Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer.

OBJECTIVES: To investigate the predictive performance of the deep learning radiomics (DLR) model integrating pretreatment ultrasound imaging features and clinical characteristics for evaluating therapeutic response after neoadjuvant chemotherapy (NAC) in patients with breast cancer. METHODS: A total of 603 patients who underwent NAC were retrospectively included between January 2018 and June 2021 from three different institutions. Four different deep convolutional neural networks (DCNNs) were trained by pretreatment ultrasound images using annotated training dataset (n = 420) and validated in a testing cohort (n = 183). Comparing the predictive performance of these models, the best one was selected for image-only model structure. Furthermore, the integrated DLR model was constructed based on the image-only model combined with independent clinical-pathologic variables. Areas under the curve (AUCs) of these models and two radiologists were compared by using the DeLong method. RESULTS: As the optimal basic model, Resnet50 achieved an AUC and accuracy of 0.879 and 82.5% in the validation set. The integrated DLR model, yielding the highest classification performance in predicting response to NAC (AUC 0.962 and 0.939 in the training and validation cohort), outperformed the image-only model and the clinical model and also performed better than two radiologists' prediction (all p < 0.05). In addition, predictive efficacy of the radiologists was improved under the assistance of the DLR model significantly. CONCLUSION: The pretreatment US-based DLR model could hold promise as a clinical guidance for predicting NAC response of patients with breast cancer, thereby providing benefit of timely treatment strategy adjustment to potential poor NAC responders. KEY POINTS: • Multicenter retrospective study showed that deep learning radiomics (DLR) model based on pretreatment ultrasound image and clinical parameter achieved satisfactory prediction of tumor response to neoadjuvant chemotherapy (NAC) in breast cancer. • The integrated DLR model could become an effective tool to guide clinicians in identifying potential poor pathological responders before chemotherapy. • The predictive efficacy of the radiologists was improved under the assistance of the DLR model.

Characterizing Brain Tumor Regions Using Texture Analysis in Magnetic Resonance Imaging.

PURPOSE: To extract texture features from magnetic resonance imaging (MRI) scans of patients with brain tumors and use them to train a classification model for supporting an early diagnosis. METHODS: Two groups of regions (control and tumor) were selected from MRI scans of 40 patients with meningioma or glioma. These regions were analyzed to obtain texture features. Statistical analysis was conducted using SPSS (version 20.0), including the Shapiro-Wilk test and Wilcoxon signed-rank test, which were used to test significant differences in each feature between the tumor and healthy regions. T-distributed stochastic neighbor embedding (t-SNE) was used to visualize the data distribution so as to avoid tumor selection bias. The Gini impurity index in random forests (RFs) was used to select the top five out of all features. Based on the five features, three classification models were built respectively with three machine learning classifiers: RF, support vector machine (SVM), and back propagation (BP) neural network. RESULTS: Sixteen of the 25 features were significantly different between the tumor and healthy areas. Through the Gini impurity index in RFs, standard deviation, first-order moment, variance, third-order absolute moment, and third-order central moment were selected to build the classification model. The classification model trained using the SVM classifier achieved the best performance, with sensitivity, specificity, and area under the curve of 94.04%, 92.3%, and 0.932, respectively. CONCLUSION: Texture analysis with an SVM classifier can help differentiate between brain tumor and healthy areas with high speed and accuracy, which would facilitate its clinical application.

Retinoic acid promotes metabolic maturation of human Embryonic Stem Cell-derived Cardiomyocytes.

Cardiomyocytes differentiated from human embryonic stem cells (hESCs) represent a promising cell source for heart repair, disease modeling and drug testing. However, improving the differentiation efficiency and maturation of hESC-derived cardiomyocytes (hESC-CMs) is still a major concern. Retinoic acid (RA) signaling plays multiple roles in heart development. However, the effects of RA on cardiomyocyte differentiation efficiency and maturation are still unknown. Methods: RA was added at different time intervals to identify the best treatment windows for cardiomyocyte differentiation and maturation. The efficiency of cardiomyocyte differentiation was detected by quantitative real-time PCR and flow cytometry. Cardiomyocytes maturation was detected by immunofluorescence staining, metabolic assays and patch clamp to verify structural, metabolic and electrophysiological maturation, respectively. RNA sequencing was used for splicing analysis. Results: We found that RA treatment at the lateral mesoderm stage (days 2-4) significantly improved cardiomyocyte differentiation, as evidenced by the upregulation of TNNT2, NKX2.5 and MYH6 on day 10 of differentiation. In addition, flow cytometry showed that the proportion of differentiated cardiomyocytes in the RA-treated group was significantly higher than that in control group. RA treatment on days 15-20 increased cardiomyocyte area, sarcomere length, multinucleation and mitochondrial copy number. RNA sequencing revealed RA promoted RNA isoform switch to the maturation-related form. Meanwhile, RA promoted electrophysiological maturation and calcium handling of hESC-CMs. Importantly, RA-treated cardiomyocytes showed decreased glycolysis and enhanced mitochondrial oxidative phosphorylation, with the increased utilization of fatty acid and exogenous pyruvate but not glutamine. Conclusion: Our data indicated that RA treatment at an early time window (days 2-4) promotes the efficiency of cardiomyocyte differentiation and that RA treatment post beating (days 15-20) promotes cardiomyocyte maturation. The biphasic effects of RA provide new insights for improving cardiomyocyte differentiation and quality.

The analysis of differential diagnosis of benign and malignant thyroid nodules based on ultrasound reports.

BACKGROUND: Thyroid cancer is a common endocrine tumor, the incidence of which is increasing each year. Early diagnosis and treatment can effectively prevent thyroid cancer. This article uses Chinese's ultrasound reports to determine the value of early diagnosis. METHODS: The clinical data center of the First Affiliated Hospital of Nanjing Medical University was screened for patients diagnosed with a thyroid nodule, who had undergone a thyroid function test, ultrasound records and pathological assessment. A total of 811 patients with a total of 1,290 pathologically confirmed nodules (506 benign and 784 malignant) were enrolled. Logistic regression was used to analyze the variables that significantly affected malignant nodules. The sensitivity and specificity of ultrasound thyroid imaging-reporting and data system (TI-RADS) classification results for benign and malignant tumors were calculated. RESULTS: The age of the patients had a very significant difference in the classification of benign and malignant nodules (P<0.001), and the marital status was significantly different (P<0.05). Gender and medical insurance had no significant effect (P>0.05). Thyroglobulin (TG), free thyroxine (FT4), and free triiodothyronine (FT3) had significant effects (P=0.003) on the incidence of malignant nodules in patients, while thyroid-stimulating hormone (TSH) had no significant effect (P>0.05). Ultrasound analysis showed a Youden's index of 78.97%, a positive predictive value of 93.20%, and a negative predicted value of 84.10% at the most excellent classification effect. The sensitivity was 89.0%, the specificity was 89.9%; much greater than the classification model based on the thyroid function test (sensitivity =80.6%, specificity =55.8%). CONCLUSIONS: The present study verifies the effectiveness of using TI-RADS classification for diagnosis of benign and malignant thyroid nodules, and explores the use of new analysis methods for clinical data. To reduce dependence on the doctors, ultrasound image data and clinical phenotypic data can be further used to assist clinical decision making.

Automated detection of cardiovascular disease by electrocardiogram signal analysis: a deep learning system.

Automated electrocardiogram (ECG) diagnosis could be a useful aid for clinical use. We applied a deep learning method to build a system for automated detection and classification of ECG signals. We first trained a convolutional neural network (CNN) to detect cardiovascular disease in ECG signals using a training data set of 259,789 ECG signals collected from the cardiac function rooms of a tertiary care hospital. The CNN classification was validated using an independent test data set of 18,018 ECG signals. The labels used covered >90% of clinical diagnoses. The system grouped ECGs into 18 classifications-17 different types of abnormalities and normal ECG. The overall accuracy of the model was tested and found to be close to 95%; the accuracy for diagnosis of normal rhythm/atrial fibrillation was 99.15%. The proposed CNN model could help reduce misdiagnosis and missed diagnosis in primary care settings and also improve efficiency and save manpower cost for large general hospitals.

Association between type 2 diabetes and cancer incidence in China: data in hospitalized patients from 2006 to 2013.

BACKGROUND: Evidence of a role for type 2 diabetes in overall cancer risk is limited in ethnic Chinese populations. We therefore investigated whether there is an association between diabetes and cancer incidence. METHODS: All type 2 diabetes and cancer hospitalized patients from the First Affiliated Hospital of Nanjing Medical University between 2006.01 and 2013.12 were eligible for the study. Our research used healthcare information technology and statistical methods to analyze the clinical data of hospitalized patients and explored the relationship between diabetes and cancer. Participants with fasting glucose ≥126 mg/dL, or taking hypoglycemic medications, were classed as having type 2 diabetes. Cancer incidence was established through regular follow-up interviews and medical records. Data were entered into Excel and a database was set up with ACCESS software. Clinical information such as demographics like gender, age, occupation, marriage, insurance and etc., diagnoses, and prescription record were chosen and analyzed. SPSS software was also used for statistical analysis. RESULTS: The number of patients with both diabetes and cancer rose from 220 cases in 2006 to 1,623 cases in 2013. The proportion of cancer patients with diabetes has also increased every year. Younger participants (aged ≤50 years) with diabetes had a greater risk of all cancers [P<0.005, odds ratio (OR) >3.4]. And cancer patients with diabetes occurs more frequently in male patients than in female patients, especially since 2009 the proportion has increased more evidently (P<0.005, OR >1.4). Further analysis showed that the level of blood lipid in patients with diabetes mellitus and cancer was significantly different from that in patients with simple diabetes mellitus (P<0.05). CONCLUSIONS: Our results clearly demonstrate a positive association between diabetes and cancer, especially in younger individuals aged less than 50 years. This finding highlights a need for greater awareness among public health workers and physicians of the importance of effective control of diabetes in the younger population.

A predictive model for respiratory distress in patients with COVID-19: a retrospective study.

BACKGROUND: Coronavirus disease 2019 (COVID-19), associated with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has become a global public health crisis. We retrospectively evaluated 863 hospitalized patients with COVID-19 infection, designated IWCH-COVID-19. METHODS: We built a successful predictive model after investigating the risk factors to predict respiratory distress within 30 days of admission. These variables were analyzed using Kaplan-Meier and Cox proportional hazards (PHs) analyses. Hazard ratios (HRs) and performance of the final model were determined. RESULTS: Neutrophil count >6.3×109/L, D-dimer level ≥1.00 mg/L, and temperature ≥37.3 °C at admission showed significant positive association with the outcome of respiratory distress in the final model. Complement C3 (C3) of 0.9-1.8 g/L, platelet count >350×109/L, and platelet count of 125-350×109/L showed a significant negative association with outcomes of respiratory distress in the final model. The final model had a C statistic of 0.891 (0.867-0.915), an Akaike's information criterion (AIC) of 567.65, and a bootstrap confidence interval (CI) of 0.866 (0.842-0.89). This five-factor model could help in early allocation of medical resources. CONCLUSIONS: The predictive model based on the five factors obtained at admission can be applied for calculating the risk of respiratory distress and classifying patients at an early stage. Accordingly, high-risk patients can receive timely and effective treatment, and health resources can be allocated effectively.

Prevalence of hypertension, diabetes, and dyslipidemia, and their additive effects on myocardial infarction and stroke: a cross-sectional study in Nanjing, China.

BACKGROUND: This study aimed to investigate the prevalence and risk factors for hypertension, diabetes, and dyslipidemia, and to evaluate their additive effects on myocardial infarction (MI) and stroke in Nanjing in East China. METHODS: A multistage, stratified random cluster sampling method was used to select representative participants. All eligible participants completed questionnaires, physical measurements, and blood tests. Multivariable and univariable logistic regression analyses were used to identify associated risk factors and evaluate additive effects on cardiovascular events, respectively. RESULTS: Hypertension was the most prevalent chronic disease among 11,036 participants enrolled (18.5%), followed by dyslipidemia (8.3%) and diabetes (6.0%). The prevalence of hypertension was higher in men than in women while no sex-related difference was observed in the prevalence of diabetes and dyslipidemia. Older age and higher body mass index were risk factors for all three diseases. Sex, central obesity, smoking, number of family members, salt intake, and family history of hypertension were associated with hypertension; central obesity, smoking, alcohol assumption, and family history of diabetes correlated with diabetes; and female sex, higher education, and alcohol assumption were risk factors for dyslipidemia. Hypertension complicated with dyslipidemia conferred more risk of MI and stroke than independent effects. Diabetes also contributed to risk based on hypertension or dyslipidemia. CONCLUSIONS: The burden of hypertension and diabetes has stopped increasing. However, total cholesterol (TC) concentration in the population has not been well controlled. A more comprehensive approach to managing dyslipidemia, hypertension, and diabetes needs to be developed, especially for individuals with multiple cardiovascular risk factors.

MIR148A family regulates cardiomyocyte differentiation of human embryonic stem cells by inhibiting the DLL1-mediated NOTCH signaling pathway.

MicroRNAs (miRNAs), as a class of naturally occurring RNAs, play important roles in cardiac physiology and pathology. There are many miRNAs that show multifarious expression patterns during cardiomyocyte genesis. Here, we focused on the MIR148A family, which is composed of MIR148A, MIR148B and MIR152, and shares the same seed sequences. The expression levels of all MIR148A family members progressively increased during the differentiation of human embryonic stem cells (hESCs) into cardiomyocytes. The deletion of MIR148A family (MIR148A-TKO) resulted in a decreased proportion of cardiomyocytes after cardiac induction, which was restored by the ectopic expression of MIR148A family members. Transcriptome analyses indicated that the MIR148A family could partially repress paraxial mesodermal differentiation from primitive streak cells. In turn, these miRNAs promoted lateral mesoderm and cardiomyocyte differentiation. Furthermore, the NOTCH ligand Delta-like 1 (DLL1) was validated as the target gene of MIR148A family, and knockdown of DLL1 could promote the cardiomyocyte differentiation of MIR148A-TKO hESCs. Thus, our results demonstrate MIR148A family could promote cardiomyocyte differentiation by inhibiting undesired paraxial mesoderm lineage commitment, which improves our understanding on cardiomyocyte differentiation from hESCs.

Detecting pioglitazone use and risk of cardiovascular events using electronic health record data in a large cohort of Chinese patients with type 2 diabetes.

BACKGROUND: Pioglitazone may have a protective effect against cardiovascular disease risk among type 2 diabetes (T2D) patients, but evidence from China is lacking. This study investigated the association using electronic health records (EHR) data from a Chinese cohort of T2D patients. METHODS: All T2D patients from the First Affiliated Hospital of Nanjing Medical University who were prescribed at least one oral antidiabetic drug and were aged ≥18 years between 1 July 2005 and 30 June 2017 were eligible for inclusion (n = 71 783). Pioglitazone use was determined in 6-month study intervals, with outcome events of myocardial infarction (MI), ischemic stroke, and heart failure. Poisson regression was used to estimate adjusted rate ratios (RRs) with 95% confidence intervals (CIs). RESULTS: In multivariable analysis adjusted for potential confounders, pioglitazone use, compared with no use, was associated with a significant 39% decreased risk of MI (RR = 0.61; 95% CI = 0.42-0.90; P = 0.012). Pioglitazone use was also associated with a non-significant reduction in risk of heart failure or stroke. When MI, heart failure, and stroke were combined as a composite outcome, pioglitazone use was associated with a 30% decrease in risk (RR = 0.70; 95% CI = 0.56-0.88; P = 0.002). CONCLUSIONS: This study demonstrates that applying informatics tools to a large EHR database could be a good way to efficiently conduct clinical observational research. In addition, the findings validated the favorable effect of pioglitazone on the risk of MI among T2D patients in China, with the use of pioglitazone decreasing the risk of MI among those with T2D.

Analysis of treatment pathways for three chronic diseases using OMOP CDM.

The present study examined treatment pathways (the ordered sequence of medications that a patient is prescribed) for three chronic diseases (hypertension, type 2 diabetes, and depression), compared the pathways with recommendations from guidelines, discussed differences and standardization of medications in different medical institutions, explored population diversification and changes of clinical treatment, and provided clinical big data analysis-based data support for the development and study of drugs in China. In order to run the "Treatment Pathways in Chronic Disease" protocol in Chinese data sources,we have built a large data research and analysis platform for Chinese clinical medical data. Data sourced from the Clinical Data Repository (CDR) of the First Affiliated Hospital of Nanjing Medical University was extracted, transformed, and loaded into an observational medical outcomes partnership common data model (OMOP CDM) Ver. 5.0. Diagnosis and medication information for patients with hypertension, type 2 diabetes, and depression from 2005 to 2015 were extracted for observational research to obtain treatment pathways for the three diseases. The most common medications used to treat diabetes and hypertension were metformin and acarbose, respectively, at 28.5 and 20.9% as first-line medication. New drugs were emerging for depression; therefore, the favorite medication changed accordingly. Most patients with these three diseases had different treatment pathways from other patients with the same diseases. The proportions of monotherapy increased for the three diseases, especially in recent years. The recommendations presented in guidelines show some predominance. High-quality, effective guidelines incorporating domestic facts should be established to further guide medication and improve therapy at local hospitals. Medical institutions at all levels could improve the quality of medical services, and further standardize medications in the future. This research is the first application of the CDM model and OHDSI software in China, which were used to study, treatment pathways for three chronic diseases (hypertension, type 2 diabetes and depression), compare the pathways with recommendations from guidelines, discuss differences and standardization of medications in different medical institutions, demonstrate the urgent need for quality national guidelines, explores population diversification and changes of clinical treatment, and provide clinical big data analysis-based data support for the development and study of drugs in China.

Extraction of BI-RADS findings from breast ultrasound reports in Chinese using deep learning approaches.

BACKGROUND: The wide adoption of electronic health record systems (EHRs) in hospitals in China has made large amounts of data available for clinical research including breast cancer. Unfortunately, much of detailed clinical information is embedded in clinical narratives e.g., breast radiology reports. The American College of Radiology (ACR) has developed a Breast Imaging Reporting and Data System (BI-RADS) to standardize the clinical findings from breast radiology reports. OBJECTIVES: This study aims to develop natural language processing (NLP) methods to extract BI-RADS findings from breast ultrasound reports in Chinese, thus to support clinical operation and breast cancer research in China. METHODS: We developed and compared three different types of NLP approaches, including a rule-based method, a traditional machine learning-based method using the Conditional Random Fields (CRF) algorithm, and deep learning-based approaches, to extract all BI-RADS finding categories from breast ultrasound reports in Chinese. RESULTS: Using a manually annotated dataset containing 540 reports, our evaluation shows that the deep learning-based method achieved the best F1-score of 0.904, when compared with rule-based and CRF-based approaches (0.848 and 0.881 respectively). CONCLUSIONS: This is the first study that applies deep learning technologies to BI-RADS findings extraction in Chinese breast ultrasound reports, demonstrating its potential on enabling international collaborations on breast cancer research.

The analysis of the disease spectrum in China.

Analysis of the related risks of disease provides a scientific basis for disease prevention and treatment, hospital management, and policy formulation by the changes in disease spectrum of patients in hospital. Retrospective analysis was made to the first diagnosis, age, gender, daily average cost of hospitalized patients, and other factors in the First Affiliated Hospital of Nanjing Medical University during 2006-2013. The top 4 cases were as follows: cardiovascular disease, malignant tumors, lung infections, and noninsulin dependent diabetes mellitus. By the age of disease analysis, we found a younger age trend of cardiovascular disease, and the age of onset of cancer or diabetes was somewhat postponed. The average daily cost of hospitalization and the average daily cost of the main noncommunicable diseases were both on the rise. Noncommunicable diseases occupy an increasingly important position in the constitution of the disease, and they caused an increasing medical burden. People should pay attention to health from the aspects of lifestyle changing. Hospitals should focus on building the appropriate discipline. On the other hand, an integrated government response is required to tackle key risks. Multiple interventions are needed to lower the burden of these diseases and to improve national health.