Establishment of machine learning-based tool for early detection of pulmonary embolism.

BACKGROUND AND OBJECTIVES: Pulmonary embolism (PE) is a complex disease with high mortality and morbidity rate, leading to increasing society burden. However, current diagnosis is solely based on symptoms and laboratory data despite its complex pathology, which easily leads to misdiagnosis and missed diagnosis by inexperienced doctors. Especially, CT pulmonary angiography, the gold standard method, is not widely available. In this study, we aim to establish a rapid and accurate screening model for pulmonary embolism using machine learning technology. Importantly, data required for disease prediction are easily accessed, including routine laboratory data and medical record information of patients. METHODS: We extracted features from patients' routine laboratory results and medical records, including blood routine, biochemical group, blood coagulation routine and other test results, as well as symptoms and medical history information. Samples with a feature loss rate greater than 0.8 were deleted from the original database. Data from 4723 cases were retained, 231 of which were positive for pulmonary embolism. 50 features were retained through the positive and negative statistical hypothesis testing which was used to build the predictive model. In order to avoid identification as majority-class samples caused by the imbalance of sample proportion, we used the method of Synthetic Minority Oversampling Technique (SMOTE) to increase the amount of information on minority samples. Five typical machine learning algorithms were used to model the screening of pulmonary embolism, including Support Vector Machines, Logistic Regression, Random Forest, XGBoost, and Back Propagation Neural Networks. To evaluate model performance, sensitivity, specificity and AUC curve were analyzed as the main evaluation indicators. Furthermore, a baseline model was established using the characteristics of the pulmonary embolism guidelines as a comparison model. RESULTS: We found that XGBoost showed better performance compared to other models, with the highest sensitivity and specificity (0.99 and 0.99, respectively). Moreover, it showed significant improvement in performance compared to the baseline model (sensitivity and specificity were 0.76 and 0.76 respectively). More important, our model showed low missed diagnosis rate (0.46) and high AUC value (0.992). Finally, the calculation time of our model is only about 0.05 s to obtain the possibility of pulmonary embolism. CONCLUSIONS: In this study, five machine learning classification models were established to assess the likelihood of patients suffering from pulmonary embolism, and the XGBoost model most significantly improved the precision, sensitivity, and AUC for pulmonary embolism screening. Collectively, we have established an AI-based model to accurately predict pulmonary embolism at early stage.

Genome assembly of Erythrophleum Fordii, a special "ironwood" tree in China.

OBJECTIVES: Erythrophleum is a genus in the Fabaceae family. The genus contains only about 10 species, and it is best known for its hardwood and medical properties worldwide. Erythrophleum fordii Oliv. is the only species of this genus distributed in China. It has superior wood and can be used in folk medicine, which leads to its overexploitation in the wild. For its effective conservation and elucidation of the distinctive genetic traits of wood formation and medical components, we present its first genome assembly. DATA DESCRIPTION: This work generated ~ 160.8 Gb raw Nanopore whole genome sequencing (WGS) long reads, ~ 126.0 Gb raw MGI WGS short reads and ~ 29.0 Gb raw RNA-seq reads using E. fordii leaf tissues. The de novo assembly contained 864,825,911 bp in the E. fordii genome, with 59 contigs and a contig N50 of 30,830,834 bp. Benchmarking Universal Single-Copy Orthologs (BUSCO) revealed 98.7% completeness of the assembly. The assembly contained 471,006,885 bp (54.4%) repetitive sequences and 28,761 genes that coded for 33,803 proteins. The protein sequences were functionally annotated against multiple databases, facilitating comparative genomic analysis.

Establishment of risk model for elderly CAP at different age stages: a single-center retrospective observational study.

Community-acquired pneumonia (CAP) is one of the main reasons of mortality and morbidity in elderly population, causing substantial clinical and economic impacts. However, clinically available score systems have been shown to demonstrate poor prediction of mortality for patients aged over 65. Especially, no existing clinical model can predict morbidity and mortality for CAP patients among different age stages. Here, we aimed to understand the impact of age variable on the establishment of assessment model and explored prognostic factors and new biomarkers in predicting mortality. We retrospectively analyzed elderly patients with CAP in Minhang Hospital, Fudan University. We used univariate and multiple logistic regression analyses to study the prognostic factors of mortality in each age-based subgroup. The prediction accuracy of the prognostic factors was determined by the Receiver Operating Characteristic curves and the area under the curves. Combination models were established using several logistic regressions to save the predicted probabilities. Four factors with independently prognostic significance were shared among all the groups, namely Albumin, BUN, NLR and Pulse, using univariate analysis and multiple logistic regression analysis. Then we built a model with these 4 variables (as ABNP model) to predict the in-hospital mortality in all three groups. The AUC value of the ABNP model were 0.888 (95% CI 0.854-0.917, p < 0.000), 0.912 (95% CI 0.880-0.938, p < 0.000) and 0.872 (95% CI 0.833-0.905, p < 0.000) in group 1, 2 and 3, respectively. We established a predictive model for mortality based on an age variable -specific study of elderly patients with CAP, with higher AUC value than PSI, CURB-65 and qSOFA in predicting mortality in different age groups (66-75/ 76-85/ over 85 years).

Prognostic Significance of Cuproptosis-Related Gene Signatures in Breast Cancer Based on Transcriptomic Data Analysis.

Breast cancer (BRCA) remains a serious threat to women's health, with the rapidly increasing morbidity and mortality being possibly due to a lack of a sophisticated classification system. To date, no reliable biomarker is available to predict prognosis. Cuproptosis has been recently identified as a new form of programmed cell death, characterized by the accumulation of copper in cells. However, little is known about the role of cuproptosis in breast cancer. In this study, a cuproptosis-related genes (CRGs) risk model was constructed, based on transcriptomic data with corresponding clinical information relating to breast cancer obtained from both the TCGA and GEO databases, to assess the prognosis of breast cancer by comprehensive bioinformatics analyses. The CRGs risk model was constructed and validated based on the expression of four genes (NLRP3, LIPT1, PDHA1 and DLST). BRCA patients were then divided into two subtypes according to the CRGs risk model. Furthermore, our analyses revealed that the application of this risk model was significantly associated with clinical outcome, immune infiltrates and tumor mutation burden (TMB) in breast cancer patients. Additionally, a new clinical nomogram model based on risk score was established and showed great performance in overall survival (OS) prediction, confirming the potential clinical significance of the CRGs risk model. Collectively, our findings revealed that the CRGs risk model can be a useful tool to stratify subtypes and that the cuproptosis-related signature plays an important role in predicting prognosis in BRCA patients.

Exploration of prognostic factors for prediction of mortality in elderly CAP population using a nomogram model.

Background: The incidence and mortality rate of community-acquired pneumonia (CAP) in elderly patients were higher than the younger population. The assessment tools including CURB-65 and qSOFA have been applied in early detection of high-risk patients with CAP. However, several disadvantages exist to limit the efficiency of these tools for accurate assessment in elderly CAP. Therefore, we aimed to explore a more comprehensive tool to predict mortality in elderly CAP population by establishing a nomogram model. Methods: We retrospectively analyzed elderly patients with CAP in Minhang Hospital, Fudan University. The least absolute shrinkage and selection operator (LASSO) logistic regression combined with multivariate analyses were used to select independent predictive factors and established nomogram models via R software. Calibration plots, decision curve analysis (DCA) and receiver operating characteristic curve (ROC) were generated to assess predictive performance. Results: LASSO and multiple logistic regression analyses showed the age, pulse, NLR, albumin, BUN, and D-dimer were independent risk predictors. A nomogram model (NB-DAPA model) was established for predicting mortality of CAP in elderly patients. In both training and validation set, the area under the curve (AUC) of the NB-DAPA model showed superiority than CURB-65 and qSOFA. Meanwhile, DCA revealed that the predictive model had significant net benefits for most threshold probabilities. Conclusion: Our established NB-DAPA nomogram model is a simple and accurate tool for predicting in-hospital mortality of CAP, adapted for patients aged 65 years and above. The predictive performance of the NB-DAPA model was better than PSI, CURB-65 and qSOFA.

Exploration of Aging-Care Parameters to Predict Mortality of Patients Aged 80-Years and Above with Community-Acquired Pneumonia.

Purpose: The study explores a clinical model based on aging-care parameters to predict the mortality of hospitalized patients aged 80-year and above with community-acquired pneumonia (CAP). Patients and methods: In this study, four hundred and thirty-five CAP patients aged 80-years and above were enrolled in the Central Hospital of Minhang District, Shanghai during 01,01,2018-31,12,2021. The clinical data were collected, including aging-care relevant factors (ALB, FRAIL, Barthel Index and age-adjusted Charlson Comorbidity Index) and other commonly used factors. The prognostic factors were screened by multivariable logistic regression analysis. Receiver operating characteristic (ROC) curves were used to predict the mortality risk. Results: Univariate analysis demonstrated that several factors, including gender, platelet distribution width, NLR, ALB, CRP, pct, pre-albumin, CURB-65, low-density, lipoprotein, Barthel Index, FRAIL, leucocyte count, neutrophil count, lymphocyte count and aCCI, were associated with the prognosis of CAP. Multivariate model analyses further identified that CURB-65 (p < 0.0001, OR = 5.44, 95% CI = 3.021-10.700), FRAIL (p < 0.0001, OR = 5.441, 95% CI = 2.611-12.25) and aCCI (p = 0.003, OR = 1.551, 95% CI = 1.165-2.099) were independent risk factors, whereas ALB (p = 0.005, OR = 0.871, 95% CI = 0.788-0.957) and Barthel Index (p = 0.0007, OR = 0.958, 95% CI = 0.933-0.981) were independent protective factors. ROC curves were plotted to further predict the in-hospital mortality and revealed that combination of three parameters (Barthel Index+ FRAI +CURB-65) showed the best performance. Conclusion: This study showed that CURB-65, frailty and aCCI were independent risk factors influencing prognosis. In addition, ALB and Barthel Index were protective factors for in CAP patients over 80-years old. AUC was calculated and revealed that combination of three parameters (Barthel Index+ FRAI +CURB-65) showed the best performance.

[The randomized controlled trial of influences of T shape approach on the function of knee joint in the treatment of proximal tibial fractures].

OBJECTIVE: To investigate the clinical value of T shape approach in the treatment of proximal tibial fractures. METHODS: One handrend and thirteen patients of proximal tibial fractures were randomly divided into two groups. Group A: 62 cases underwent the traditional exposure approach. According to Schatzker classification,the cases of II to VI type was 25, 10, 16, 6, 5 respectively. Group B:51 cases underwent T shape approach ahead of knee joint, the cases of II to VI type was 21, 8, 13, 5, 4 respectively. All data were analyzed by SPSS 10.0 to compare operation time, blood loss, duration of hospitalization, healing time, the time of osseous union and complications after operation. RESULTS: Sixty patients in group A and 50 patients in group B were followed-up from 12 to 24 months. (1) Operation time:group B was longer than A (P < 0.01). (2) Mean blood loss and duration of hospitalization was the same. (3) Clinical healing time:group B was shorter. (4) Mean time of osseous union: 48 group B was shorter. Function of knee: group B was better than group A. (Complication: group B was less than group A. CONCLUSION: As compared with traditional exposure approach, T shape approach of knee joint had advantages of small scar, fewer complications, faster union of fracture and earlier recovery of joint function. The approach is valuable for the treatment of proximal tibial fractures.