of internal medicine"

Lisa S. Rotenstein, Zili He, James Dziura et al.

Abstract Background The USA faces a predicted shortage of 36,500 physicians by 2036, with an increasing proportion of physicians leaving clinical practice or expressing an intent to do so. Female physicians have known differential workplace experiences, and prior studies have demonstrated higher attrition rates by sex in specific specialties. Objective To characterize nationwide hazards of attrition from clinical practice by physician sex across specialties. To describe the relative age at attrition by sex among physicians who leave clinical practice. Design Nationwide, longitudinal study based on national Medicare administrative data. Setting and Participants Physicians across clinical settings who provided care to Medicare patients from 2013 to 2023. Measurements Time to attrition from clinical practice. Results The sample consisted of 707,934 physicians of which 217,013 (30.7%) were female. Over the study period, female physicians had a higher likelihood of clinical practice attrition (HR: 1.43 (95% CI: 1.41, 1.44) compared to male counterparts across physician ages. Hazards of attrition were additionally greater for female physicians across multiple specialty categories (HRs ranging from 1.26 (9% CI: 1.23, 1.28) for hospital-based specialties to 1.72 (95% CI: 1.65, 1.78) for psychiatry specialties) and in both rural (HR: 1.42 (95% CI: 1.37, 1.47) and urban areas (HR: 1.43 (95% CI: 1.41, 1.44). Among physicians who left clinical practice, the median (IQR) age at attrition was significantly lower for females than males (49 (39–61) vs. 64 (53–70) years). Conclusions US female physicians are significantly more likely to leave clinical practice than male counterparts at every age, across specialties and practice locations. Among physicians who leave clinical practice, female physicians are younger when they do so. Given projected clinical workforce shortages, health systems and policymakers should pursue interventions and policies that mitigate the concerning trends identified.

Justin Ren, PhD, Colin Royse, MBBS, MD, David H. Tian, MD, PhD et al.

Rajat Vashistha, Arif Gulzar, Parveen Kundu et al.

India faces a significant cancer burden, with an incidence-to-mortality ratio indicating that nearly three out of five individuals diagnosed with cancer succumb to the disease. While the limitations of physical healthcare infrastructure are widely acknowledged as a primary challenge, concerted efforts by government and healthcare agencies are underway to mitigate these constraints. However, given the country's vast geography and high population density, it is imperative to explore alternative soft infrastructure solutions to complement existing frameworks. Artificial Intelligence agents are increasingly transforming problem-solving approaches across various domains, with their application in medicine proving particularly transformative. In this perspective, we examine the potential role of AI agents in advancing nuclear medicine for cancer research, diagnosis, and management in India. We begin with a brief overview of AI agents and their capabilities, followed by a proposed agent-based ecosystem that can address prevailing sustainability challenges in India nuclear medicine.

Nanjun Zhang, Bowen Li, Yu Yan et al.

Abstract Background The occurrence of arrhythmias as a complication of Kawasaki disease (KD) is extremely rare. Moreover, previous literature showed a low incidence of arrhythmias during the acute phase of KD, and the majority occurred in the subacute and chronic phases. To date, we have found only 17 sporadically reported global cases in the available literature. Case presentation We present the first documented case of an infant with KD complicated with supraventricular tachycardia (Atrioventricular reentrant tachycardia) during the acute phase. The arrhythmia resolved promptly after the combination therapy of intravenous Immunoglobulin (IVIG) and steroids during the acute phase since the inflammation subsided. Additionally, we conducted a review and summary of cases involving KD-related arrhythmias. Conclusions KD rarely causes arrhythmias, which might be associated with myocarditis and myocardial ischemia attributed to scar formation and/or excessive inflammatory factors damaging the conduction system. Strengthening the early identification and management of complications in patients with KD and personalized follow-up strategies for high-risk children during the chronic phase can enhance patients’ prognosis.

Emmanouil Nikolakakis, Joann Ching, Emmanouil Karystinaios et al.

Music therapy has been shown in recent years to provide multiple health benefits related to emotional wellness. In turn, maintaining a healthy emotional state has proven to be effective for patients undergoing treatment, such as Parkinson's patients or patients suffering from stress and anxiety. We propose fine-tuning MusicGen, a music-generating transformer model, to create short musical clips that assist patients in transitioning from negative to desired emotional states. Using low-rank decomposition fine-tuning on the MTG-Jamendo Dataset with emotion tags, we generate 30-second clips that adhere to the iso principle, guiding patients through intermediate states in the valence-arousal circumplex. The generated music is evaluated using a music emotion recognition model to ensure alignment with intended emotions. By concatenating these clips, we produce a 15-minute "music medicine" resembling a music therapy session. Our approach is the first model to leverage Language Models to generate music medicine. Ultimately, the output is intended to be used as a temporary relief between music therapy sessions with a board-certified therapist.

Yirui Chen, Qinyu Xiao, Jia Yi et al.

This paper explores the application of prompt engineering to enhance the performance of large language models (LLMs) in the domain of Traditional Chinese Medicine (TCM). We propose TCM-Prompt, a framework that integrates various pre-trained language models (PLMs), templates, tokenization, and verbalization methods, allowing researchers to easily construct and fine-tune models for specific TCM-related tasks. We conducted experiments on disease classification, syndrome identification, herbal medicine recommendation, and general NLP tasks, demonstrating the effectiveness and superiority of our approach compared to baseline methods. Our findings suggest that prompt engineering is a promising technique for improving the performance of LLMs in specialized domains like TCM, with potential applications in digitalization, modernization, and personalized medicine.

Hanguang Xiao, Feizhong Zhou, Xingyue Liu et al.

Since the release of ChatGPT and GPT-4, large language models (LLMs) and multimodal large language models (MLLMs) have attracted widespread attention for their exceptional capabilities in understanding, reasoning, and generation, introducing transformative paradigms for integrating artificial intelligence into medicine. This survey provides a comprehensive overview of the development, principles, application scenarios, challenges, and future directions of LLMs and MLLMs in medicine. Specifically, it begins by examining the paradigm shift, tracing the transition from traditional models to LLMs and MLLMs, and highlighting the unique advantages of these LLMs and MLLMs in medical applications. Next, the survey reviews existing medical LLMs and MLLMs, providing detailed guidance on their construction and evaluation in a clear and systematic manner. Subsequently, to underscore the substantial value of LLMs and MLLMs in healthcare, the survey explores five promising applications in the field. Finally, the survey addresses the challenges confronting medical LLMs and MLLMs and proposes practical strategies and future directions for their integration into medicine. In summary, this survey offers a comprehensive analysis of the technical methodologies and practical clinical applications of medical LLMs and MLLMs, with the goal of bridging the gap between these advanced technologies and clinical practice, thereby fostering the evolution of the next generation of intelligent healthcare systems.

Wasif Khan, Seowung Leem, Kyle B. See et al.

Foundation models (FMs) are large-scale deep learning models trained on massive datasets, often using self-supervised learning techniques. These models serve as a versatile base for a wide range of downstream tasks, including those in medicine and healthcare. FMs have demonstrated remarkable success across multiple healthcare domains. However, existing surveys in this field do not comprehensively cover all areas where FMs have made significant strides. In this survey, we present a comprehensive review of FMs in medicine, focusing on their evolution, learning strategies, flagship models, applications, and associated challenges. We examine how prominent FMs, such as the BERT and GPT families, are transforming various aspects of healthcare, including clinical large language models, medical image analysis, and omics research. Additionally, we provide a detailed taxonomy of FM-enabled healthcare applications, spanning clinical natural language processing, medical computer vision, graph learning, and other biology- and omics- related tasks. Despite the transformative potentials of FMs, they also pose unique challenges. This survey delves into these challenges and highlights open research questions and lessons learned to guide researchers and practitioners. Our goal is to provide valuable insights into the capabilities of FMs in health, facilitating responsible deployment and mitigating associated risks.

Khaled Saab, Tao Tu, Wei-Hung Weng et al.

Excellence in a wide variety of medical applications poses considerable challenges for AI, requiring advanced reasoning, access to up-to-date medical knowledge and understanding of complex multimodal data. Gemini models, with strong general capabilities in multimodal and long-context reasoning, offer exciting possibilities in medicine. Building on these core strengths of Gemini, we introduce Med-Gemini, a family of highly capable multimodal models that are specialized in medicine with the ability to seamlessly use web search, and that can be efficiently tailored to novel modalities using custom encoders. We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable, often by a wide margin. On the popular MedQA (USMLE) benchmark, our best-performing Med-Gemini model achieves SoTA performance of 91.1% accuracy, using a novel uncertainty-guided search strategy. On 7 multimodal benchmarks including NEJM Image Challenges and MMMU (health & medicine), Med-Gemini improves over GPT-4V by an average relative margin of 44.5%. We demonstrate the effectiveness of Med-Gemini's long-context capabilities through SoTA performance on a needle-in-a-haystack retrieval task from long de-identified health records and medical video question answering, surpassing prior bespoke methods using only in-context learning. Finally, Med-Gemini's performance suggests real-world utility by surpassing human experts on tasks such as medical text summarization, alongside demonstrations of promising potential for multimodal medical dialogue, medical research and education. Taken together, our results offer compelling evidence for Med-Gemini's potential, although further rigorous evaluation will be crucial before real-world deployment in this safety-critical domain.

Pimsiri Sripongpun, Apichat Kaewdech, Prowpanga Udompap et al.

Background & Aims: The new nomenclature of steatotic liver disease (SLD) was recently launched with sub-classifications of metabolic dysfunction-associated SLD (MASLD), MASLD with increased alcohol intake (MetALD), and alcohol-related liver disease (ALD). Herein, we aimed to evaluate the characteristics and long-term outcomes associated with these subgroups and the utility of non-invasive biomarkers. Methods: Using NHANES III (the third National Health and Nutrition Examination Survey) and linked mortality data, all adult participants with available ultrasonographic liver steatosis status were included. Those with viral hepatitis, incomplete data on alcohol consumption, cardiometabolic risk, and missing data that hindered Steatosis-associated Fibrosis Estimator (SAFE) score calculation were excluded. The characteristics of those without SLD (no steatosis on ultrasound), MASLD, MetALD, and ALD were compared. Overall survival (OS) was determined and SAFE score strata were applied to SLD subgroups. Results: A total of 9,939 participants were eligible; 64% had no SLD, while 30%, 2.3%, and 1% had MASLD, MetALD, and ALD, respectively. A higher proportion of men, as well as active smokers, was observed in the MetALD and ALD groups compared to the MASLD group. Diabetes was more prevalent in the MASLD group than in the MetALD and ALD groups. The ALD subgroup had significantly lower OS than the MASLD group (p = 0.004), but the MetALD did not (p = 0.165). SAFE score strata meaningfully differentiated OS of all SLD subgroups. Conclusions: MASLD accounted for the largest proportion of SLD. MetALD shared the characteristics of both MASLD and ALD. The ALD subgroup had a significantly lower OS than the MASLD subgroup but there was no difference between MetALD and MASLD. The SAFE score can be used to stratify long-term outcomes in all SLD subgroups. Impact and implications:: “Steatotic liver disease (SLD)” is a recently introduced term covering three subgroups: MASLD (metabolic dysfunction-associated SLD), MetALD (MASLD with increased alcohol intake), and ALD (alcohol-related liver disease). We explored the characteristics and outcomes of these subgroups among the US population. We found that MASLD was far more common than MetALD and ALD, but all subgroups shared cardiometabolic risk factors. The ALD subgroup has the worst survival, pointing to the synergistic effect of alcohol and metabolic dysfunction. In addition, the SAFE (Steatosis-associated Fibrosis Estimator) score might be a useful non-invasive test to stratify long-term risk in all three SLD subgroups.

William J. Benjamin, N. Lenze, Lauren A. Bohm et al.

Abstract Purpose To assess the impact of applicant and residency program characteristics on preference signaling outcomes in the Match during the first 2 years of implementation across 6 specialties. Method Data were obtained from the Texas Seeking Transparency in Application to Residency survey for applicants applying into otolaryngology during the 2020–2021 and 2021–2022 application cycles and into dermatology, internal medicine (categorical and preliminary year), general surgery, and urology during the 2021–2022 application cycle. The primary outcome was signal yield, defined as the number of interviews at signaled programs divided by the total number of signals sent. Associations with applicant-reported characteristics and geographic connections to residency programs were assessed using Wilcoxon rank sum testing, Spearman’s rank correlation testing, and ordinary least squares regression. Results 1,749 applicants with preference signaling data were included from internal medicine (n = 884), general surgery (n = 291), otolaryngology (n = 217), dermatology (n = 147), urology (n = 124), and internal medicine preliminary year (n = 86). On average 60.9% (standard deviation 32.3%) of signals resulted in an interview (signal yield). There was a stepwise increase in signal yield with the percentage of signals sent to programs with a geographic connection (57.3% for no signals vs. 68.9% for 5 signals, P < .01). Signal yield was positively associated with applicant characteristics, such as United States Medical Licensing Exam Step 1 and 2 scores, honors society membership, and number of publications (P < .01). Applicants reporting a lower class rank quartile were significantly more likely to have a higher percentage of their interviews come from signaled programs (P < .01). Conclusions Signal yield is significantly associated with geographic connections to residency programs and applicant competitiveness based on traditional metrics. These findings can inform applicants, programs, and specialties as preference signaling grows.

Charlene L. Preys, C. L. Blout Zawatsky, Amanda Massmann et al.

Aim: To understand how attitudes toward pharmacogenomic (PGx) testing among healthcare providers varies by specialty. Methods: Providers reported comfort ordering PGx testing and its perceived utility on web-based surveys before and after genetics education. Primary quantitative analyses compared primary care providers (PCPs) to specialty providers at both timepoints. Results: PCPs were more likely than specialty care providers to rate PGx testing as useful at both timepoints. Education increased comfort ordering PGx tests, with larger improvements among PCPs than specialty providers. Over 90% of cardiology and internal medicine providers rated PGx testing as useful at pre- and post-education. Conclusion: PCPs overwhelmingly perceive PGx to be useful, and provider education is particularly effective for improving PCPs' confidence. Education for all specialties will be essential to ensure appropriate integration into routine practice.

A. Giannini, O. D’Oria, V. Chiantera et al.

aDepartment of Medical and surgical sciences and translational Medicine, PhD Course in “translational Medicine and oncology”, sapienza university, rome, Italy; bunit of gynecologic oncology, arnas "Civico – Di Cristina – Benfratelli", Palermo, Italy; cDepartment of Health Promotion, Mother and Child Care, Internal Medicine and Medical specialties (ProMIse), university of Palermo, Palermo, Italy; d2nd academic Department of obstetrics and gynaecology, Hippokration general Hospital, aristotle university of thessaloniki, thessaloníki, greece; eDepartment of surgical, oncological and oral sciences (Di.Chir.on.s.), university of Palermo, Palermo, Italy; fDepartment of Medicine, school of Medicine, nazarbayev university, nur-sultan, Kazakhstan; gDepartment of obstetrics and gynecology, lebanese american university, Beirut, lebanon

Hongjian Zhou, Fenglin Liu, Boyang Gu et al.

Large language models (LLMs), such as ChatGPT, have received substantial attention due to their capabilities for understanding and generating human language. While there has been a burgeoning trend in research focusing on the employment of LLMs in supporting different medical tasks (e.g., enhancing clinical diagnostics and providing medical education), a review of these efforts, particularly their development, practical applications, and outcomes in medicine, remains scarce. Therefore, this review aims to provide a detailed overview of the development and deployment of LLMs in medicine, including the challenges and opportunities they face. In terms of development, we provide a detailed introduction to the principles of existing medical LLMs, including their basic model structures, number of parameters, and sources and scales of data used for model development. It serves as a guide for practitioners in developing medical LLMs tailored to their specific needs. In terms of deployment, we offer a comparison of the performance of different LLMs across various medical tasks, and further compare them with state-of-the-art lightweight models, aiming to provide an understanding of the advantages and limitations of LLMs in medicine. Overall, in this review, we address the following questions: 1) What are the practices for developing medical LLMs 2) How to measure the medical task performance of LLMs in a medical setting? 3) How have medical LLMs been employed in real-world practice? 4) What challenges arise from the use of medical LLMs? and 5) How to more effectively develop and deploy medical LLMs? By answering these questions, this review aims to provide insights into the opportunities for LLMs in medicine and serve as a practical resource. We also maintain a regularly updated list of practical guides on medical LLMs at https://github.com/AI-in-Health/MedLLMsPracticalGuide

Ahmad Wisnu Mulyadi, Heung-Il Suk

Extensive adoption of electronic health records (EHRs) offers opportunities for their use in various downstream clinical analyses. To accomplish this purpose, enriching an EHR cohort with external knowledge (e.g., standardized medical ontology and wealthy semantics) could help us reveal more comprehensive insights via a spectrum of informative relations among medical codes. Nevertheless, harnessing those beneficial interconnections was scarcely exercised, especially in the medication recommendation task. This study proposes a novel Knowledge-Induced Medicine Prescribing Network (KindMed) to recommend medicines by inducing knowledge from myriad medical-related external sources upon the EHR cohort and rendering interconnected medical codes as medical knowledge graphs (KGs). On top of relation-aware graph representation learning to obtain an adequate embedding over such KGs, we leverage hierarchical sequence learning to discover and fuse temporal dynamics of clinical (i.e., diagnosis and procedures) and medicine streams across patients' historical admissions to foster personalized recommendations. Eventually, we employ attentive prescribing that accounts for three essential patient representations, i.e., a summary of joint historical medical records, clinical progression, and the current clinical state of patients. We validated the effectiveness of our KindMed on the augmented real-world EHR cohorts, achieving improved recommendation performances against a handful of graph-driven baselines.

Haider Sultan, Hafiza Farwa Mahmood, Noor Fatima et al.

Like other fields of Traditional Medicines, Unani Medicines have been found as an effective medical practice for ages. It is still widely used in the subcontinent, particularly in Pakistan and India. However, Unani Medicines Practitioners are lacking modern IT applications in their everyday clinical practices. An Online Clinical Decision Support System may address this challenge to assist apprentice Unani Medicines practitioners in their diagnostic processes. The proposed system provides a web-based interface to enter the patient's symptoms, which are then automatically analyzed by our system to generate a list of probable diseases. The system allows practitioners to choose the most likely disease and inform patients about the associated treatment options remotely. The system consists of three modules: an Online Clinical Decision Support System, an Artificial Intelligence Inference Engine, and a comprehensive Unani Medicines Database. The system employs advanced AI techniques such as Decision Trees, Deep Learning, and Natural Language Processing. For system development, the project team used a technology stack that includes React, FastAPI, and MySQL. Data and functionality of the application is exposed using APIs for integration and extension with similar domain applications. The novelty of the project is that it addresses the challenge of diagnosing diseases accurately and efficiently in the context of Unani Medicines principles. By leveraging the power of technology, the proposed Clinical Decision Support System has the potential to ease access to healthcare services and information, reduce cost, boost practitioner and patient satisfaction, improve speed and accuracy of the diagnostic process, and provide effective treatments remotely. The application will be useful for Unani Medicines Practitioners, Patients, Government Drug Regulators, Software Developers, and Medical Researchers.

N. V. Mikryukova, N. M. Kalinina

Mast Cell Activation Syndrome (MCAS) is a severe relapsing disease requiring inpatient treatment, with clinical pattern including the features of anaphylaxis. The article presents diagnostic criteria aimed for differentiation of MCAS from similar severe conditions as well as discusses local forms of mast cell activation. The consensus group has established distinct criteria for diagnosing MCAS. The agreed criteria include episodic (recurrent) occurrence of typical systemic symptoms caused by release of mast cell mediators and involve, at least, two organs; an increase in serum tryptase level by, at least, 20% over individual baseline tryptase plus  2 ng/mL tryptase during 3-4 hours of the pathological reaction; a positive response to drugs that either target mast cells mediators, or their effects. In principle, the classification of MCAS is based on its etiology being subdivided into primary (clonal) MCAS, secondary MCAS, and idiopathic MCAS. The primary MCAS is determined by clonal expansion of mast cells and is considered systemic mastocytosis. In secondary MCAS, normal mast cells are activated by the known triggers, e.g., IgE. If neither clonal expansion nor a trigger for mast cells activation are identified, the condition is defined as idiopathic MCAS.The new COVID-19 infection has attracted particular interest in MCAS, since the severe course of COVID-19 was thought to develop due to latent MCAS, but the criteria for MCAS in these patients were not reproduced. In the presence of local symptoms, such as urticaria, or in cases of single-organ involvement, e.g., isolated gastrointestinal symptoms, and suspected mast cell activation being basic to pathogenesis, the term mast cell activation disorder was introduced. Moreover, the article discusses several different mediators that are proposed as markers in the diagnosis of MCAS.However, over-diagnosis of MCAS entails the risk of missing the underlying pathology, which is not associated with MCAS, and requires differential diagnosis with a number of diseases. In the absence of severe attacks (with hypotension and shock), the likelihood of MCAS is generally very low. Of course, the patients with mastocytosis and/or confirmed IgE-dependent allergy are at higher risk of developing MCAS, but a   key diagnostic marker is an event-related increase in mast cells tryptase from baseline determined over the asymptomatic period. The diagnosis of MCAS is highly likely if the tryptase level rises above a certain threshold (20% of baseline plus 2 ng/mL).

Katiuska H. Liendo-Martínez, Stephany I. Briones-Alvarado, Virginia Gallo-González et al.

El uso diagnóstico y terapéutico de la broncoscopia flexible (BF) ha tenido una gran evolución desde que Gustav Killian realizó en 1897 la primera endoscopia traqueal para extraer un cuerpo extraño1. Con el pasar de los años se ha demostrado que es un procedimiento seguro2 con una mortalidad escasa (< 0.1%) siendo sus complicaciones infrecuentes y derivadas principalmente del tipo de técnica, de las propias comorbilidades del paciente y de la sedación3. Dentro de las complicaciones infrecuentes podemos mencionar el neumomediastino y el neumoperitoneo que generalmente se deben a la presencia de una ruptura gástrica. Presentamos el caso de un paciente de 58 años que 15 días tras la realización de una BF, presenta el hallazgo incidental de un neumoperitoneo asintomático sin evidencia de lesión gástrica.

J. Himmelstein, Christopher Cai, D. Himmelstein et al.

P. Phimphasone-Brady, J. Chiao, L. Karamsetti et al.

Abstract The COVID-19 pandemic has rapidly altered ambulatory health care delivery and may have worsened disparities in health care access. To assess the telehealth implementation experiences of ambulatory personnel in different disciplines and their perspectives on potential telehealth disparities, and to make recommendations for more equitable telehealth delivery. We used a convergent parallel mixed-methods design. Clinic managers from geriatric medicine, internal medicine, and psychiatry e-mailed a survey to clinicians and staff regarding experiences with telehealth care delivery. Quantitative survey responses were analyzed with Fisher’s Exact tests. Qualitative responses were coded thematically. Recommendations were categorized by type of implementation strategy. Quantitative and qualitative findings on telehealth disparities were merged in a joint data display. Respondents (n = 147, 57% response rate) were distributed across three specialties: 66% internal medicine, 19% psychiatry, and 14% geriatric medicine. Prior to 2020, 77% of clinicians had never delivered telehealth services. By Spring 2020, 78% reported conducting more than half of clinic visits by telehealth. Among clinicians, 52% agreed/strongly agreed that rapid telehealth implementation exacerbated access to care disparities to: older adult patients, those with limited internet access, and those needing interpretation services. Staff expressed similar difficulties with telehealth set-up especially for these patients. To improve telehealth equity, clinicians recommended to: (i) change infrastructure; (ii) train and educate stakeholders; and (iii) support clinicians. Clinicians and staff reported specific subpopulations had challenges in accessing telehealth visits. To avoid perpetuating telehealth access disparities, further co-discovery of equitable implementation strategies with patients and clinics are urgently needed.