Assessing AI efficacy in medical knowledge tests: A study using Taiwan's internal medicine exam questions from 2020 to 2023.

Background: The aim of this study is to evaluate the ability of generative artificial intelligence (AI) models to handle specialized medical knowledge and problem-solving in a formal examination context. Methods: This research utilized internal medicine exam questions provided by the Taiwan Internal Medicine Society from 2020 to 2023, testing three AI models: GPT-4o, Claude_3.5 Sonnet, and Gemini Advanced models. Rejected queries for Gemini Advanced were translated into French for resubmission. Performance was assessed using IBM SPSS Statistics 26, with accuracy percentages calculated and statistical analyses such as Pearson correlation and analysis of variance (ANOVA) performed to gauge AI efficacy. Results: GPT-4o's top annual score was 86.25 in 2022, with an average of 81.97. Claude_3.5 Sonnet reached a peak score of 88.13 in 2021 and 2022, averaging 84.85, while Gemini Advanced lagged with an average score of 69.84. In specific specialties, Claude_3.5 Sonnet scored highest in Psychiatry (100%) and Nephrology (97.26%), with GPT-4o performing similarly well in Hematology & oncology (97.10%) and Nephrology (94.52%). Gemini's best scores were in Psychiatry (86.96%) and Hematology & Oncology (82.76%). Gemini Advanced models struggled with Neurology, scoring below 60%. Additionally, all models performed better on text-based questions than on image-based ones, without significant differences. Claude 3 Opus scored highest on COVID-19-related questions at 89.29%, followed by GPT-4o at 75.00% and Gemini Advanced at 67.86%. Conclusions: AI models showed varied proficiency across medical specialties and question types. GPT-4o demonstrated higher image-based correction rates. Claude_3.5 Sonnet generally and consistently outperformed others, highlighting significant potential for AI in assisting medical education.

The effect of colchicine on cancer risk in patients with immune-mediated inflammatory diseases: a time-dependent study based on the Taiwan's National Health Insurance Research Database.

BACKGROUND: To determine the effect of colchicine on cancer risk in patients with the immune-mediated inflammatory diseases (IMIDs)-related to colchicine use. METHODS: This is a time-dependent propensity-matched general population study based on the National Health Insurance Research Database (NHIRD) of Taiwan. We identified the IMIDs patients (n = 111,644) newly diagnosed between 2000 and 2012 based on the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM)-274,712, 135, 136.1, 279.49, 518.3, 287.0, 696.0, 696.1, 696.8, 420, 429.4, 710.0, 710.1, 710.3, 710.4, 714.0, 720, 55.0, 55.1, 55.9, 556. INCLUSION CRITERIA: aged ≧ 20 years, if a patient had at least these disease diagnosis requirements within 1 year of follow-up, and, these patients had at least two outpatient visits or an inpatient visit. After propensity-matched according to age, sex, comorbidities, medications and index date, the IMIDs patients enter into colchicine users (N = 16,026) and colchicine nonusers (N = 16,026). Furthermore, time-dependent Cox models were used to analyze cancer risk in propensity-matched colchicine users compared with the nonusers. The cumulative cancer incidence was analyzed using Cox proportional regression analysis. We calculated adjusted hazard ratios (aHRs) and their 95% confidence intervals (95% CIs) for cancer after adjusting for sex, age, comorbidities, and use of medicine including acetylcysteine, medication for smoking cessation such as nicotine replacement medicines (the nicotine patch) and pill medicines (varenicline), anti-inflammatory drugs and immunosuppressant drugs. RESULTS: Comparing the colchicine nonusers, all cancer risk were mildly attenuated, the (aHR (95% CI)) of all cancer is (0.84 (0.55, 0.99)). Meanwhile, the colchicine users were associated with the lower incidence of the colorectal cancer, the (aHRs (95% CI)) is (0.22 (0.19, 0.89)). Those aged < 65 years and male/female having the colchicine users were associated with lower risk the colorectal cancer also. Moreover, the colchicine > 20 days use with the lower aHR for colorectal cancer. CONCLUSION: Colchicine was associated with the lower aHR of the all cancer and colorectal cancer formation in patients with the IMIDs.

Exploring the proficiency of ChatGPT-4: An evaluation of its performance in the Taiwan advanced medical licensing examination.

Background: Taiwan is well-known for its quality healthcare system. The country's medical licensing exams offer a way to evaluate ChatGPT's medical proficiency. Methods: We analyzed exam data from February 2022, July 2022, February 2023, and July 2033. Each exam included four papers with 80 single-choice questions, grouped as descriptive or picture-based. We used ChatGPT-4 for evaluation. Incorrect answers prompted a "chain of thought" approach. Accuracy rates were calculated as percentages. Results: ChatGPT-4's accuracy in medical exams ranged from 63.75% to 93.75% (February 2022-July 2023). The highest accuracy (93.75%) was in February 2022's Medicine Exam (3). Subjects with the highest misanswered rates were ophthalmology (28.95%), breast surgery (27.27%), plastic surgery (26.67%), orthopedics (25.00%), and general surgery (24.59%). While using "chain of thought," the "Accuracy of (CoT) prompting" ranged from 0.00% to 88.89%, and the final overall accuracy rate ranged from 90% to 98%. Conclusion: ChatGPT-4 succeeded in Taiwan's medical licensing exams. With the "chain of thought" prompt, it improved accuracy to over 90%.

Machine Learning and Radiomics of Bone Scintigraphy: Their Role in Predicting Recurrence of Localized or Locally Advanced Prostate Cancer.

BACKGROUND: Machine-learning (ML) and radiomics features have been utilized for survival outcome analysis in various cancers. This study aims to investigate the application of ML based on patients' clinical features and radiomics features derived from bone scintigraphy (BS) and to evaluate recurrence-free survival in local or locally advanced prostate cancer (PCa) patients after the initial treatment. METHODS: A total of 354 patients who met the eligibility criteria were analyzed and used to train the model. Clinical information and radiomics features of BS were obtained. Survival-related clinical features and radiomics features were included in the ML model training. Using the pyradiomics software, 128 radiomics features from each BS image's region of interest, validated by experts, were extracted. Four textural matrices were also calculated: GLCM, NGLDM, GLRLM, and GLSZM. Five training models (Logistic Regression, Naive Bayes, Random Forest, Support Vector Classification, and XGBoost) were applied using K-fold cross-validation. Recurrence was defined as either a rise in PSA levels, radiographic progression, or death. To assess the classifier's effectiveness, the ROC curve area and confusion matrix were employed. RESULTS: Of the 354 patients, 101 patients were categorized into the recurrence group with more advanced disease status compared to the non-recurrence group. Key clinical features including tumor stage, radical prostatectomy, initial PSA, Gleason Score primary pattern, and radiotherapy were used for model training. Random Forest (RF) was the best-performing model, with a sensitivity of 0.81, specificity of 0.87, and accuracy of 0.85. The ROC curve analysis showed that predictions from RF outperformed predictions from other ML models with a final AUC of 0.94 and a p-value of <0.001. The other models had accuracy ranges from 0.52 to 0.78 and AUC ranges from 0.67 to 0.84. CONCLUSIONS: The study showed that ML based on clinical features and radiomics features of BS improves the prediction of PCa recurrence after initial treatment. These findings highlight the added value of ML techniques for risk classification in PCa based on clinical features and radiomics features of BS.

Imaging prediction of KRAS mutation in patients with rectal cancer through deep metric learning using pretreatment [18F]Fluorodeoxyglucose positron emission tomography/computed tomography.

OBJECTIVES: To predict KRAS mutation in rectal cancer (RC) through computer vision of [18F]fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) by using metric learning (ML). METHODS: This study included 160 patients with RC who had undergone preoperative PET/CT. KRAS mutation was identified through polymerase chain reaction analysis. This model combined ML with the deep-learning framework to analyze PET data with or without CT images. The Batch Balance Wrapper framework and K-fold cross-validation were employed during the learning process. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. RESULTS: Genetic alterations in KRAS were identified in 82 (51%) tumors. Both PET and CT images were used, and the proposed model had an area under the ROC curve of 0.836 for its ability to predict a mutation status. The sensitivity, specificity, and accuracy were 75.3%, 79.3%, and 77.5%, respectively. When PET images alone were used, the area under the curve was 0.817, whereas the sensitivity, specificity, and accuracy were 73.2%, 79.6%, and 76.2%, respectively. CONCLUSIONS: The ML model presented herein revealed that baseline 18F-FDG PET/CT images could provide supplemental information to determine KRAS mutation in RC. Additional studies are required to maximize the predictive accuracy. ADVANCES IN KNOWLEDGE: The results of the ML model presented herein indicate that baseline 18F-FDG PET/CT images could provide supplemental information for determining KRAS mutation in RC.The predictive accuracy of the model was 77.5% when both image types were used and 76.2% when PET images alone were used. Additional studies are required to maximize the predictive accuracy.

Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation.

Positron emission tomography and computed tomography with 18F-fluorodeoxyglucose (18F-FDG PET-CT) were used to predict outcomes after liver transplantation in patients with hepatocellular carcinoma (HCC). However, few approaches for prediction based on 18F-FDG PET-CT images that leverage automatic liver segmentation and deep learning were proposed. This study evaluated the performance of deep learning from 18F-FDG PET-CT images to predict overall survival in HCC patients before liver transplantation (LT). We retrospectively included 304 patients with HCC who underwent 18F-FDG PET/CT before LT between January 2010 and December 2016. The hepatic areas of 273 of the patients were segmented by software, while the other 31 were delineated manually. We analyzed the predictive value of the deep learning model from both FDG PET/CT images and CT images alone. The results of the developed prognostic model were obtained by combining FDG PET-CT images and combining FDG CT images (0.807 AUC vs. 0.743 AUC). The model based on FDG PET-CT images achieved somewhat better sensitivity than the model based on CT images alone (0.571 SEN vs. 0.432 SEN). Automatic liver segmentation from 18F-FDG PET-CT images is feasible and can be utilized to train deep-learning models. The proposed predictive tool can effectively determine prognosis (i.e., overall survival) and, thereby, select an optimal candidate of LT for patients with HCC.

Artificial Intelligence of Object Detection in Skeletal Scintigraphy for Automatic Detection and Annotation of Bone Metastases.

BACKGROUND: When cancer has metastasized to bone, doctors must identify the site of the metastases for treatment. In radiation therapy, damage to healthy areas or missing areas requiring treatment should be avoided. Therefore, it is necessary to locate the precise bone metastasis area. The bone scan is a commonly applied diagnostic tool for this purpose. However, its accuracy is limited by the nonspecific character of radiopharmaceutical accumulation. The study evaluated object detection techniques to improve the efficacy of bone metastases detection on bone scans. METHODS: We retrospectively examined the data of 920 patients, aged 23 to 95 years, who underwent bone scans between May 2009 and December 2019. The bone scan images were examined using an object detection algorithm. RESULTS: After reviewing the image reports written by physicians, nursing staff members annotated the bone metastasis sites as ground truths for training. Each set of bone scans contained anterior and posterior images with resolutions of 1024 × 256 pixels. The optimal dice similarity coefficient (DSC) in our study was 0.6640, which differs by 0.04 relative to the optimal DSC of different physicians (0.7040). CONCLUSIONS: Object detection can help physicians to efficiently notice bone metastases, decrease physician workload, and improve patient care.

Neck Lymph Node Recurrence in HNC Patients Might Be Predicted before Radiotherapy Using Radiomics Extracted from CT Images and XGBoost Algorithm.

The five-year overall survival rate of patients without neck lymph node recurrence is over 50% higher than those with lymph node metastasis. This study aims to investigate the prognostic impact of computed tomogram (CT)-based radiomics on the outcome of metastatic neck lymph nodes in patients with head and neck cancer (HNC) receiving definitive radiotherapy or chemoradiotherapy for organ preservation. The pretreatment 18F-FDG PET/CT of 79 HNC patients was retrospectively analyzed with radiomics extractors. The imbalanced data was processed using two techniques: over-sampling and under-sampling, after which the prediction model was established with a machine learning model using the XGBoost algorithm. The imbalanced dataset strategies slightly decreased the specificity but greatly improved the sensitivity. To have a higher chance of predicting neck cancer recurrence, however, clinical data combined with CT-based radiomics provides the best prediction effect. The original dataset performed was as follows: accuracy = 0.76 ± 0.07, sensitivity = 0.44 ± 0.22, specificity = 0.88 ± 0.06. After we used the over-sampling technique, the accuracy, sensitivity, and specificity values were 0.80 ± 0.05, 0.67 ± 0.11, and 0.84 ± 0.05, respectively. Furthermore, after using the under-sampling technique, the accuracy, sensitivity, and specificity values were 0.71 ± 0.09, 0.73 ± 0.13, and 0.70 ± 0.13, respectively. The outcome of metastatic neck lymph nodes in patients with HNC receiving radiotherapy for organ preservation can be predicted based on the results of machine learning. This way, patients can be treated alternatively. A further external validation study is required to verify our findings.

Differentiation Between Malignant and Benign Pulmonary Nodules by Using Automated Three-Dimensional High-Resolution Representation Learning With Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography.

Background: The investigation of incidental pulmonary nodules has rapidly become one of the main indications for 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET), currently combined with computed tomography (PET-CT). There is also a growing trend to use artificial Intelligence for optimization and interpretation of PET-CT Images. Therefore, we proposed a novel deep learning model that aided in the automatic differentiation between malignant and benign pulmonary nodules on FDG PET-CT. Methods: In total, 112 participants with pulmonary nodules who underwent FDG PET-CT before surgery were enrolled retrospectively. We designed a novel deep learning three-dimensional (3D) high-resolution representation learning (HRRL) model for the automated classification of pulmonary nodules based on FDG PET-CT images without manual annotation by experts. For the images to be localized more precisely, we defined the territories of the lungs through a novel artificial intelligence-driven image-processing algorithm, instead of the conventional segmentation method, without the aid of an expert; this algorithm is based on deep HRRL, which is used to perform high-resolution classification. In addition, the 2D model was converted to a 3D model. Results: All pulmonary lesions were confirmed through pathological studies (79 malignant and 33 benign). We evaluated its diagnostic performance in the differentiation of malignant and benign nodules. The area under the receiver operating characteristic curve (AUC) of the deep learning model was used to indicate classification performance in an evaluation using fivefold cross-validation. The nodule-based prediction performance of the model had an AUC, sensitivity, specificity, and accuracy of 78.1, 89.9, 54.5, and 79.4%, respectively. Conclusion: Our results suggest that a deep learning algorithm using HRRL without manual annotation from experts might aid in the classification of pulmonary nodules discovered through clinical FDG PET-CT images.

Rare "Burned-Out" Testicular Mixed Germ Cell Tumor on 18 F-FDG PET/CT.

ABSTRACT: Spontaneous regression of testicular mixed germ cell tumor is rare and is also called burned-out testicular tumor. We herein present the case of a 20-year-old man who was initially diagnosed with metastatic embryonal carcinoma. 18 F-FDG PET/CT demonstrated apparent metastases in the lymph node regions and both lungs. A covert right testicular lesion was noted according to the features on the CT component of PET/CT, which was subsequently confirmed as burned-out testicular mixed germ cell tumor.

18F-Fluciclovine Uptake in Intramuscular Injecting Site of Antiandrogen.

ABSTRACT: 18F-fluciclovine, a radiolabeled amino acid analog, has been approved by US Food and Drug Administration for detecting lesions of biochemical recurrence of prostate adenocarcinoma with PET/CT. However, it is not specific for prostate cancer and has been found to be present in variety of malignant and benign etiologies. We herein present an interesting case of the incidental finding of increasing uptake of 18F-fluciclovine related to intramuscular injection of antiandrogen.

Adjuvant radiotherapy did not increase the risk of coronary heart disease in patients with non-metastatic breast cancer.

OBJECTIVE: Adjuvant radiotherapy (RT) in patients with breast cancer can adversely cause the heart to receive some radiation doses, which may lead to cardiovascular diseases. The results of previous research regarding this issue are not consistent. Therefore, we conducted a nationwide population-based study in Taiwan to evaluate whether adjuvant RT for breast cancer patients increased the risk of developing coronary heart disease (CHD). METHODS: This retrospective cohort study examined data from the National Health Insurance Research Database, Registry for Catastrophic Illness Patients, and Taiwan Cancer Registry Database. We identified 83,733 patients with breast cancer between 1 January 2000 and 31 December 2017. Individuals without breast cancer from the general population were frequency-matched by age and index year with individuals with breast cancer. Participants were followed until the occurrence of a CHD event, the end of follow-up, or patient record removal due to death or withdrawal from the NHI. A Cox proportional hazards regression analysis was conducted to compare the risk of CHD in breast cancer patients with that in patients in the comparison cohort. RESULTS: Compared to breast cancer patients without RT, those who underwent RT had a similar risk of subsequently developing CHD (adjusted hazard ratio, 0.94; 95% confidence interval, 0.87-1.02). Similar results were observed in a subgroup of patients with left-sided breast cancer. However, among patients who received adjuvant RT, those with left-sided breast cancer had a significantly higher risk of CHD than did those with right-sided breast cancer (adjusted hazard ratio, 1.17; 95% confidence interval, 1.04-1.30). Patients who received RT in 2010 or later had a significantly lower risk of CHD compared with those who received RT before 2010 (adjusted hazard ratio, 0.64; 95% confidence interval, 0.45-0.91). Higher prescribed doses of RT to the left-sided breast did not correspond to a higher risk of CHD. CONCLUSION: This large, nationwide cohort study suggests that adjuvant RT in patients with breast cancer did not increase the risk of CHD.

Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer with Metric Learning Using Pretreatment 18F-Fluorodeoxyglucose Positron Emission Tomography.

OBJECTIVES: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT. PATIENTS AND METHODS: This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. RESULTS: In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively. CONCLUSIONS: The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model's predictive value.

Detection of Bone Metastases on Bone Scans through Image Classification with Contrastive Learning.

Patients with bone metastases have poor prognoses. A bone scan is a commonly applied diagnostic tool for this condition. However, its accuracy is limited by the nonspecific character of radiopharmaceutical accumulation, which indicates all-cause bone remodeling. The current study evaluated deep learning techniques to improve the efficacy of bone metastasis detection on bone scans, retrospectively examining 19,041 patients aged 22 to 92 years who underwent bone scans between May 2011 and December 2019. We developed several functional imaging binary classification deep learning algorithms suitable for bone scans. The presence or absence of bone metastases as a reference standard was determined through a review of image reports by nuclear medicine physicians. Classification was conducted with convolutional neural network-based (CNN-based), residual neural network (ResNet), and densely connected convolutional networks (DenseNet) models, with and without contrastive learning. Each set of bone scans contained anterior and posterior images with resolutions of 1024 × 256 pixels. A total of 37,427 image sets were analyzed. The overall performance of all models improved with contrastive learning. The accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve, and negative predictive value (NPV) for the optimal model were 0.961, 0.878, 0.599, 0.712, 0.92 and 0.965, respectively. In particular, the high NPV may help physicians safely exclude bone metastases, decreasing physician workload, and improving patient care.

Plantar fascial fibromatosis and herpes zoster.

PURPOSE: Infection, chronic pain and depression are considered risk factors for herpes zoster (HZ). However, the correlation between plantar fascial fibromatosis (PFF) and HZ remains unknown. This study investigated HZ risk in patients with PFF. METHODS: Data was extracted from the Longitudinal Health Insurance Database 2000, which is a subsample of the Taiwan National Health Insurance (NHI) Research Database and contains 1 million NHI beneficiaries. Between 2000 and 2012, patients diagnosed as having PFF were included in the case cohort. Every case was age and sex-matched with individuals without PFF through 1:4 frequency matching (control cohort). The end of the follow-up was defined as December 31, 2013, the date of HZ diagnosis, death, emigration, or withdrawal from the NHI program. RESULTS: In total, 4,729 patients were diagnosed as having PFF and were matched with 18,916 individuals without PFF. Patients with PFF were 1.23 times more likely to develop HZ than were those without PFF. Among those aged ≥65 years, patients with PFF had a higher HZ risk than did those without PFF (adjusted hazard ratio [aHR] = 1.48). Men with PFF had a significantly higher risk of HZ than did men without PFF (aHR = 1.44). CONCLUSION: Patients with PFF, particularly older and male patients, having a high HZ risk and may thus be vaccinated for HZ.

Time-dependent propensity-matched general population study of the effects of statin use on cancer risk in an interstitial lung disease and pulmonary fibrosis cohort.

OBJECTIVE: To determine the effect of statins on risk of cancer in patients with interstitial lung disease (ILD) and pulmonary fibrosis. SETTING: We retrospectively enrolled patients with ILD and pulmonary fibrosis and divided them into two cohorts by statin use (statin users (n=10 036) and statin non-users (n=10 036)). PARTICIPANTS: We selected patients with ILD and pulmonary fibrosis (N=53 862) from Taiwan's National Health Insurance Research Database. Time-dependent Cox models were used to compare risk of cancer of propensity-matched statin users and non-users. Cumulative cancer incidence was analysed through Cox proportional regression. We calculated adjusted HRs (aHRs) and their 95% CIs for cancer after adjusting for sex, age, comorbidities, and use of inhaled corticosteroids, oral steroids and statins. RESULTS: Compared with statin non-users, the aHRs (95% CIs) for statin users were 0.60 (0.55 to 0.65) for cancer, 0.52 (0.35 to 0.78) for haematological malignancy, 0.52 (0.38 to 0.72) for cancer of the head and neck, 0.73 (0.59 to 0.89) for colorectal cancer, 0.34 (0.26 to 0.43) for liver cancer, 0.39 (0.23 to 0.67) for pancreatic cancer, 0.40 (0.17 to 0.96) for skin cancer, 0.67 (0.52 to 0.87) for breast cancer, 0.27 (0.14 to 0.54) for cervical cancer, 0.37 (0.30 to 0.46) for other immunological cancers, 0.73 (0.54 to 0.98) for bladder/kidney cancer and 0.88 (0.71 to 1.09) for lung cancer. CONCLUSION: Statin use is associated with lower risk of cancer in the ILD and pulmonary fibrosis cohort.

Association of antihypertensives during hospitalisation with acute respiratory failure in patients with viral pneumonia: A population-based case-control study.

BACKGROUND: We aimed to identify associations between the risk of acute respiratory failure (ARF) and types of antihypertensive agents in patients with viral pneumonia. METHODS: In this case-control study, data extracted from the Taiwan National Health Insurance Research Database were analysed. The base population comprised patients with viral pneumonia treated from 2000 to 2013. The case group comprised patients with ARF and the control group comprised participants without ARF. Adjusted odds ratios (ORs) were calculated using a multivariable logistic regression model. RESULTS: In total, 4427 viral pneumonia patients with ARF and 4427 matched control participants without ARF were recruited. Patients with diabetes, alcohol-related disease, asthma, chronic kidney disease or end-stage renal disease, chronic obstructive pulmonary disease, cancer, congestive heart failure, stroke, acute pulmonary oedema and shock had increased odds of developing ARF, especially shock (adjusted OR = 49.3; 95% CI = 27.4, 88.7), cancer (12.6; 8.67, 18.2) and stroke (7.51; 5.32, 10.6). Increasing odds of developing ARF were noted in patients using potassium-sparing diuretics (2.95; 1.54, 5.64), loop diuretics (68.2; 48.1, 96.6), calcium channel blockers (1.64; 1.26, 2.13) and angiotensin-converting enzyme inhibitors (1.70; 1.15, 2.53). Patients with prescriptions of α-blockers (0.44; 0.26, 0.74), ß-blockers (0.37; 0.26, 0.52), thiazides (0.38; 0.25, 0.59) and angiotensin receptor blockers (0.65; 0.51, 0.83) had lower odds of having ARF. CONCLUSION: Patients with viral pneumonia who received α-blockers, ß-blockers, thiazides or angiotensin receptor blockers during hospitalisation had a lower risk of developing ARF.

Risk of diabetes mellitus in patients with prostate cancer receiving injection therapy: A nationwide population-based propensity score-matched study.

OBJECTIVES: We aimed to investigate whether the risk of diabetes mellitus (DM) is heightened in patients with prostate cancer receiving injection therapy. METHODS: Men diagnosed with prostate cancer between 2000 and 2012 were included in the case cohort, and men without prostate cancer were included as controls. Each patient with prostate cancer was matched with a control patient with the same index year, demographic variables and comorbidities, and comparisons were made using propensity score matching. The hazard ratio of DM was estimated using the Cox proportional hazards model. RESULTS: This cohort study consisted of 1213 patients with prostate cancer and 1213 control patients. The risk of DM in patients with prostate cancer was 1.60 times (95% CI = 1.12, 2.27) that of patients without prostate cancer. Compared with the controls, the hazard ratios of DM for patients with prostate cancer not receiving oral hormone therapy, patients with prostate cancer receiving oral hormone therapy, and patients with prostate cancer not receiving injection hormone therapy were 1.65 (95% CI = 1.01, 2.70), 1.57 (95% CI = 1.07, 2.70), and 1.94 (95% CI = 1.34, 2.81), respectively. The risk of DM in patients who received injection hormone therapy was 0.45 times (95% CI = 0.25, 0.82) that of patients who did not receive injection hormone therapy. CONCLUSION: Patients with prostate cancer had an increased risk of DM compared with patients without prostate cancer. Patients with prostate cancer who received injection therapy had a lower risk of DM compared with those who did not.

Lesion-Based Bone Metastasis Detection in Chest Bone Scintigraphy Images of Prostate Cancer Patients Using Pre-Train, Negative Mining, and Deep Learning.

This study aimed to explore efficient ways to diagnose bone metastasis early using bone scintigraphy images through negative mining, pre-training, the convolutional neural network, and deep learning. We studied 205 prostate cancer patients and 371 breast cancer patients and used bone scintigraphy data from breast cancer patients to pre-train a YOLO v4 with a false-positive reduction strategy. With the pre-trained model, transferred learning was applied to prostate cancer patients to build a model to detect and identify metastasis locations using bone scintigraphy. Ten-fold cross validation was conducted. The mean sensitivity and precision rates for bone metastasis location detection and classification (lesion-based) in the chests of prostate patients were 0.72 ± 0.04 and 0.90 ± 0.04, respectively. The mean sensitivity and specificity rates for bone metastasis classification (patient-based) in the chests of prostate patients were 0.94 ± 0.09 and 0.92 ± 0.09, respectively. The developed system has the potential to provide pre-diagnostic reports to aid in physicians' final decisions.

Complications of Outpatient and Inpatient Renal Biopsy: A Systematic Review and Meta-Analysis.

Background: The evidence indicates that the optimal observation period following renal biopsy ranges between 6 and 8 h. This systematic review and meta-analysis explored whether differences exist in the complication rates of renal biopsies performed in outpatient and inpatient settings. Methods: We searched the MEDLINE, EMBASE, and the Cochrane Database of Systematic Reviews from 1985 to February 2020. Two reviewers independently selected studies evaluating the bleeding risk from renal biopsies performed in outpatient and inpatient settings and reviewed their full texts. The primary and secondary outcomes were risks of bleeding and major events (including mortality) following the procedure, respectively. Subgroup analysis was conducted according to the original study design (i.e., prospective or retrospective). Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated using a random effect meta-analysis. Heterogeneity was assessed using the I2 test. Results: Data from all 10 eligible studies, which included a total of 1801 patients and 203 bleeding events, were included for analysis. Renal biopsies in outpatient settings were not associated with a higher bleeding risk than those in inpatient settings (OR = 0.81; 95% CI, 0.59-1.11; I2 = 0%). The risk of major events was also comparable across both groups (OR = 0.45; 95% CI, 0.16-1.29; I2 = 4%). Conclusions: Similar rates of bleeding and major events following renal biopsy in outpatient and inpatient settings were observed.