ABSTRACT
OBJECTIVE: Traditional knowledge-based and machine learning diagnostic decision support systems have benefited from integrating the medical domain knowledge encoded in the Unified Medical Language System (UMLS). The emergence of Large Language Models (LLMs) to supplant traditional systems poses questions of the quality and extent of the medical knowledge in the models' internal knowledge representations and the need for external knowledge sources. The objective of this study is three-fold: to probe the diagnosis-related medical knowledge of popular LLMs, to examine the benefit of providing the UMLS knowledge to LLMs (grounding the diagnosis predictions), and to evaluate the correlations between human judgments and the UMLS-based metrics for generations by LLMs. METHODS: We evaluated diagnoses generated by LLMs from consumer health questions and daily care notes in the electronic health records using the ConsumerQA and Problem Summarization datasets. Probing LLMs for the UMLS knowledge was performed by prompting the LLM to complete the diagnosis-related UMLS knowledge paths. Grounding the predictions was examined in an approach that integrated the UMLS graph paths and clinical notes in prompting the LLMs. The results were compared to prompting without the UMLS paths. The final experiments examined the alignment of different evaluation metrics, UMLS-based and non-UMLS, with human expert evaluation. RESULTS: In probing the UMLS knowledge, GPT-3.5 significantly outperformed Llama2 and a simple baseline yielding an F1 score of 10.9% in completing one-hop UMLS paths for a given concept. Grounding diagnosis predictions with the UMLS paths improved the results for both models on both tasks, with the highest improvement (4%) in SapBERT score. There was a weak correlation between the widely used evaluation metrics (ROUGE and SapBERT) and human judgments. CONCLUSION: We found that while popular LLMs contain some medical knowledge in their internal representations, augmentation with the UMLS knowledge provides performance gains around diagnosis generation. The UMLS needs to be tailored for the task to improve the LLMs predictions. Finding evaluation metrics that are aligned with human judgments better than the traditional ROUGE and BERT-based scores remains an open research question.
ABSTRACT
Diabetic lumbosacral radiculoplexus neuropathy (DLSRPN), also known as diabetic amyotrophy, is a rare disease of exclusion that is difficult to diagnose due to its non-specific clinical presentation of neuropathy, autonomic symptoms, and potential weight loss. Due to this, many differential diagnoses are raised before making a diagnosis of such an uncommon disease. However, once the diagnosis is made, the management of this disease can vary. Here, we would like to discuss the etiology, pathophysiology, diagnosis, and management of this disease, as well as present a rare case of diabetic lumbosacral radiculoplexus neuropathy in a 50-year-old male.
ABSTRACT
Artificial intelligence (AI) is a suite of technologies that enables computers to learn and interpret information like human cognition. It has found applications across various fields, including healthcare, agriculture, astronomy, navigation, and robotics. Within healthcare, AI has the potential to enhance diagnostic accuracy, facilitate drug research, and automate patient experiences. This comparative study focuses on the proficiency of AI in generating accurate differential diagnoses in the field of pathology. Six medical vignettes were crafted, and each scenario was then input into three different AI platforms. The pathologist reviewed and determined the most accurate AI model.
ABSTRACT
Neuralgic muscular atrophy is not uncommon in clinical practice. Due to the different branches of brachial plexus involved in the lesion, the clinical symptoms are different, and there is a lack of clear imaging diagnostic criteria, so the diagnosis of this disease brings great challenges to clinicians. We have certain experience in the diagnosis and treatment of this disease, and hereby select a representative case of neuralgic muscular atrophy to share its diagnosis and treatment process, focusing on analyzing the characteristic symptoms of this disease, valuable imaging data and targeted treatment, so as to enable clinicians to better understand this disease.
ABSTRACT
BACKGROUND/OBJECTIVE: Neurosurgery emphasizes the criticality of accurate differential diagnoses, with diagnostic delays posing significant health and economic challenges. As large language models (LLMs) emerge as transformative tools in healthcare, this study seeks to elucidate their role in assisting neurosurgeons with the differential diagnosis process, especially during preliminary consultations. METHODS: This study employed 3 chat-based LLMs, ChatGPT (versions 3.5 and 4.0), Perplexity AI, and Bard AI, to evaluate their diagnostic accuracy. Each LLM was prompted using clinical vignettes, and their responses were recorded to generate differential diagnoses for 20 common and uncommon neurosurgical disorders. Disease-specific prompts were crafted using Dynamed, a clinical reference tool. The accuracy of the LLMs was determined based on their ability to identify the target disease within their top differential diagnoses correctly. RESULTS: For the initial differential, ChatGPT 3.5 achieved an accuracy of 52.63%, while ChatGPT 4.0 performed slightly better at 53.68%. Perplexity AI and Bard AI demonstrated 40.00% and 29.47% accuracy, respectively. As the number of considered differentials increased from 2 to 5, ChatGPT 3.5 reached its peak accuracy of 77.89% for the top 5 differentials. Bard AI and Perplexity AI had varied performances, with Bard AI improving in the top 5 differentials at 62.11%. On a disease-specific note, the LLMs excelled in diagnosing conditions like epilepsy and cervical spine stenosis but faced challenges with more complex diseases such as Moyamoya disease and amyotrophic lateral sclerosis. CONCLUSIONS: LLMs showcase the potential to enhance diagnostic accuracy and decrease the incidence of missed diagnoses in neurosurgery.
Subject(s)
Artificial Intelligence , Missed Diagnosis , Neurosurgeons , Humans , Diagnosis, Differential , Neurosurgery , Diagnostic ErrorsABSTRACT
Background: Autosomal dominant polycystic kidney disease (ADPKD) is the most common hereditary disease causing chronic renal failure, with a high incidence of extra-renal manifestations including pericardial effusion. Case summary: We present the case of a 41-year-old female, known for ADPKD, who presented to our emergency department with epigastric pain radiating to the interscapular area. Blood exams showed moderate increase in inflammatory markers. Echocardiography revealed a circumferential pericardial effusion of 10â mm. She was put under treatment with colchicine therapy (1â mg b.i.d.) based on a presumptive diagnosis of acute pericarditis with pericardial effusion. She was hospitalized due to increase in pericardial effusion, underwent pericardial drainage, and started prednisone therapy with rapid recovery. We started a close follow-up on a monthly basis, with progressive decrease in pericardial effusion and progressive amelioration in symptoms, although the patient continued to report mild asthenia. Discussion: Pericardial effusion and ADPKD are conditions that both require an interdisciplinary discussion for optimal patient care that avoids neglecting pivotal symptoms and avoidable invasive examinations.
ABSTRACT
Splenogonadal fusion is a rare, benign congenital malformation characterized by the association of splenic tissue and gonads (typically testicles). It is a condition of male predominance and can be classified into two types: continuous, if the spleen and gonad are united by a splenic cord or fibrous tissue, or discontinuous. Splenogonadal fusion is often associated with other congenital anomalies such as cryptorchidism, limb defects, and micrognathia. Differential diagnosis can be difficult and includes inguinal hernia, spermatic cord cyst, cryptorchidism, or testicular mass. Due to little knowledge of the pathology, unnecessary orchidectomies are often performed. A previously healthy five-year-old boy was sent to a pediatric surgery appointment due to testicular asymmetry. The physical examination showed a painless, nodular mass adhering to the upper pole of the left testicle, without any palpable inguinal masses. Tumor markers were negative, and a testicular ultrasound with Doppler revealed a mass suggestive of an accessory testicle. Left inguinal surgical exploration revealed the presence of a mass joined by fibrous tissue to the upper pole of the testicle, but no connection to the native spleen was found. Total excision was performed with the testicle's preservation. The anatomopathological analysis revealed morphological aspects compatible with splenic tissue with normal characteristics. The diagnosis of splenogonadal fusion is rare and complex, requires several differential diagnoses, and is often made intraoperatively.The prognosis is excellent as long as there are no associated malformations. A high level of suspicion for this pathology, with recognition of the anatomical structures, can avoid unnecessary orchidectomy.
ABSTRACT
Subacute thyroiditis (SAT) is an inflammatory disease of the thyroid gland. It can present with overlapping features of other etiology of thyroiditis. It can present with thyroid enlargement and systemic symptoms such as fever as well as neck pain and may be confused with infectious thyroiditis. It can be difficult to diagnose and present as fever of unknown origin (FUO). A good history, physical examination, laboratory investigation, as well as imaging may aid in the correct diagnosis and prevent the inappropriate use of antibiotics. Treatment is usually with nonsteroidal anti-inflammatory drugs (NSAIDs) as well as corticosteroids. We herein present a case of SAT presenting as FUO. We highlighted the importance of proper clinical evaluation, the importance of thyroid imaging, and how to differentiate other forms of thyroiditis.
ABSTRACT
BACKGROUND: Migraine, a frequent and debilitating neurological disease, shows gender-specific differences in prevalence and severity. Pregnancy is associated with numerous unique features in terms of migraine course, treatment options and differential diagnoses. OBJECTIVES: How does pregnancy influence the course of migraine? What are the possible treatment options during pregnancy? Which differential diagnoses should be considered? MATERIAL AND METHODS: Narrative review with summary and discussion of relevant studies and guidelines on migraine in pregnancy. RESULTS: During pregnancy up to three quarters of women experience improvement of their migraine; however, there may be a renewed increase in frequency after childbirth. Choosing an appropriate treatment during pregnancy requires a careful risk-benefit assessment. It is important to consider secondary causes of headache as these can occur more frequently during pregnancy and some can be life-threatening. CONCLUSION: Consideration of specific aspects of migraine in pregnancy is crucial to be able to develop the best possible treatment strategies for affected patients.
Subject(s)
Migraine Disorders , Nervous System Diseases , Pregnancy , Humans , Female , Migraine Disorders/diagnosis , Migraine Disorders/epidemiology , Migraine Disorders/therapy , Headache/therapy , Risk AssessmentABSTRACT
INTRODUCTION: A previously published web-based App using Gradient-boosted models (GBMs) of eight laboratory parameters was established by Oster et al. to facilitate diagnosis or exclusion of myelodysplastic syndromes (MDS) in patients. METHODS: To validate their algorithm, we compared 175 anemic patients with MDS diagnosis from our German MDS Registry with 1378 non-MDS anemic patients who consulted various specialties in the Düsseldorf university hospital. RESULTS: Based on hemoglobin level, leukocyte and platelet count, mean corpuscular volume, absolute neutrophil count, absolute monocyte count, glucose and creatinine, plus the patients' gender and age, we could not reproduce a high negative predictive value (NPV), but confirmed a useful specificity of 90.9% and a positive predictive value (PPV) of 77.1%. 1192 of 1378 controls were correctly categorized as "probably not MDS (pnMDS)" patients. A total of 65 patients were wrongly classified as "probable MDS (pMDS)," of whom 48 had alternative explanations for their altered laboratory results. In a second analysis, we included 29 patients with chronic myelomonocytic leukemia (CMML) resulting in only one label as possible MDS, suggesting that highly proliferative bone marrow disorders are correctly excluded. CONCLUSION: The possibility of reliably excluding MDS from differential diagnosis based on peripheral blood lab work appears to be attractive for patients and physicians alike while the confirmation of MDS diagnosis still requires a bone marrow biopsy.
Subject(s)
Algorithms , Myelodysplastic Syndromes , Humans , Myelodysplastic Syndromes/diagnosis , Myelodysplastic Syndromes/blood , Female , Male , Aged , Middle Aged , Diagnosis, Differential , Aged, 80 and over , Sensitivity and SpecificityABSTRACT
Orbital tumours include a variety of orbital diseases of different origins. In the case of malignant orbital tumours, early detection is important so that treatment can be initiated promptly. Neuroradiological imaging, in particular magnetic resonance imaging (MRI), plays an important role in the diagnostic of orbital tumours. In adults, lymphoproliferative diseases, inflammations and secondary orbital tumours are most frequently found, whereas in children mostly dermoid cysts, optic gliomas and capillary haemangiomas are found. Optic glioma is a pilocytic astrocytoma and accounts for two thirds of all primary optic tumours. Optic nerve sheath meningiomas mostly affect middle-aged women. In childhood, retinoblastoma is the most common intraocular tumour. This is an aggressive malignant tumour which can occur unilaterally or bilaterally. Based on the imaging findings, differential diagnoses can usually be easily narrowed down using criteria such as age of manifestation, frequency, localisation and imaging characteristics.
Subject(s)
Meningeal Neoplasms , Optic Nerve Glioma , Optic Nerve Neoplasms , Orbital Diseases , Orbital Neoplasms , Retinal Neoplasms , Adult , Child , Middle Aged , Humans , Female , Orbital Neoplasms/diagnostic imaging , Orbital Neoplasms/therapy , Orbital Diseases/diagnosis , Optic Nerve Neoplasms/diagnostic imaging , Optic Nerve Neoplasms/therapyABSTRACT
Artificial intelligence (AI), particularly ChatGPT, developed by OpenAI (San Francisco, CA, USA), is making significant strides in the medical field. In a simulated case study, a 66-year-old Japanese female patient's dialogue with a physician was transcribed and inputted into ChatGPT to assess its efficacy in drafting medical records, formulating differential diagnoses, and establishing treatment plans. The results showed a high similarity between the medical summaries generated by ChatGPT and those of the attending physician. This suggests that ChatGPT has the potential to assist physicians in clinical reasoning and reduce the administrative burden, allowing them to spend more time with patients. However, there are limitations, such as the system's reliance on linguistic data and occasional inaccuracies. Despite its potential, the ethical implications of using patient data and the risk of AI replacing clinicians emphasize the need for continuous evaluation, rigorous oversight, and the establishment of comprehensive guidelines. As AI continues to integrate into healthcare, it is crucial for physicians to ensure that technology complements, rather than replaces, human expertise, with the primary focus remaining on delivering high-quality patient care.
ABSTRACT
The complex structure of the liver and its elaborate hemodynamics can cause hepatic pseudolesions on contrast-enhanced imaging, making the interpretation of diagnostic liver imaging challenging. Aberrant gastric veins are rare; most of their epidemiology data comes from small single-center studies. While current literature suggests that pseudolesions originating from aberrant gastric veins mainly present as hyperdense defects, some cases can also show up as hypodense, as shown in these cases. Differences in flow rates between the portal and aberrant veins and the timing of the scans could explain this contradiction. Identifying aberrant gastric veins on cross-sectional imaging is crucial because they could be misdiagnosed as liver lesions, granting further unnecessary workups or invasive procedures. Aberrant gastric veins can also act as pathways for the spread of gastric cancer. This manuscript presents one aberrant right gastric vein and two aberrant left gastric veins causing hepatic pseudolesions.
ABSTRACT
Neurofilament light chain has become a promising biomarker for neuroaxonal injury; however, its diagnostic utility is limited to chronic disorders or specific contexts. Alteration of consciousness is a common clinical problem with diverse aetiologies, many of which require timely diagnoses. We evaluated the value of neurofilament light chain alone, as well as creating diagnostic models, in distinguishing causes of alteration of consciousness. Patients presenting with alteration of consciousness were enrolled. Initial clinical data of each participant were evaluated by a neurologist to give a provisional diagnosis. Each participant subsequently received advanced investigations and follow-up to conclude the final diagnosis. All diagnoses were classified into a structural or non-structural cause of alteration of consciousness. Plasma and cerebrospinal fluid levels of neurofilament light chain were measured. Cerebrospinal fluid neurofilament light chain and other clinical parameters were used to develop logistic regression models. The performance of cerebrospinal fluid neurofilament light chain, the neurologist's provisional diagnosis, and the model to predict the final diagnosis were compared. For the results, among 71 participants enrolled, 67.6% and 32.4% of their final diagnoses were classified as structural and non-structural, respectively. Cerebrospinal fluid neurofilament light chain demonstrated an area under the curve of 0.75 (95% confidence interval 0.63-0.88) which was not significantly different from a neurologist's provisional diagnosis 0.85 (95% confidence interval 0.75-0.94) (P = 0.14). The multivariable regression model using cerebrospinal fluid neurofilament light chain and other basic clinical data achieved an area under the curve of 0.90 (95% confidence interval 0.83-0.98). In conclusion, neurofilament light chain classified causes of alteration of consciousness with moderate accuracy. Nevertheless, including other basic clinical data to construct a model improved the performance to a level that was comparable to clinical neurologists.
ABSTRACT
The present study describes a case of cystic neutrophilic granulomatous mastitis. The clinical and radiological findings of the patient were consistent with idiopathic granulomatous mastitis. Cystic neutrophilic granulomatous mastitis is a rare subtype of mastitis with a distinct histological pattern that is associated with the Corynebacterium species. The diagnosis and treatment of cystic neutrophilic granulomatous mastitis remains a significant challenge due to the scarcity of available data. The present study describes a classic case of cystic neutrophilic granulomatous mastitis that includes clinical, radiological and histopathological findings. To the best of our knowledge, this is the first case documenting radiological findings before and after treatment. This report encourages the consideration of this entity in the differential diagnoses of mastitis.
ABSTRACT
Backgrounds: Differentiation between benign and malignant diseases in EBV-positive patients poses a significant challenge due to the lack of efficient diagnostic tools. Metagenomic Next-Generation Sequencing (mNGS) is commonly used to identify pathogens of patients with fevers of unknown-origin (FUO). Recent studies have extended the application of Next-Generation Sequencing (NGS) in identifying tumors in body fluids and cerebrospinal fluids. In light of these, we conducted this study to develop and apply metagenomic methods to validate their role in identifying EBV-associated malignant disease. Methods: We enrolled 29 patients with positive EBV results in the cohort of FUO in the Department of Infectious Diseases of Huashan Hospital affiliated with Fudan University from 2018 to 2019. Upon enrollment, these patients were grouped for benign diseases, CAEBV, and malignant diseases according to their final diagnosis, and CNV analysis was retrospectively performed in 2022 using samples from 2018 to 2019. Results: Among the 29 patients. 16 of them were diagnosed with benign diseases, 3 patients were diagnosed with CAEBV and 10 patients were with malignant diseases. 29 blood samples from 29 patients were tested for mNGS. Among all 10 patients with malignant diagnosis, CNV analysis suggested neoplasms in 9 patients. Of all 19 patients with benign or CAEBV diagnosis, 2 patients showed abnormal CNV results. The sensitivity and specificity of CNV analysis for the identification for tumors were 90% and 89.5%, separately. Conclusions: The application of mNGS could assist in the identification of microbial infection and malignancies in EBV-related diseases. Our results demonstrate that CNV detection through mNGS is faster compared to conventional oncology tests. Moreover, the convenient collection of peripheral blood samples adds to the advantages of this approach.
Subject(s)
Epstein-Barr Virus Infections , Fever of Unknown Origin , Neoplasms , Humans , Herpesvirus 4, Human/genetics , Epstein-Barr Virus Infections/complications , Epstein-Barr Virus Infections/diagnosis , Metagenomics , Retrospective Studies , Neoplasms/complications , Neoplasms/diagnosisABSTRACT
BACKGROUND: Extraskeletal myxoid chondrosarcoma (EMC) is a rare malignant tumor described in the head and neck region, especially in the gingival. We present one case arising in the gingival of right mandible, and briefly reviewed the related literature. CASE PRESENTATION: A 24-year-old male patient with a lesion of 3.5*2.0 cm in buccal gingival of right posterior mandible for 2 months. The tumor was composed of cartilaginous structures and myxoid matrix. Immunohistochemical(IHC) showed that the tumor cells to be positive for vimentin, focally positive for S-100, negative for calponin, SMA, SOX10. The Ki-67 labelling index was 80%. Fluorescent in situ Hybridization (FISH) was positive for NR4A3 rearrangement. CONCLUSIONS: Due to its unusual site and low incidence in the oral region, a combination of histological findings, immunohistochemistry, and molecular pathology as well as differential diagnosis with other diseases should be taken into consideration in the process of clinical diagnosis and treatment.
Subject(s)
Chondrosarcoma , Male , Humans , Young Adult , Adult , In Situ Hybridization, Fluorescence , Chondrosarcoma/genetics , Diagnosis, Differential , MandibleABSTRACT
Hashimoto's thyroiditis (HT) and Graves' disease (GD) are two very common autoimmune thyroid diseases (AITD). In this review, we use "HT in the hyperthyroidism stage" to refer to early HT with clinical manifestations of hyperthyroidism. In clinical practice, it is not easy to distinguish between HT in the hyperthyroidism stage and GD as they exhibit very similar clinical symptoms. The current literature lacks so far studies that systematically compare and summarize hyperthyroidism due to HT and GD from varied aspects. It is necessary to focus on all the clinical indices of HT in the hyperthyroidism stage and GD, for accurate diagnosis. Multiple databases such as PubMed, CNKI, WF Data, and CQVIP Data were used to search the literature concerning HT in the hyperthyroidism stage and GD. The information extracted from the relevant literature was summarized and further analyzed. To differentially diagnose hyperthyroidism as HT or GD, it is recommended to first focus on serological tests, followed by imaging tests, as well as the thyroid I131 uptake index. In pathology, fine needle aspiration cytology (FNAC) is the gold standard for the differential diagnosis of HT and GD. Test results from cellular immunology and genetics could also be used to accurately diagnose between the two diseases, which may be further developed and studied in the future. In this paper, we reviewed and summarized the difference between HT in the hyperthyroidism stage and GD from the following six aspects: blood tests, imaging, thyroid I131 uptake, pathology, cellular immunology, and genetics.
ABSTRACT
Blast trauma results from highly variable events that can lead to similar effects in the skeleton. Clinical literature, which largely focuses on soft tissue, provides limited efficacy for interpreting fully skeletonized cases. Interpretation of skeletal blast trauma is hampered by the low number of fully skeletonized case studies and experimental replication studies, which mainly use nonhuman proxies. The purpose of this study is to discuss fracture patterns on two individuals from WWII as a means to better understand and identify fracture patterns associated with blast trauma. Existing clinical and anthropological criteria are reviewed and applied to two World War II cases, both presumed to exhibit blast trauma based on historical contexts. These case studies exhibit combinations of complicated and extensive signs of blunt-force and projectile trauma, reflecting the diversity of skeletal trauma resulting from blast-related events. This analysis emphasizes the arguably impossible task of establishing a diagnosis based on the available literature and lack of prior knowledge about specific losses. Ultimately, analysts must consider the totality of skeletal trauma, combining biomechanical theory and relevant clinical and anthropological literature to arrive at useful yet defensible assessments of trauma. However, refined criteria and additional studies are needed to assess complicated trauma from blast-related events in anthropological contexts.
Subject(s)
Blast Injuries , Fractures, Bone , Humans , Body Remains , Skeleton , Forensic AnthropologyABSTRACT
Cervical varicosities are dilated cervical veins and are uncommon causes of third-trimester vaginal bleeding. Early identification of patients with cervical varices is critical to prevent postpartum hemorrhage, which increases the risk of maternal morbidity and mortality. This is a case report of a 30-year-old woman, gravida 2 para 1, who presented to the labor and delivery unit at 35 weeks 6 days of gestation with a singleton pregnancy with vaginal bleeding. She underwent a pelvic exam under anesthesia and was found to have a 5x5 cm mass of varicosities protruding from the external cervical os, extending over the anterior vaginal lip to the anterior vaginal fornix. A decision was made to deliver via cesarean section. Intraoperative findings were significant for 800 cc of blood loss and a 5-6 cm right ovarian teratoma, which was excised. The patient received two units of packed red blood cells for acute blood-loss anemia postoperatively. This case is unique as the patient had none of the established risk factors for the development of cervical varices. Due to the risks of hemorrhage, morbidity and mortality, physicians and healthcare providers should include cervical varices in their differential diagnoses of patients who present with vaginal bleeding.