Performance of large language models on benign prostatic hyperplasia frequently asked questions.

BACKGROUND: Benign prostatic hyperplasia (BPH) is a common condition, yet it is challenging for the average BPH patient to find credible and accurate information about BPH. Our goal is to evaluate and compare the accuracy and reproducibility of large language models (LLMs), including ChatGPT-3.5, ChatGPT-4, and the New Bing Chat in responding to a BPH frequently asked questions (FAQs) questionnaire. METHODS: A total of 45 questions related to BPH were categorized into basic and professional knowledge. Three LLM-ChatGPT-3.5, ChatGPT-4, and New Bing Chat-were utilized to generate responses to these questions. Responses were graded as comprehensive, correct but inadequate, mixed with incorrect/outdated data, or completely incorrect. Reproducibility was assessed by generating two responses for each question. All responses were reviewed and judged by experienced urologists. RESULTS: All three LLMs exhibited high accuracy in generating responses to questions, with accuracy rates ranging from 86.7% to 100%. However, there was no statistically significant difference in response accuracy among the three (p > 0.017 for all comparisons). Additionally, the accuracy of the LLMs' responses to the basic knowledge questions was roughly equivalent to that of the specialized knowledge questions, showing a difference of less than 3.5% (GPT-3.5: 90% vs. 86.7%; GPT-4: 96.7% vs. 95.6%; New Bing: 96.7% vs. 93.3%). Furthermore, all three LLMs demonstrated high reproducibility, with rates ranging from 93.3% to 97.8%. CONCLUSIONS: ChatGPT-3.5, ChatGPT-4, and New Bing Chat offer accurate and reproducible responses to BPH-related questions, establishing them as valuable resources for enhancing health literacy and supporting BPH patients in conjunction with healthcare professionals.

Native top-down mass spectrometry for higher-order structural characterization of proteins and complexes.

Progress in structural biology research has led to a high demand for powerful and yet complementary analytical tools for structural characterization of proteins and protein complexes. This demand has significantly increased interest in native mass spectrometry (nMS), particularly native top-down mass spectrometry (nTDMS) in the past decade. This review highlights recent advances in nTDMS for structural research of biological assemblies, with a particular focus on the extra multi-layers of information enabled by TDMS. We include a short introduction of sample preparation and ionization to nMS, tandem fragmentation techniques as well as mass analyzers and software/analysis pipelines used for nTDMS. We highlight unique structural information offered by nTDMS and examples of its broad range of applications in proteins, protein-ligand interactions (metal, cofactor/drug, DNA/RNA, and protein), therapeutic antibodies and antigen-antibody complexes, membrane proteins, macromolecular machineries (ribosome, nucleosome, proteosome, and viruses), to endogenous protein complexes. The challenges, potential, along with perspectives of nTDMS methods for the analysis of proteins and protein assemblies in recombinant and biological samples are discussed.

Super-resolution ultrasound and microvasculomics: a consensus statement.

This is a summary of a consensus statement on the introduction of "Ultrasound microvasculomics" produced by The Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound. The evaluation of microvessels is a very important part for the assessment of diseases. Super-resolution ultrasound (SRUS) microvascular imaging surpasses traditional ultrasound imaging in the morphological and functional analysis of microcirculation. SRUS microvascular imaging relies on contrast microbubbles to gain sensitivity to microvessels and improves the spatial resolution of ultrasound blood flow imaging for a more detailed depiction of vascular structures and hemodynamics. This method has been applied in preclinical animal models and pilot clinical studies, involving areas including neurology, oncology, nephrology, and cardiology. However, the current quantitative parameters of SRUS images are not enough for precise evaluation of microvessels. Therefore, by employing omics methods, more quantification indicators can be obtained, enabling a more precise and personalized assessment of microvascular status. Ultrasound microvasculomics - a high-throughput extraction of image features from SRUS images - is one novel approach that holds great promise but needs further validation in both bench and clinical settings. CLINICAL RELEVANCE STATEMENT: Super-resolution Ultrasound (SRUS) blood flow imaging improves spatial resolution. Ultrasound microvasculomics is possible to acquire high-throughput information of features from SRUS images. It provides more precise and abundant micro-blood flow information in clinical medicine. KEY POINTS: This consensus statement reviews the development and application of super-resolution ultrasound (SRUS). The shortcomings of the current quantification indicators of SRUS and strengths of the omics methodology are addressed. "Ultrasound microvasculomics" is introduced for a high-throughput extraction of image features from SRUS images.

Volume reduction rate of radiofrequency ablation in ≤ 2 cm Bethesda IV thyroid nodules.

OBJECTIVE: This prospective observational study aimed to evaluate the efficacy of radiofrequency ablation (RFA) in treating ≤ 2 cm thyroid nodules with Bethesda IV cytology and C-TIRADS 4A categorization. Additionally, the factors influencing the completed absorption of ablation (CAA) were examined. METHODS: A total of 62 cases with 62 nodules underwent ultrasound-guided RFA and were included in the study. The volume reduction rate (VRR), CAA, and incomplete absorption of ablation (IAA) were assessed at the 1st, 3rd, 6th, and subsequent 6-month follow-ups. Clinical and ultrasound features were compared between the CAA and IAA groups at the 12th month follow-up. RESULTS: The average VRR at the 1st, 3rd, 6th, 12th month, and last follow-up were -88.6%, 16.0%, 59.7%, 82.0%, and 98.2%, respectively. More than half of the nodules achieved a 90% VRR after 1 year of RFA, with 88.7% demonstrating CAA at the end of the study (follow-up duration of 14 to 63 months). Nodules with grade 3 vascularity and those associated with chronic thyroiditis showed delayed CAA at the 12th month follow-up (p = 0.036 and 0.003, respectively). CONCLUSION: RFA is an effective technique for treating ≤ 2 cm thyroid nodules with Bethesda IV cytology and C-TIRADS 4A categorization. Nodules with grade 3 blood supply and patients with chronic thyroiditis exhibited an impact on the completed absorption following RFA. CLINICAL RELEVANCE STATEMENT: Our study has shown that radiofrequency ablation is an effective treatment for ≤ 2 cm thyroid nodules classified as Bethesda IV cytology. However, we identified that high vascularity of the nodule and chronic thyroiditis are adverse factors affecting the completed absorption of the ablation. KEY POINTS: •Radiofrequency ablation (RFA) is an effective technique for treatment of ≤ 2 cm Bethesda IV category thyroid nodules. •Higher blood supply and chronic thyroiditis influence the completed absorption after RFA.

Comparison of the efficacy and safety of ultrasound-guided radiofrequency ablation and microwave ablation for the treatment of unifocal papillary thyroid microcarcinoma: a retrospective study.

PURPOSE: This study aimed to compare the efficacy and safety of ultrasound-guided RFA and MWA in the treatment of unifocal PTMC. METHODS: This retrospective study included 512 patients with 512 unifocal papillary thyroid microcarcinomas (PTMCs) who underwent RFA (n = 346) and MWA (n = 166) between January 2021 and December 2021. The volumes of the ablation areas were measured during follow-up, and the volume reduction rates were evaluated. The ablation duration, volume of hydrodissection, and ablation-related complications were also compared between the groups. RESULTS: All lesions received complete ablation and no local or distant recurrences were observed in the two groups. A larger volume of isolation liquid was used for RFA than for MWA (p = 0.000). Hoarseness occurred in seven patients who underwent RFA (p = 0.102). At the 1-week follow-up, the mean volume of the areas ablated by RFA was smaller than that of the areas ablated by MWA (p = 0.049). During follow-ups at months 3, 9, 12, 15, and 18, the mean volumes of the ablated areas were larger in the RFA group than in the MWA group (all, p < 0.05). The mean volume of the ablated lesions increased slightly at the 1-week follow-up and then decreased at 1 month after ablation in both groups. The absorption curve of the ablated lesions in the RFA group was similar to that in the MWA group. CONCLUSIONS: RFA and MWA are both efficient and safe methods for treating unifocal PTMC. They may be alternative techniques for patients who are not eligible or are unwilling to undergo surgery.

Drug loading techniques for exosome-based drug delivery systems.

Exosomes are bilayer membrane-coated extracellular vesicles measuring between 40 and 100 nm in diameter. As a natural carrier, exosomes have the advantages of low immunogenicity, high stability in blood, and direct delivery of drugs to cells. Exosomes can be transported between cells and thus are conducive to the exchange of substances and information between cells. They change the functional state of recipient cells by loading exogenous drugs (e.g., small-molecule drugs, transmembrane proteins, and nucleic acid drugs). The key to using exosomes as drug carriers is the effective loading of exogenous drugs into exosomes; however, this task poses a challenge in studying the functionalization of exosomes as drug carriers. Currently, sonication, electroporation, transfection, incubation, extrusion, saponin-assisted loading, transgenesis, freeze-thaw cycles, thermal shock, pH gradient method, and hypotonic dialysis have been applied to load these drugs into exosomes. This review aims to provide an overview of the advantages and disadvantages of various drug loading technologies for exosomes.

Application of Contrast-Enhanced Ultrasound in the Diagnosis of Ductal Carcinoma In Situ: Analysis of 127 Cases.

OBJECTIVES: To explore the characteristics of breast ductal carcinoma in situ (DCIS) on real-time grayscale contrast-enhanced ultrasound (CEUS) imaging and the diagnostic value of CEUS in DCIS. METHODS: A total of 127 histopathologically confirmed DCIS lesions and 124 fibroadenomas (FAs; controls) were subjected to conventional ultrasound and CEUS. Next, the CEUS findings of DCIS and FA lesions, including morphologic features and quantitative parameters, were analyzed. RESULTS: Binary logistic regression was used to identify the independent risk factors from DCIS and FA lesions detected by CEUS. Contrast-enhanced ultrasound revealed significant differences between DCIS and FA. The wash-in time, enhancement mode, enhancement intensity, blood perfusion defects, peripheral high enhancement, enhancement scope, intratumoral vessels and their courses and dilatation degree, and penetrating vessels on CEUS were identified as features correlated with DCIS (P < .05). Moreover, a multivariate logistic regression analysis was developed, and the area under receiver operating characteristic curve of each index was generated, including the wash-in time, enhancement intensity, blood perfusion defects, enhancement scope, penetrating vessels, arrival time, and peak intensity (P < .05; area under the curve, >0.6). CONCLUSIONS: The contrast-enhancement patterns and DCIS parameters appeared different from FA lesions, thus suggesting that CEUS can be very useful in distinguishing DCIS from FA lesions.

A computer-aided diagnosing system in the evaluation of thyroid nodules-experience in a specialized thyroid center.

BACKGROUND: The evaluation of thyroid nodules with ultrasonography has created a large burden for radiologists. Artificial intelligence technology has been rapidly developed in recent years to reduce the cost of labor and improve the differentiation of thyroid malignancies. This study aimed to investigate the diagnostic performance of a novel computer-aided diagnosing system (CADs: S-detect) for the ultrasound (US) interpretation of thyroid nodule subtypes in a specialized thyroid center. METHODS: Our study prospectively included 180 thyroid nodules that underwent ultrasound interpretation. The CADs and radiologist assessed all nodules. The ultrasonographic features of different subtypes were analyzed, and the diagnostic performances of the CADs and radiologist were compared. RESULTS: There were seven subtypes of thyroid nodules, among which papillary thyroid cancer (PTC) accounted for 50.6% and follicular thyroid carcinoma (FTC) accounted for 2.2%. Among all thyroid nodules, the CADs presented a higher sensitivity and lower specificity than the radiologist (90.5% vs 81.1%; 41.2% vs 83.5%); the radiologist had a higher accuracy than the CADs (82.2% vs 67.2%) for diagnosing malignant thyroid nodules. The accuracy of the CADs was not as good as that of the radiologist in diagnosing PTCs (70.9% vs 82.1%). The CADs and radiologist presented accuracies of 43.8% and 60.9% in identifying FTCs, respectively. CONCLUSIONS: The ultrasound CADs presented a higher sensitivity for identifying malignant thyroid nodules than experienced radiologists. The CADs was not as good as experienced radiologists in a specialized thyroid center in identifying PTCs. Radiologists maintained a higher specificity than the CADs for FTC detection.

CHL1 expression differentiates Hürthle cell carcinoma from benign Hürthle cell nodules.

BACKGROUND AND OBJECTIVES: Hürthle cell carcinoma (HCC) is an unusual and relatively rare type of differentiated thyroid cancer. Currently, cytologic analysis of fine-needle aspiration biopsy is limited in distinguishing benign Hürthle cell neoplasms from malignant ones. The aim of this study was to determine whether differences in the expression of specific genes could differentiate HCC from benign Hürthle cell nodules by evaluating differential gene expression in Hürthle cell disease. METHODS: Eighteen benign Hürthle cell nodules and seven HCC samples were analyzed by whole-transcriptome sequencing. Bioinformatics analysis was carried out to identify candidate differentially expressed genes. Expression of these candidate genes was re-examined by quantitative real-time polymerase chain reaction (qRT-PCR). Protein expression was quantified by immunohistochemistry. RESULTS: Close homolog of L1 (CHL1) was identified as overexpressed in HCC. CHL1 was found to have greater than 15-fold higher expression in fragments per kilobase million in HCC compared with benign Hurthle cell tumors. This was confirmed by qRT-PCR. Moreover, the immunoreactivity score of the CHL1 protein was significantly higher in HCC compared with benign Hürthle cell nodules. CONCLUSIONS: CHL1 expression may represent a novel and useful prognostic biomarker to distinguish HCC from benign Hürthle cell disease.

Analysis of three ultrasound elastography techniques for grading liver fibrosis in patients with chronic hepatitis B.

BACKGROUND: Evaluation of liver fibrosis is important to assess prognosis and guide the treatment for chronic hepatitis B. OBJECTIVE: To analyze and compare transient, point, and two-dimensional (2D) shear wave elastography techniques in grading the liver fibrosis. METHODS: Based on the severity of liver inflammation and fibrosis (Scheuer criteria), 158 patients with chronic hepatitis B were assigned into group 1 (either G or S classification < 2) or group 2 (either G or S classification ≥ 2). Group 2 patients commonly require anti-viral treatment. All patients received transient (FibroScan), point (STQ), and 2D (STE) elastography examinations. Receiver operating characteristic curves were calculated from three elastography techniques in individual or in combination. RESULTS: A total of 158 patients were enrolled into the study, with 39.2% (62) female and mean age of 42.8 (standard deviation 19.1) years old. Transient elastography could not differentiate between group 1 and group 2 patients (P = 0.12), whereas point and 2D elastography examinations could distinguish patients in group 1 from group 2 (P < 0.01 for both STQ and STE). Administration of combined three elastography techniques showed the best diagnostic accuracy (90.1%) for liver fibrosis, which was confirmed with hepatic biopsy examination. CONCLUSION: Point and 2D elastography were superior to transient elastography to detect liver fibrosis and guide clinical anti-viral treatment. Analysis of combined transient, point, and 2D elastography techniques showed the better diagnostic accuracy for liver fibrosis.

Long noncoding RNA papillary thyroid carcinoma susceptibility candidate 3 (PTCSC3) inhibits proliferation and invasion of glioma cells by suppressing the Wnt/ß-catenin signaling pathway.

BACKGROUND: The dysregulation of long noncoding RNAs (lncRNAs) has been identified in a variety of cancers. An increasing number of studies have found the critical role of lncRNAs in the regulation of cellular processes, such as proliferation, invasion and differentiation. Long noncoding RNA papillary thyroid carcinoma susceptibility candidate 3 (PTCSC3) is a novel lncRNA that was primarily detected in papillary thyroid carcinoma. However, the biological function and molecular mechanism of lncRNA PTCSC3 in glioma are still unknown. METHODS: The expression level of lncRNA PTCSC3 in human microglia and glioma cell lines was examined using quantitative real-time polymerase chain reaction (qRT-PCR). The influence of lncRNA PTCSC3 on cell proliferation were studied using the cell counting kit-8, and cell cycle and apoptosis were analyzed by flow cytometry assays. The migration and invasion abilities were investigated by transwell and wound healing assays. The target genes of lncRNA PTCSC3 were explored by qRT-PCR, immunofluorescence and western blot. RESULTS: LncRNA PTCSC3 was significantly downregulated in glioma cell lines. The overexpression of lncRNA PTCSC3 suppressed proliferation and induced apoptosis in U87 and U251 cells. Additionally, the overexpression of lncRNA PTCSC3 inhibited the migration and invasion of U87 and U251 cells. Moreover, lncRNA PTCSC3 inhibited the epithelial-mesenchymal transition of U87 cells. The study also demonstrated that LRP6, as a receptor of the Wnt/ß-catenin pathway, was a target of lncRNA PTCSC3. By evaluating the expression levels of Axin1, active ß-catenin, c-myc, and cyclin D1, the study indicated that lncRNA PTCSC3 inhibited the activation of the Wnt/ß-cateninpathway through targeting LRP6. CONCLUSIONS: LncRNA PTCSC3 inhibits the proliferation and migration of glioma cells and suppresses Wnt/ß-catenin signaling pathway by targeting LRP6. LncRNA PTCSC3 is a potential therapeutic target for treatment of glioma.

Preparation of arginine-modified reduced graphene oxide composite filled in an on-line solid-phase extraction disk and its application in the analysis of heterocyclic aromatic amines.

An arginine-modified reduced graphene oxide composite was prepared in an on-line solid-phase extraction disk and coupled to high-performance liquid chromatography for the re-enrichment of heterocyclic aromatic amines. The synthetic composite presented an excellent adsorption capability because of the ultrahigh active surface area of graphene and the abundant alkaline groups of arginine. The adsorption capacity of it was 52.7 mg 2-amino-3-methyl-imidazo[4,5-f]-quinoline per gram, nearly twice that of threonine-modified reduced graphene oxide composite, glutamic acid modified reduced graphene oxide composite, and reduced graphene oxide. This on-line method was successfully applied to the detection of a series of heterocyclic aromatic amines in beef jerky. After clean-up and re-enrichment of the on-line solid-phase extraction disk, the chromatographic background of the sample was low and the shape of chromatographic peaks was sharp. The method detection limit was in the range of 0.30-0.49 ng/g, and the recovery was in the range of 82.0-111.5%.

Exploratory study on association of single-nucleotide polymorphisms with hydromorphone analgesia in ED.

OBJECTIVES: The objective of this study is to provide information on distribution of important single-nucleotide polymorphisms (SNPs) and evaluate their associations with clinical response to intravenous hydromorphone in emergency department. METHODS: A prospective exploratory study was performed. A convenience sample of adult emergency department patients with acute pain deemed to require intravenous opioids received 1 mg of intravenous hydromorphone. Primary outcome was pain score (numeric rating scale, NRS) reduction between baseline and 30 minutes after medication administration. Secondary outcomes were pain relief, patient satisfaction with analgesia, desire for more analgesics, and side effects (nausea, vomiting, and pruritis). Single-nucleotide polymorphisms in OPRM1 gene (opioid receptor, A118G), ABCB1 gene (opioid transporter, C3435T), COMT gene (pain sensitivity, G1947A), and UGT2B7 gene (opioid metabolism, -G840A) were tested. We used Kruskal-Wallis test to compare the primary outcome and χ(2) test (or Fisher test) to compare the secondary outcomes among patients carrying different SNPs. RESULTS: One thousand four hundred thirty-eight patients were screened, and 163 patients were enrolled in the study. The mean age was 39 years. Sixty-three percent were female, 58% were Hispanic, and 67% had pain located in abdomen. The median pain NRS reduction at 30 minutes was 5 (interquartile range, 3-8). There was no difference in pain NRS reduction among patients carrying different SNPs. Secondary outcome analysis revealed statistically significant associations between patient satisfaction with treatment and OPRM1 and between nausea and UGT2B7. CONCLUSIONS: This exploratory study did not show a significant difference in pain NRS reduction among patients carrying different SNPs. Patient satisfaction with analgesia and nausea were statistically significantly associated with OPRM1 and UGT2B7, respectively.

Prehospital trauma arrival notification associated with more image studies in patients with minor head trauma discharged from ED.

OBJECTIVES: The objective of this study was to determine whether prehospital trauma arrival notification was associated with more head computed tomography (CT) scans and image studies performed in patients with minor head trauma and discharged from emergency department (ED). METHODS: A retrospective cross-sectional study based on hospital electronic medical record was performed. Patients with head trauma indicated by their diagnostic codes or chief complaints, presenting to and discharged from ED in a level I trauma center between January 1, 2010, and June 30, 2014, and triage Glasgow Coma Scale (GCS) score 14 or greater were selected from electronic medical record. Triage prehospital trauma arrival notification, number and types of image studies performed, and basic demographics were extracted. χ(2) Analysis (or Fisher test) was applied to compare the proportions of patients who received image studies between prehospital trauma arrival notification and non-notification groups. RESULTS: There were 3603 patients with head trauma, triage GCS score 14 or greater, and discharged from ED. Mean age was 43.8 years. Forty-six percent was female. Thirty-two point nine percent was Hispanic, and 28.6% was black. Numbers (proportions) of patients who received prehospital trauma arrival notification, head CT scan, or any image study (x-ray, CT, magnetic resonance imaging, or sonogram) were 287 (8.0%), 1621 (45.0%), and 2267 (63.0%), respectively. Compared with patients without prehospital trauma arrival notifications, patients with prehospital trauma arrival notifications were significantly more likely to receive a head CT scan as well as an image study. CONCLUSIONS: Prehospital trauma arrival notification was associated with significantly more head CT scans and more image studies in patients with minor head trauma and discharged from ED.

Does initial hydromorphone relieve pain best if dosing is fixed or weight based?

STUDY OBJECTIVE: It remains unknown whether initial opioid dosing should optimally be fixed or weight-based. We wish to determine whether pain response after an initial fixed dose of intravenous hydromorphone varied by total body weight. METHODS: We enrolled a convenience sample of emergency department adults aged 18 to 65 years with acute pain requiring intravenous opioids and administered 1 mg of hydromorphone. Our primary outcome was the correlation of total body weight with the reduction in pain at 30 minutes, as measured with a numeric rating scale. Our secondary outcomes contrasted total body weight by other measures of efficacy (numeric rating scale <3, pain relief, satisfaction, and desire for more analgesics) and adverse events (nausea, vomiting, and pruritus). We also performed a multivariate analysis to control for variables that might affect the relationship of pain response to total body weight. RESULTS: We enrolled 163 subjects with a range of weights from 45 to 157 kg, and their mean numeric rating scale pain reduction at 30 minutes was 5.3. Pain reduction did not correlate with weight in either univariate or multivariable models. Secondary outcomes were also similar, except greater pruritus in lower-weight subjects. CONCLUSION: Pain response to a fixed 1 mg intravenous dose of hydromorphone did not vary by total body weight in this sample of adults aged 18 to 65 years, suggesting no advantage to weight-based over fixed opioid dosing.

[Application of miRNAs in the occurrence and early diagnosis of pancreatic cancer].

OBJECTIVE: To find the potential serum specific miRNAs with diagnostic value in early pancreatic cancer and study the alteration of miRNAs levels in the process of origin and development of pancreatic cancer and discuss the diagnostic value of miRNAs in early pancreatic cancer. METHODS: DMBA-induced rat model was established. The miRNAs expression profile of early stage was screened out by microarray. And confirmation study was performed. RESULTS: The 35 and 12 abnormally expressed miRNAs were acquired in pancreatic tissue and blood respectively. There were no significant differences between normal pancreas and pancreatic cancer in expressions of hsa-let-7c, hsa-miR-122-5p, hsa-miR-142-5p, hsa-miR-199a-3p and hsa-miR-451a (P > 0.05). CONCLUSIONS: miRNAs are the potential biomarkers of early pancreatic cancer. The establishment of the miRNAs expression profile has build the foundation of exploring the molecular mechanism of origin of pancreatic cancer.

Transforming free-text radiology reports into structured reports using ChatGPT: A study on thyroid ultrasonography.

PURPOSE: The importance of structured radiology reports has been fully recognized, as they facilitate efficient data extraction and promote collaboration among healthcare professionals. Our purpose is to assess the accuracy and reproducibility of ChatGPT, a large language model, in generating structured thyroid ultrasound reports. METHODS: This is a retrospective study that includes 184 nodules in 136 thyroid ultrasound reports from 136 patients. ChatGPT-3.5 and ChatGPT-4.0 were used to structure the reports based on ACR-TIRADS guidelines. Two radiologists evaluated the responses for quality, nodule categorization accuracy, and management recommendations. Each text was submitted twice to assess the consistency of the nodule classification and management recommendations. RESULTS: On 136 ultrasound reports from 136 patients (mean age, 52 years ± 12 [SD]; 61 male), ChatGPT-3.5 generated 202 satisfactory structured reports, while ChatGPT-4.0 only produced 69 satisfactory structured reports (74.3 % vs. 25.4 %, odds ratio (OR) = 8.490, 95 %CI: 5.775-12.481, p < 0.001). ChatGPT-4.0 outperformed ChatGPT-3.5 in categorizing thyroid nodules, with an accuracy of 69.3 % compared to 34.5 % (OR = 4.282, 95 %CI: 3.145-5.831, p < 0.001). ChatGPT-4.0 also provided more comprehensive or correct management recommendations than ChatGPT-3.5 (OR = 1.791, 95 %CI: 1.297-2.473, p < 0.001). Finally, ChatGPT-4.0 exhibits higher consistency in categorizing nodules compared to ChatGPT-3.5 (ICC = 0.732 vs. ICC = 0.429), and both exhibited moderate consistency in management recommendations (ICC = 0.549 vs ICC = 0.575). CONCLUSIONS: Our study demonstrates the potential of ChatGPT in transforming free-text thyroid ultrasound reports into structured formats. ChatGPT-3.5 excels in generating structured reports, while ChatGPT-4.0 shows superior accuracy in nodule categorization and management recommendations.

Harnessing Large Language Models for Structured Reporting in Breast Ultrasound: A Comparative Study of Open AI (GPT-4.0) and Microsoft Bing (GPT-4).

OBJECTIVES: To assess the capabilities of large language models (LLMs), including Open AI (GPT-4.0) and Microsoft Bing (GPT-4), in generating structured reports, the Breast Imaging Reporting and Data System (BI-RADS) categories, and management recommendations from free-text breast ultrasound reports. MATERIALS AND METHODS: In this retrospective study, 100 free-text breast ultrasound reports from patients who underwent surgery between January and May 2023 were gathered. The capabilities of Open AI (GPT-4.0) and Microsoft Bing (GPT-4) to convert these unstructured reports into structured ultrasound reports were studied. The quality of structured reports, BI-RADS categories, and management recommendations generated by GPT-4.0 and Bing were evaluated by senior radiologists based on the guidelines. RESULTS: Open AI (GPT-4.0) was better than Microsoft Bing (GPT-4) in terms of performance in generating structured reports (88% vs. 55%; p < 0.001), giving correct BI-RADS categories (54% vs. 47%; p = 0.013) and providing reasonable management recommendations (81% vs. 63%; p < 0.001). As the ability to predict benign and malignant characteristics, GPT-4.0 performed significantly better than Bing (AUC, 0.9317 vs. 0.8177; p < 0.001), while both performed significantly inferior to senior radiologists (AUC, 0.9763; both p < 0.001). CONCLUSION: This study highlights the potential of LLMs, specifically Open AI (GPT-4.0), in converting unstructured breast ultrasound reports into structured ones, offering accurate diagnoses and providing reasonable recommendations.

Clinical application potential of large language model: a study based on thyroid nodules.

BACKGROUND: Limited data indicated the performance of large language model (LLM) taking on the role of doctors. We aimed to investigate the potential for ChatGPT-3.5 and New Bing Chat acting as doctors using thyroid nodules as an example. METHODS: A total of 145 patients with thyroid nodules were included for generating questions. Each question was entered into chatbot of ChatGPT-3.5 and New Bing Chat five times and five responses were acquired respectively. These responses were compared with answers given by five junior doctors. Responses from five senior doctors were regarded as gold standard. Accuracy and reproducibility of responses from ChatGPT-3.5 and New Bing Chat were evaluated. RESULTS: The accuracy of ChatGPT-3.5 and New Bing Chat in answering Q2, Q3, Q5 were lower than that of junior doctors (all P < 0.05), while both LLMs were comparable to junior doctors when answering Q4 and Q6. In terms of "high reproducibility and accuracy", ChatGPT-3.5 outperformed New Bing Chat in Q1 and Q5 (P < 0.001 and P = 0.008, respectively), but showed no significant difference in Q2, Q3, Q4, and Q6 (P > 0.05 for all). New Bing Chat generated higher accuracy than ChatGPT-3.5 (72.41% vs 58.62%) (P = 0.003) in decision making of thyroid nodules, and both were less accurate than junior doctors (89.66%, P < 0.001 for both). CONCLUSIONS: The exploration of ChatGPT-3.5 and New Bing Chat in the diagnosis and management of thyroid nodules illustrates that LLMs currently demonstrate the potential for medical applications, but do not yet reach the clinical decision-making capacity of doctors.

Ultrasound Viscosity Imaging in Breast Lesions: A Multicenter Prospective Study.

RATIONALE AND OBJECTIVES: To explore and validate the clinical value of ultrasound (US) viscosity imaging in differentiating breast lesions by combining with BI-RADS, and then comparing the diagnostic performances with BI-RADS alone. MATERIALS AND METHODS: This multicenter, prospective study enrolled participants with breast lesions from June 2021 to November 2022. A development cohort (DC) and validation cohort (VC) were established. Using histological results as reference standard, the viscosity-related parameter with the highest area under the receiver operating curve (AUC) was selected as the optimal one. Then the original BI-RADS would upgrade or not based on the value of this parameter. Finally, the results were validated in the VC and total cohorts. In the DC, VC and total cohorts, all breast lesions were divided into the large lesion, small lesion and overall groups respectively. RESULTS: A total of 639 participants (mean age, 46 years ± 14) with 639 breast lesions (372 benign and 267 malignant lesions) were finally enrolled in this study including 392 participants in the DC and 247 in the VC. In the DC, the optimal viscosity-related parameter in differentiating breast lesions was calculated to be A'-S2-Vmax, with the AUC of 0.88 (95% CI: 0.84, 0.91). Using > 9.97 Pa.s as the cutoff value, the BI-RADS was then modified. The AUC of modified BI-RADS significantly increased from 0.85 (95% CI: 0.81, 0.88) to 0.91 (95% CI: 0.87, 0.93), 0.85 (95% CI: 0.80, 0.89) to 0.90 (95% CI: 0.85, 0.93) and 0.85 (95% CI: 0.82, 0.87) to 0.90 (95% CI: 0.88, 0.92) in the DC, VC and total cohorts respectively (P < .05 for all). CONCLUSION: The quantitative viscous parameters evaluated by US viscosity imaging contribute to breast cancer diagnosis when combined with BI-RADS.