Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Asynchronous fault detection filter of positive Markov jump systems by dynamic event-triggered mechanism.

In ISA transactions

This paper explores the design of a positive l1-gain asynchronous non-fragile fault detection filter (FDF) for discrete-time positive Markov jump systems (PMJSs) based on the dynamic event-triggered method (DETM). Due to the effect of positivity on event-triggered mechanisms and non-triviality on stability of discrete-time PMJSs, a new more powerful and generic DETM that can avoid non-triviality is developed. The asynchronous situation between the non-fragile FDF modes and the system modes is effectively managed by employing a hidden Markov model. Then, the solvability criteria for issues of concern are presented by building the copositive Lyapunov function (CLF) with internal dynamic variables (IDV). An alternative sufficient condition is derived based on the obtained results. Subsequently, a co-design project of the expected dynamic event-triggered positive l1-gain asynchronous non-fragile fault detection filter (DETPGAN-FFDF) and the designed DETM is proposed in this paper. Finally, the effectiveness and superiority of the approach are verified by numerical arithmetic examples and practical applications based on pest management.

Yin Kai, Yang Dedong

2023-Mar-15

A hidden Markov model, Dynamic event-triggered mechanism, Non-triviality, Positive Markov jump systems, Positive asynchronous fault detection filter

General General

Multivariable time series classification for clinical mastitis detection and prediction in automated milking systems.

In Journal of dairy science

In this study, we developed a machine learning framework to detect clinical mastitis (CM) at the current milking (i.e., the same milking) and predict CM at the next milking (i.e., one milking before CM occurrence) at the quarter level. Time series quarter-level milking data were extracted from an automated milking system (AMS). For both CM detection and prediction, the best classification performance was obtained from the decision tree-based ensemble models. Moreover, applying models on a data set containing data from the current milking and past 9 milkings before the current milking showed the best accuracy for detecting CM; modeling with a data set containing data from the current milking and past 7 milkings before the current milking yielded the best results for predicting CM. The models combined with oversampling methods resulted in specificity of 95 and 93% for CM detection and prediction, respectively, with the same sensitivity (82%) for both scenarios; when lowering specificity to 80 to 83%, undersampling techniques facilitated models to increase sensitivity to 95%. We propose a feasible machine learning framework to identify CM in a timely manner using imbalanced data from an AMS, which could provide useful information for farmers to manage the negative effects of CM.

Fan X, Watters R D, Nydam D V, Virkler P D, Wieland M, Reed K F

2023-Mar-17

automated milking system, clinical mastitis, machine learning, time series classification

General General

Using machine learning algorithm to predict the risk of post-traumatic stress disorder among firefighters in Changsha.

In Zhong nan da xue xue bao. Yi xue ban = Journal of Central South University. Medical sciences

OBJECTIVES : Firefighters are prone to suffer from psychological trauma and post-traumatic stress disorder (PTSD) in the workplace, and have a poor prognosis after PTSD. Reliable models for predicting PTSD allow for effective identification and intervention for patients with early PTSD. By collecting the psychological traits, psychological states and work situations of firefighters, this study aims to develop a machine learning algorithm with the aim of effectively and accurately identifying the onset of PTSD in firefighters, as well as detecting some important predictors of PTSD onset.

METHODS : This study conducted a cross-sectional survey through convenient sampling of firefighters from 20 fire brigades in Changsha, which were evenly distributed across 6 districts and Changsha County, with a total of 628 firefighters. We used the synthetic minority oversampling technique (SMOTE) to process data sets and used grid search to finish the parameter tuning. The predictive capability of several commonly used machine learning models was compared by 5-fold cross-validation and using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, precision, recall, and F1 score.

RESULTS : The random forest model achieved good performance in predicting PTSD with an average AUC score at 0.790. The mean accuracy of the model was 90.1%, with an F1 score of 0.945. The three most important predictors were perseverance, forced thinking, and reflective deep thinking, with weights of 0.165, 0.158, and 0.152, respectively. The next most important predictors were employment time, psychological power, and optimism.

CONCLUSIONS : PTSD onset prediction model for Changsha firefighters constructed by random forest has strong predictive ability, and both psychological characteristics and work situation can be used as predictors of PTSD onset risk for firefighters. In the next step of the study, validation using other large datasets is needed to ensure that the predictive models can be used in clinical setting.

Deng Aoqian, Yang Yanyi, Li Yunjing, Huang Mei, Li Liang, Lu Yimei, Chen Wentao, Yuan Rui, Ju Yumeng, Liu Bangshan, Zhang Yan

2023-Jan-28

firefighter, machine learning algorithm, post-traumatic stress disorder, predictor

General General

Multiplex single-cell droplet PCR with machine learning for detection of high-risk human papillomaviruses.

In Analytica chimica acta

High-risk human papillomavirus (HPV) testing can significantly decline the incidence and mortality of cervical cancer. Microfluidic technology provides an effective method for accurate detection of high-risk HPV by utilizing multiplex single-cell droplet polymerase chain reaction (PCR). However, current strategies are limited by low-integration microfluidic chip, complex reagent system, expensive detection equipment and time-consuming droplet identification. Here, we developed a novel multiplex droplet PCR method that directly detected high-risk HPV sequences in single cells. A multiplex microfluidic chip integrating four flow-focusing structures was designed for one-step and parallel droplet preparation. Using single-cell droplet PCR, multi-target sequences were detected simultaneously based on a monochromatic fluorescence signal. We applied machine learning to automatically identify the large populations of single-cell droplets with 97% accuracy. HPV16, 18 and 45 sequences were sensitively detected without cross-contamination in mixed CaSki and Hela cells. The approach enables rapid and reliable detection of multi-target sequences in single cells, making it powerful for investigating cellular heterogeneity related to cancer diagnosis and treatment.

Huang Yizheng, Sun Linjun, Liu Wenwen, Yang Ling, Song Zhigang, Ning Xin, Li Weijun, Tan Manqing, Yu Yude, Li Zhao

2023-Apr-29

High-risk HPV detection, Machine learning, Multiplex microfluidic chip, Single-cell droplet PCR

General General

Bioinformatics analysis of rheumatoid arthritis tissues identifies genes and potential drugs that are expressed specifically.

In Scientific reports ; h5-index 158.0

Studies have implicated necroptosis mechanisms in orthopaedic-related diseases, since necroptosis is a unique regulatory cell death pattern. However, the role of Necroptosis-related genes in rheumatoid arthritis (RA) has not been well described. We downloaded RA-related data information and Necroptosis-related genes from the Gene Expression Omnibus (GEO), Kyoto Gene and Genome Encyclopedia (KEGG) database, and Genome Enrichment Analysis (GSEA), respectively. We identified 113 genes associated with RA-related necroptosis, which was closely associated with the cytokine-mediated signaling pathway, necroptosis and programmed necrosis. Subsequently, FAS, MAPK8 and TNFSF10 were identified as key genes among 48 Necroptosis-associated differential genes by three machine learning algorithms (LASSO, RF and SVM-RFE), and the key genes had good diagnostic power in distinguishing RA patients from healthy controls. According to functional enrichment analysis, these genes may regulate multiple pathways, such as B-cell receptor signaling, T-cell receptor signaling pathways, chemokine signaling pathways and cytokine-cytokine receptor interactions, and play corresponding roles in RA. Furthermore, we predicted 48 targeted drugs against key genes and 31 chemical structural formulae based on targeted drug prediction. Moreover, key genes were associated with complex regulatory relationships in the ceRNA network. According to CIBERSORT analysis, FAS, MAPK8 and TNFSF10 may be associated with changes in the immune microenvironment of RA patients. Our study developed a diagnostic validity and provided insight to the mechanisms of RA. Further studies will be required to test its diagnostic value for RA before it can be implemented in clinical practice.

He Qingshan, Ding Hanmeng

2023-Mar-18

Radiology Radiology

Integration of Radiomics and Tumor Biomarkers in Interpretable Machine Learning Models

ArXiv Preprint

Despite the unprecedented performance of deep neural networks (DNNs) in computer vision, their practical application in the diagnosis and prognosis of cancer using medical imaging has been limited. One of the critical challenges for integrating diagnostic DNNs into radiological and oncological applications is their lack of interpretability, preventing clinicians from understanding the model predictions. Therefore, we study and propose the integration of expert-derived radiomics and DNN-predicted biomarkers in interpretable classifiers which we call ConRad, for computerized tomography (CT) scans of lung cancer. Importantly, the tumor biomarkers are predicted from a concept bottleneck model (CBM) such that once trained, our ConRad models do not require labor-intensive and time-consuming biomarkers. In our evaluation and practical application, the only input to ConRad is a segmented CT scan. The proposed model is compared to convolutional neural networks (CNNs) which act as a black box classifier. We further investigated and evaluated all combinations of radiomics, predicted biomarkers and CNN features in five different classifiers. We found the ConRad models using non-linear SVM and the logistic regression with the Lasso outperform others in five-fold cross-validation, although we highlight that interpretability of ConRad is its primary advantage. The Lasso is used for feature selection, which substantially reduces the number of non-zero weights while increasing the accuracy. Overall, the proposed ConRad model combines CBM-derived biomarkers and radiomics features in an interpretable ML model which perform excellently for the lung nodule malignancy classification.

Lennart Brocki, Neo Christopher Chung

2023-03-20