UNASSIGNED: This study aims to develop an artificial intelligence model utilizing clinical blood markers, ultrasound data, and breast biopsy pathological information to predict the distant metastasis in breast cancer patients.
UNASSIGNED: Data from two medical centers were utilized, Clinical blood markers, ultrasound data, and breast biopsy pathological information were separately extracted and selected. Feature dimensionality reduction was performed using Spearman correlation and LASSO regression. Predictive models were constructed using LR and LightGBM machine learning algorithms and validated on internal and external validation sets. Feature correlation analysis was conducted for both models.
UNASSIGNED: The LR model achieved AUC values of 0.892, 0.816, and 0.817 for the training, internal validation, and external validation cohorts, respectively. The LightGBM model achieved AUC values of 0.971, 0.861, and 0.890 for the same cohorts, respectively. Clinical decision curve analysis showed a superior net benefit of the LightGBM model over the LR model in predicting distant metastasis in breast cancer. Key features identified included creatine kinase isoenzyme (CK-MB) and alpha-hydroxybutyrate dehydrogenase.
UNASSIGNED: This study developed an artificial intelligence model using clinical blood markers, ultrasound data, and pathological information to identify distant metastasis in breast cancer patients. The LightGBM model demonstrated superior predictive accuracy and clinical applicability, suggesting it as a promising tool for early diagnosis of distant metastasis in breast cancer.

UNASSIGNED: Traumatic brain injury (TBI) is the major reason for the death of young people and is well known for its high mortality and morbidity. This paper aim to predict the 24h survival of patients with TBI.
UNASSIGNED: A total of 1224 samples were involved in this analysis, and the clinical indicators involved included age, gender, blood pressure, MGAP and other fields, among which the target variable was \"outcome\", which was a binary variable. The methods mainly involved in this paper include data visualization analysis, single factor analysis, feature engineering analysis, random forest model (RF), K-Nearst Neighbors (KNN) model, and so on. Logistic regression model (LR) and deep neural network model (DNN). We will oversample the training set using the SMOTE method because of the very unbalanced labeling of the sample itself.
UNASSIGNED: Although the accuracy of all models is very high, the recall rate is relatively low. The DNN model with the best performance only reaches 0.17, and the corresponding AUC is 0.80. After resampling, we find that the recall rate of positive samples of all models has increased a lot, but the AUC of some models has decreased. Finally, the optimal model is LR, whose positive sample recall rate is 0.67 and AUC is 0.82.
UNASSIGNED: Through resampling, we obtained that the best model is the RF model, whose recall rate and AUC are the best, and the AUC level is about 0.87, indicating that the accuracy performance of the model is still good.

In this study, we focused on using microarray gene data from pancreatic sources to detect diabetes mellitus. Dimensionality reduction (DR) techniques were used to reduce the dimensionally high microarray gene data. DR methods like the Bessel function, Discrete Cosine Transform (DCT), Least Squares Linear Regression (LSLR), and Artificial Algae Algorithm (AAA) are used. Subsequently, we applied meta-heuristic algorithms like the Dragonfly Optimization Algorithm (DOA) and Elephant Herding Optimization Algorithm (EHO) for feature selection. Classifiers such as Nonlinear Regression (NLR), Linear Regression (LR), Gaussian Mixture Model (GMM), Expectation Maximum (EM), Bayesian Linear Discriminant Classifier (BLDC), Logistic Regression (LoR), Softmax Discriminant Classifier (SDC), and Support Vector Machine (SVM) with three types of kernels, Linear, Polynomial, and Radial Basis Function (RBF), were utilized to detect diabetes. The classifier\'s performance was analyzed based on parameters like accuracy, F1 score, MCC, error rate, FM metric, and Kappa. Without feature selection, the SVM (RBF) classifier achieved a high accuracy of 90% using the AAA DR methods. The SVM (RBF) classifier using the AAA DR method for EHO feature selection outperformed the other classifiers with an accuracy of 95.714%. This improvement in the accuracy of the classifier\'s performance emphasizes the role of feature selection methods.

Hepatitis is among the deadliest diseases on the planet. Machine learning approaches can contribute toward diagnosing hepatitis disease based on a few characteristics. On the UCI dataset, authors assessed distinct classifiers\' performance in order to develop a systematic strategy for hepatitis disease diagnosis. The classifiers used are support vector machine, logistic regression (LR), K-nearest neighbor, and random forest. The classifiers were employed without class balancing and in conjunction with class balancing using SMOTE strategy. Both studies, classification without class balancing and with class balancing, were compared in terms of different performance parameters. After adopting class balancing, the efficiency of classifiers improved significantly. LR with SMOTE provided the highest level of accuracy (93.18%).

The machine learning (ML)-based classification models are widely utilized for the automated detection of heart diseases (HDs) using various physiological signals such as electrocardiogram (ECG), magnetocardiography (MCG), heart sound (HS), and impedance cardiography (ICG) signals. However, ECG-based HD identification is the most common one used by clinicians. In the current investigation, the ECG records or subjects have been sampled and are used as inputs to the classification model to distinguish between normal and abnormal patients. The study has employed an imbalanced number of ECG samples for training the various classification models. Few ML methods such as support vector machine (SVM), logistic regression (LR), and adaptive boosting (AdaBoost) which have been rarely used for HD detection have been selected. The performance of the developed model has been evaluated in terms of accuracy, F1-score, and area under curve (AUC) values using ECG signals of subjects given in publicly available (PTB-ECG, MIT-BIH) datasets. Ranking of the models has been assigned based on these performance metrics and it is found that the AdaBoost and LR classifiers stand in first and second positions. These two models have been ensembled based on the majority voting principle and the performance measure of this ensemble model has also been determined. It is, in general, observed that the proposed ensemble model demonstrates the best HD detection performance of 0.946, 0.949, and 0.951 for the PTB-ECG dataset and 0.921, 0.926, and 0.950 for the MIT-BIH dataset in terms of accuracy, F1-score, and AUC, respectively. The proposed methodology can also be employed for the classification of HD using ICG, MCG, and HS signals as inputs. Further, the proposed methodology can also be applied to the detection of other diseases.

We present an automatic non-invasive way of detecting cough events based on both accelerometer and audio signals. The acceleration signals are captured by a smartphone firmly attached to the patient\'s bed, using its integrated accelerometer. The audio signals are captured simultaneously by the same smartphone using an external microphone. We have compiled a manually-annotated dataset containing such simultaneously-captured acceleration and audio signals for approximately 6000 cough and 68000 non-cough events from 14 adult male patients. Logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) classifiers provide a baseline and are compared with three deep architectures, convolutional neural network (CNN), long short-term memory (LSTM) network, and residual-based architecture (Resnet50) using a leave-one-out cross-validation scheme. We find that it is possible to use either acceleration or audio signals to distinguish between coughing and other activities including sneezing, throat-clearing, and movement on the bed with high accuracy. However, in all cases, the deep neural networks outperform the shallow classifiers by a clear margin and the Resnet50 offers the best performance, achieving an area under the ROC curve (AUC) exceeding 0.98 and 0.99 for acceleration and audio signals respectively. While audio-based classification consistently offers better performance than acceleration-based classification, we observe that the difference is very small for the best systems. Since the acceleration signal requires less processing power, and since the need to record audio is sidestepped and thus privacy is inherently secured, and since the recording device is attached to the bed and not worn, an accelerometer-based highly accurate non-invasive cough detector may represent a more convenient and readily accepted method in long-term cough monitoring.

This study aimed to determine the risk factors of ischemic/hemorrhagic stroke in patients suffering moyamoya disease (MMD), as well as to compare the effects of six analysis methods.
In the present retrospective study, the data originated from the database of Jiang Xi Province Medical Big Data Engineering & Technology Research Center. In addition, the information of patients with MMD that were admitted to the second affiliated hospital of Nanchang university from January 1st, 2012 to December 31st, 2019 was acquired. Six different machine learning methods were adopted to build the models, and XGboost, Logistic regression (LR) and Support vector machine (SVM) models were adopted to determine the risk factors of ischemic/hemorrhagic stroke in patients with MMD because of their excellent performance. Next, the effects of the built models were compared and validated in internal and independent external validation sets. The external validation set involving 204 cases from January 1st, 2018 to December 31st, 2019.
On the whole, 790 patients with MMD were screened, i.e., 397 patients with cerebral infarction and 393 patients with cerebral hemorrhage. In the internal validation set, XGboost model exhibited significant discrimination (AUC>0.75), with its area under the curve (AUC) reaching 0.874 (95% CI: 0.859, 0.889). Compared with the LR and SVM models, the XGboost model in the internal validation set achieved the improved accuracy by 3.2% and 3.1%, respectively, whereas no significant difference was identified.
XGboost model could be more efficient in analyzing the risk factors of ischemic/hemorrhagic stroke in patients with MMD; the risk factors of hemorrhagic stroke in MMD might be closely related to Suzuki stages, presence of an aneurysm, rural residence, hospitalization times and age of onset.

The increased interest in the use of Massively Parallel Sequencing (MPS) technologies to type traditional autosomal STR markers raises multiple questions regarding interpretation of the results via probabilistic genotyping. To begin to address some of those questions, we examined the effects of using differing degrees of sequence information, pre-filtering, and data modeling to interpret complex MPS-STR mixtures in a probabilistic genotyping software. Sixty ForenSeq typing results for mixtures of from two to four contributors were: 1) represented using three separate formats that captured different degrees of sequence information, and 2) were analyzed using three different filtering approaches prior to probabilistic interpretation. All mixtures for the different format and filtering variants were subsequently interpreted with respect to ten reference profiles, using both qualitative (LRmix) and quantitative (EuroForMix) models to calculate the likelihood ratio (LR). The LR results indicated moderate information gain when the STR nomenclature was based upon the longest uninterrupted stretch (LUS) compared with conventional capillary electrophoresis repeat units (RU), whereas additional gains were very small when the complete sequence information was utilised. Use of a static analytical threshold for data pre-filtering improved LRs compared to a dynamic (percentage-based) threshold, as the static threshold prevented excessive filtering of alleles originating from minor contributors. For interpretations performed using a quantitative model, a small improvement in performance was observed if a stutter model was employed instead of using stutter thresholds to pre-filter the data, whereas - as expected - performance worsened considerably under the qualitative model when stutter was not pre-filtered. Given the empirical and theoretical findings in this study we discuss the value of utilizing sequence-level information and potential paths forward to increase information gain using MPS systems.

BACKGROUND: Basal cell carcinoma (BCC) recurrence and metastatic rates are known to be very low. The risk factors for these rare outcomes are subsequently not well studied.
OBJECTIVE: To identify risk factors independently associated with local recurrence (LR) and metastasis and/or death (M/D) in large (≥2 cm) BCC.
METHODS: BCCs histologically confirmed between 2000 and 2009 were retrospectively screened for tumor diameter at 2 academic centers. Medical records of all large BCCs and an equal number of randomly selected small BCCs were reviewed for LR and M/D.
RESULTS: Included were 248 large BCC and 248 small BCC tumors. Large BCCs had a significantly higher risk of LR and M/D than small BCCs (LR: 8.9% vs 0.8%, P < .001; M/D: 6.5% vs. 0%, P < .001). Because the risks were so low in small BCCs, they were excluded from further analysis. On multivariable logistic regression, head/neck location (odds ratio [OR], 9.7; 95% confidence interval [CI], 3.0-31.3) and depth beyond fat (OR, 3.1; 95% CI, 1.0-9.6) were associated with LR in large BCCs. Risk of LR was lower with Mohs micrographic surgery (OR, 0.14; 95% CI, 0.04-0.5). Head/neck location (OR, 5.3; 95% CI, 1.2-23.2), tumor diameter ≥4 cm (OR, 11.9; 95% CI, 2.4-59.4), and depth beyond fat (OR, 28.6; 95% CI, 6.7-121) were significant predictors of M/D in large BCCs.
CONCLUSIONS: Retrospective cohort design.
CONCLUSIONS: Large BCCs, particularly those with additional risk factors, have a high enough risk of recurrence and metastasis to warrant further investigation to optimize management.

High-grade bone osteosarcoma has a high relapse rate. The best treatment of local recurrence (LR) is under discussion. The aim of this study is to analyze LR patterns and factors prognostic for survival.
LR diagnostic modality (clinical or imaging), pattern of recurrence, and post-LR survival (PLRS) were assessed.
Sixty-two patients were identified, with median age 21 years (range, 9-75 years), including 11 (18%) ≤15 years, 30 (48%) from 16 to 29 years; 21 (34%) were older. Patterns of relapse were LR only 58%, LR + distant metastases (DM) 42%. Seventy-nine percent of patients relapsed within 24 months, and diagnosis was clinical in 88%. LR treatment was surgery 85%, chemotherapy 55%, chemotherapy + surgery 45%. Surgical complete remission after LR (CR2) was achieved in 60% (LR 86%; LR + DM 23%). With a median follow-up of 43 months (range, 5-235 months), the five-year PLRS was 37%, significantly better for patients with longer LR-free interval (LRFI; ≤24 months 31% vs > 24 months 61.5%, P = 0.03), absence of DM (no DM 56% vs DM 11.5%, P = 0.0001), and achievement of CR2 (no CR2 0% vs CR2 58.5%, P = 0.0001). No difference was found according to age and chemotherapy (LR only: five-year PLRS: 53% without chemotherapy vs 58% with chemotherapy, P = 0.9; LR + DM: five-year PLRS: 25% without chemotherapy vs 9% with chemotherapy, P = 0.7).
Early relapse is detected by symptoms in 90% of cases and associated with worse outcome. The achievement of CR2, not age, is crucial for survival. For patients with LR only, better survival was demonstrated, as compared with DM, and no improvement with chemotherapy after surgery was found.