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

General General

Connecting higher education to workplace activities and earnings.

In PloS one ; h5-index 176.0

Higher education is a source of skill acquisition for many middle- and high-skilled jobs. But what specific skills do universities impart on students to prepare them for desirable careers? In this study, we analyze a large novel corpora of over one million syllabi from over eight hundred bachelors' granting US educational institutions to connect material taught in higher education to the detailed work activities in the US economy as reported by the US Department of Labor. First, we show how differences in taught skills both within and between college majors correspond to earnings differences of recent graduates. Further, we use the co-occurrence of taught skills across all of academia to predict the skills that will be taught in a major moving forward. Our unified information system connecting workplace skills to the skills taught during higher education can improve the workforce development of high-skilled workers, inform educational programs of future trends, and enable employers to quantify the skills of potential workers.

Chau Hung, Bana Sarah H, Bouvier Baptiste, Frank Morgan R

2023

Radiology Radiology

Deep Learning for Synthetic CT from Bone MRI in the Head and Neck.

In AJNR. American journal of neuroradiology

BACKGROUND AND PURPOSE : Bone MR imaging techniques enable visualization of cortical bone without the need for ionizing radiation. Automated conversion of bone MR imaging to synthetic CT is highly desirable for downstream image processing and eventual clinical adoption. Given the complex anatomy and pathology of the head and neck, deep learning models are ideally suited for learning such mapping.

MATERIALS AND METHODS : This was a retrospective study of 39 pediatric and adult patients with bone MR imaging and CT examinations of the head and neck. For each patient, MR imaging and CT data sets were spatially coregistered using multiple-point affine transformation. Paired MR imaging and CT slices were generated for model training, using 4-fold cross-validation. We trained 3 different encoder-decoder models: Light_U-Net (2 million parameters) and VGG-16 U-Net (29 million parameters) without and with transfer learning. Loss functions included mean absolute error, mean squared error, and a weighted average. Performance metrics included Pearson R, mean absolute error, mean squared error, bone precision, and bone recall. We investigated model generalizability by training and validating across different conditions.

RESULTS : The Light_U-Net architecture quantitatively outperformed VGG-16 models. Mean absolute error loss resulted in higher bone precision, while mean squared error yielded higher bone recall. Performance metrics decreased when using training data captured only in a different environment but increased when local training data were augmented with those from different hospitals, vendors, or MR imaging techniques.

CONCLUSIONS : We have optimized a robust deep learning model for conversion of bone MR imaging to synthetic CT, which shows good performance and generalizability when trained on different hospitals, vendors, and MR imaging techniques. This approach shows promise for facilitating downstream image processing and adoption into clinical practice.

Bambach S, Ho M-L

2022-Aug

General General

Correlation analysis of deep learning methods in S-ICD screening.

In Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc

BACKGROUND : Machine learning methods are used in the classification of various cardiovascular diseases through ECG data analysis. The concept of varying subcutaneous implantable cardiac defibrillator (S-ICD) eligibility, owing to the dynamicity of ECG signals, has been introduced before. There are practical limitations to acquiring longer durations of ECG signals for S-ICD screening. This study explored the potential use of deep learning methods in S-ICD screening.

METHODS : This was a retrospective study. A deep learning tool was used to provide descriptive analysis of the T:R ratios over 24 h recordings of S-ICD vectors. Spearman's rank correlation test was used to compare the results statistically to those of a "gold standard" S-ICD simulator.

RESULTS : A total of 14 patients (mean age: 63.7 ± 5.2 years, 71.4% male) were recruited and 28 vectors were analyzed. Mean T:R, standard deviation of T:R, and favorable ratio time (FVR)-a new concept introduced in this study-for all vectors combined were 0.21 ± 0.11, 0.08 ± 0.04, and 79 ± 30%, respectively. There were statistically significant strong correlations between the outcomes of our novel tool and the S-ICD simulator (p < .001).

CONCLUSION : Deep learning methods could provide a practical software solution to analyze data acquired for longer durations than current S-ICD screening practices. This could help select patients better suited for S-ICD therapy as well as guide vector selection in S-ICD eligible patients. Further work is needed before this could be translated into clinical practice.

ElRefai Mohamed, Abouelasaad Mohamed, Wiles Benedict M, Dunn Anthony J, Coniglio Stefano, Zemkoho Alain B, Morgan John, Roberts Paul R

2023-Mar-15

deep learning tools, screening, subcutaneous implantable cardiac defibrillators

Pathology Pathology

Single-cell Sequence Analysis Combined with Multiple Machine Learning to Identify Markers in Sepsis Patients: LILRA5.

In Inflammation

Sepsis is a disease with a very high mortality rate, mainly involving an immune-dysregulated response due to bacterial infection. Most studies are currently limited to the whole blood transcriptome level; however, at the single cell level, there is still a great deal unknown about specific cell subsets and disease markers. We obtained 29 peripheral blood single-cell sequencing data, including 66,283 cells from 10 confirmed samples of sepsis infection and 19 healthy samples. Cells related to the sepsis phenotype were identified and characterized by the "scissor" method. The regulatory relationships of sepsis-related phenotype cells in the cellular communication network were clarified using the "cell chat" method. The least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), and random forest (RF) were used to identify sepsis signature genes of diagnostic value. External validation was performed using multiple datasets from the GEO database (GSE28750, GSE185263, GSE57065) and 40 clinical samples. Bayesian algorithm was used to calculate the regulatory network of LILRA5 co-expressed genes. The stability of atenolol-targeting LILRA5 was determined by molecular docking techniques. Ultimately, action trajectory and survival analyses demonstrate the effectiveness of atenolol-targeted LILRA5 in treating patients with sepsis. We successfully identified 1215 healthy phenotypic cells and 462 sepsis phenotypic cells. We focused on 447 monocytes of the sepsis phenotype. Among the cellular communications, there were a large number of differences between these cells and other immune cells showing a significant inflammatory phenotype compared to the healthy phenotypic cells. Together, the three machine learning algorithms identified the LILRA5 marker gene in sepsis patients, and validation results from multiple external datasets as well as real-world clinical samples demonstrated the robust diagnostic performance of LILRA5. The AUC values of LILRA5 in the external datasets GSE28750, GSE185263, and GSE57065 could reach 0.875, 0.940, and 0.980, in that order. Bayesian networks identified a large number of unknown regulatory relationships for LILRA5 co-expression. Molecular docking results demonstrated the possibility of atenolol targeting LILRA5 for the treatment of sepsis. Behavioral trajectory analysis and survival analysis demonstrate that atenolol has a desirable therapeutic effect. LILRA5 is a marker gene in sepsis patients, and atenolol can stably target LILRA5.

Ning Jingyuan, Fan Xiaoqing, Sun Keran, Wang Xuan, Li Hongru, Jia Keqi, Ma Cuiqing

2023-Mar-15

LILRA5, machine learning, molecular docking, sepsis, single cell

Surgery Surgery

Unlocking the microbial studies through computational approaches: how far have we reached?

In Environmental science and pollution research international

The metagenomics approach accelerated the study of genetic information from uncultured microbes and complex microbial communities. In silico research also facilitated an understanding of protein-DNA interactions, protein-protein interactions, docking between proteins and phyto/biochemicals for drug design, and modeling of the 3D structure of proteins. These in silico approaches provided insight into analyzing pathogenic and nonpathogenic strains that helped in the identification of probable genes for vaccines and antimicrobial agents and comparing whole-genome sequences to microbial evolution. Artificial intelligence, more precisely machine learning (ML) and deep learning (DL), has proven to be a promising approach in the field of microbiology to handle, analyze, and utilize large data that are generated through nucleic acid sequencing and proteomics. This enabled the understanding of the functional and taxonomic diversity of microorganisms. ML and DL have been used in the prediction and forecasting of diseases and applied to trace environmental contaminants and environmental quality. This review presents an in-depth analysis of the recent application of silico approaches in microbial genomics, proteomics, functional diversity, vaccine development, and drug design.

Kumar Rajnish, Yadav Garima, Kuddus Mohammed, Ashraf Ghulam Md, Singh Rachana

2023-Mar-15

Artificial intelligence, Deep learning, Machine learning, Metagenomics, Microbiology

Surgery Surgery

ResMIBCU-Net: an encoder-decoder network with residual blocks, modified inverted residual block, and bi-directional ConvLSTM for impacted tooth segmentation in panoramic X-ray images.

In Oral radiology

OBJECTIVE : Impacted tooth is a common problem that can occur at any age, causing tooth decay, root resorption, and pain in the later stages. In recent years, major advances have been made in medical imaging segmentation using deep convolutional neural network-based networks. In this study, we report on the development of an artificial intelligence system for the automatic identification of impacted tooth from panoramic dental X-ray images.

METHODS : Among existing networks, in medical imaging segmentation, U-Net architectures are widely implemented. In this article, for dental X-ray image segmentation, blocks and convolutional block structures using inverted residual blocks are upgraded by taking advantage of U-Net's network capacity-intensive connections. At the same time, we propose a method for jumping connections in which bi-directional convolution long short-term memory is used instead of a simple connection. Assessment of the proposed artificial intelligence model performance was evaluated with accuracy, F1-score, intersection over union, and recall.

RESULTS : In the proposed method, experimental results are obtained with 99.82% accuracy, 91.59% F1-score, 84.48% intersection over union, and 90.71% recall.

CONCLUSION : Our findings show that our artificial intelligence system could help with future diagnostic support in clinical practice.

Imak Andaç, Çelebi Adalet, Polat Onur, Türkoğlu Muammer, Şengür Abdulkadir

2023-Mar-15

Deep learning, Encoder–decoder network, Impacted tooth detection, Oral health, Panoramic radiography