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

General General

Identifying Disease of Interest With Deep Learning Using Diagnosis Code.

In Journal of Korean medical science

BACKGROUND : Autoencoder (AE) is one of the deep learning techniques that uses an artificial neural network to reconstruct its input data in the output layer. We constructed a novel supervised AE model and tested its performance in the prediction of a co-existence of the disease of interest only using diagnostic codes.

METHODS : Diagnostic codes of one million randomly sampled patients listed in the Korean National Health Information Database in 2019 were used to train, validate, and test the prediction model. The first used AE solely for a feature engineering tool for an input of a classifier. Supervised Multi-Layer Perceptron (sMLP) was added to train a classifier to predict a binary level with latent representation as an input (AE + sMLP). The second model simultaneously updated the parameters in the AE and the connected MLP classifier during the learning process (End-to-End Supervised AE [EEsAE]). We tested the performances of these two models against baseline models, eXtreme Gradient Boosting (XGB) and naïve Bayes, in the prediction of co-existing gastric cancer diagnosis.

RESULTS : The proposed EEsAE model yielded the highest F1-score and highest area under the curve (0.86). The EEsAE and AE + sMLP gave the highest recalls. XGB yielded the highest precision. Ablation study revealed that iron deficiency anemia, gastroesophageal reflux disease, essential hypertension, gastric ulcers, benign prostate hyperplasia, and shoulder lesion were the top 6 most influential diagnoses on performance.

CONCLUSION : A novel EEsAE model showed promising performance in the prediction of a disease of interest.

Cho Yoon-Sik, Kim Eunsun, Stafford Patrick L, Oh Min-Hwan, Kwon Younghoon

2023-Mar-20

Deep Learning, Diagnosis Code, Gastric Cancer, Machine Learning, Prediction

Dermatology Dermatology

[Progress in research of risk prediction model for chronic kidney disease].

In Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi

Chronic kidney disease (CKD) is an important global public health problem that greatly threatens population health. Application of risk prediction model is a crucial way for the primary prevention of CKD, which can stratify the risk for developing CKD and identify high-risk individuals for more intensive interventions. By now, more than twenty risk prediction models for CKD have been developed worldwide. There are also four domestic risk prediction models developed for Chinese population. However, none of these models have been recommended in clinical guidelines yet. The existing risk prediction models have some limitations in terms of outcome definition, predictors, strategies for handling missing data, and model derivation. In the future, the applications of emerging biomarkers and polygenic risk scores as well as advances in machine learning methods will provide more possibilities for the further improvement of the model.

Zeng Z Q, Yang S C, Yu C Q, Zhang L X, Lyu J, Li L M

2023-Mar-10

Pathology Pathology

Relationship between the deep features of the full-scan pathological map of mucinous gastric carcinoma and related genes based on deep learning.

In Heliyon

BACKGROUND : Long-term differential expression of disease-associated genes is a crucial driver of pathological changes in mucinous gastric carcinoma. Therefore, there should be a correlation between depth features extracted from pathology-based full-scan images using deep learning and disease-associated gene expression. This study tried to provides preliminary evidence that long-term differentially expressed (disease-associated) genes lead to subtle changes in disease pathology by exploring their correlation, and offer a new ideas for precise analysis of pathomics and combined analysis of pathomics and genomics.

METHODS : Full pathological scans, gene sequencing data, and clinical data of patients with mucinous gastric carcinoma were downloaded from TCGA data. The VGG-16 network architecture was used to construct a binary classification model to explore the potential of VGG-16 applications and extract the deep features of the pathology-based full-scan map. Differential gene expression analysis was performed and a protein-protein interaction network was constructed to screen disease-related core genes. Differential, Lasso regression, and extensive correlation analyses were used to screen for valuable deep features. Finally, a correlation analysis was used to determine whether there was a correlation between valuable deep features and disease-related core genes.

RESULT : The accuracy of the binary classification model was 0.775 ± 0.129. A total of 24 disease-related core genes were screened, including ASPM, AURKA, AURKB, BUB1, BUB1B, CCNA2, CCNB1, CCNB2, CDCA8, CDK1, CENPF, DLGAP5, KIF11, KIF20A, KIF2C, KIF4A, MELK, PBK, RRM2, TOP2A, TPX2, TTK, UBE2C, and ZWINT. In addition, differential, Lasso regression, and extensive correlation analyses were used to screen eight valuable deep features, including features 51, 106, 109, 118, 257, 282, 326, and 487. Finally, the results of the correlation analysis suggested that valuable deep features were either positively or negatively correlated with core gene expression.

CONCLUSION : The preliminary results of this study support our hypotheses. Deep learning may be an important bridge for the joint analysis of pathomics and genomics and provides preliminary evidence for long-term abnormal expression of genes leading to subtle changes in pathology.

Li Ding, Li Xiaoyuan, Li Shifang, Qi Mengmeng, Sun Xiaowei, Hu Guojie

2023-Mar

Bioinformatics, Deep learning, Genomics, Mucinous gastric carcinoma, Pathomics

General General

A deep learning approach for lane marking detection applying encode-decode instant segmentation network.

In Heliyon

A lot of people suffer from disability and death due to unintentional road accidents, which also result in the loss of a significant amount of financial assets. Several essential features of Advanced Driver Assistance Systems (ADAS) are being incorporated into vehicles by researchers to prevent road accidents. Lane marking detection (LMD) is a fundamental ADAS technology that helps the vehicle to keep its position in the lane. The current study employs Deep Learning (DL) methodologies and has several research constraints due to various problems. Researchers sometimes encounter difficulties in LMD due to environmental factors such as the variation of lights, obstacles, shadows, and curve lanes. To address these limitations, this study presents the Encode-Decode Instant Segmentation Network (EDIS-Net) as a DL methodology for detecting lane marking under various environmental situations with reliable accuracy. The framework is based on the E-Net architecture and incorporates combined cross-entropy and discriminative losses. The encoding segment was split into binary and instant segmentation to extract information about the lane pixels and the pixel position. DenselyBased Spatial Clustering of Application with Noise (DBSCAN) is employed to connect the predicted lane pixels and to get the final output. The system was trained with augmented data from the Tusimple dataset and then tested on three datasets: Tusimple, CalTech, and a local dataset. On the Tusimple dataset, the model achieved 97.39% accuracy. Furthermore, it has an average accuracy of 97.07% and 96.23% on the CalTech and local datasets, respectively. On the testing dataset, the EDIS-Net exhibited promising results compared to existing LMD approaches. Since the proposed framework performs better on the testing datasets, it can be argued that the model can recognize lane marking confidently in various scenarios. This study presents a novel EDIS-Net technique for efficient lane marking detection. It also includes the model's performance verification by testing in three different public datasets.

Al Mamun Abdullah, Em Poh Ping, Hossen Md Jakir, Jahan Busrat, Tahabilder Anik

2023-Mar

ADAS, CalTech, Deep learning, Lane markings detection, Segmentation, Tusimple

Public Health Public Health

Acceptability and Effectiveness of COVID-19 Contact Tracing Applications: A Case Study in Saudi Arabia of the Tawakkalna Application.

In Cureus

Background Contact tracing applications were introduced during the COVID-19 pandemic to mitigate the spread of the infection in several countries. In Saudi Arabia, the Tawakkalna application was developed. The Tawakkalna application is a mobile health solution aimed to track infection cases, save lives, and reduce the burden on health facilities. This study aims to explore the public's attitude to and acceptance levels of the Tawakkalna application and to evaluate its effectiveness regarding privacy and security. The main objective of this study is to investigate the user acceptability of contact tracing applications and explore the safety and privacy effectiveness of the COVID-19 contact tracing application, the Tawakkalna application. In addition, the study analyzes factors associated with acceptance levels and compares the results obtained to similar studies in other countries using similar applications. Methodology This study used a valid and reliable online survey that was used in similar studies conducted in other countries to assess the acceptability of the application. The survey was conducted from September to November 2021, and the final dataset included 205 participants. To investigate the privacy and security performance of the Tawakkalna application, we followed the investigation method used by similar research that investigated 28 contact tracing applications across Europe. Results Out of the 205 participants, 84.87% were in favor of the opt-in voluntary installation of the Tawakkalna application, and 49.75% of the participants were in favor of the opt-out automatic installation. Individuals' trust in the government had a huge impact on acceptance, with 60.98% of the participants supporting the application because they believed that the Tawakkalna application would help them stay healthy during the COVID-19 pandemic. Overall, 49% of the participants supporting the application also agreed to the de-identification of their collected data and providing it for research. The Tawakkalna application ranked at the top compared to other contact tracing applications regarding privacy and security. Conclusions The Tawakkalna application developed by the Saudi Data and Artificial Intelligence Authority was a response to the COVID-19 pandemic, which is considered the biggest public health crisis in recent times. The Saudi Arabian government gained the population's acceptance through effective endorsement and the spread of educational content through media channels. By complying with privacy policies, the Tawakkalna application is an effective tool to combat public health infectious diseases.

Dawood Safia, AlKadi Khulud

2023-Feb

acceptability, contact tracing, covid-19, mhealth, permission, privacy, privilege, security, tawakkalna

Public Health Public Health

Racial Equity in Healthcare Machine Learning: Illustrating Bias in Models With Minimal Bias Mitigation.

In Cureus

Background and objective While the potential of machine learning (ML) in healthcare to positively impact human health continues to grow, the potential for inequity in these methods must be assessed. In this study, we aimed to evaluate the presence of racial bias when five of the most common ML algorithms are used to create models with minimal processing to reduce racial bias. Methods By utilizing a CDC public database, we constructed models for the prediction of healthcare access (binary variable). Using area under the curve (AUC) as our performance metric, we calculated race-specific performance comparisons for each ML algorithm. We bootstrapped our entire analysis 20 times to produce confidence intervals for our AUC performance metrics. Results With the exception of only a few cases, we found that the performance for the White group was, in general, significantly higher than that of the other racial groups across all ML algorithms. Additionally, we found that the most accurate algorithm in our modeling was Extreme Gradient Boosting (XGBoost) followed by random forest, naive Bayes, support vector machine (SVM), and k-nearest neighbors (KNN). Conclusion Our study illustrates the predictive perils of incorporating minimal racial bias mitigation in ML models, resulting in predictive disparities by race. This is particularly concerning in the setting of evidence for limited bias mitigation in healthcare-related ML. There needs to be more conversation, research, and guidelines surrounding methods for racial bias assessment and mitigation in healthcare-related ML models, both those currently used and those in development.

Barton Michael, Hamza Mahmoud, Guevel Borna

2023-Feb

data science, health equity, healthcare technology, machine learning, racial bias