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

General General

Health Monitoring of Movement Disorder Subject based on Diamond Stacked Sparse Autoencoder Ensemble Model

ArXiv Preprint

The health monitoring of chronic diseases is very important for people with movement disorders because of their limited mobility and long duration of chronic diseases. Machine learning-based processing of data collected from the human with movement disorders using wearable sensors is an effective method currently available for health monitoring. However, wearable sensor systems are difficult to obtain high-quality and large amounts of data, which cannot meet the requirement for diagnostic accuracy. Moreover, existing machine learning methods do not handle this problem well. Feature learning is key to machine learning. To solve this problem, a health monitoring of movement disorder subject based on diamond stacked sparse autoencoder ensemble model (DsaeEM) is proposed in this paper. This algorithm has two major components. First, feature expansion is designed using feature-embedded stacked sparse autoencoder (FSSAE). Second, a feature reduction mechanism is designed to remove the redundancy among the expanded features. This mechanism includes L1 regularized feature-reduction algorithm and the improved manifold dimensionality reduction algorithm. This paper refers to the combined feature expansion and feature reduction mechanism as the diamond-like feature learning mechanism. The method is experimentally verified with several state of art algorithms and on two datasets. The results show that the proposed algorithm has higher accuracy apparently. In conclusion, this study developed an effective and feasible feature-learning algorithm for the recognition of chronic diseases.

Likun Tang, Jie Ma, Yongming Li

2023-03-15

Surgery Surgery

Development and Assessment of Assisted Diagnosis Models Using Machine Learning for Identifying Elderly Patients With Malnutrition: Cohort Study.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Older patients are at an increased risk of malnutrition due to many factors related to poor clinical outcomes.

OBJECTIVE : This study aims to develop an assisted diagnosis model using machine learning (ML) for identifying older patients with malnutrition and providing the focus of individualized treatment.

METHODS : We reanalyzed a multicenter, observational cohort study including 2660 older patients. Baseline malnutrition was defined using the global leadership initiative on malnutrition (GLIM) criteria, and the study population was randomly divided into a derivation group (2128/2660, 80%) and a validation group (532/2660, 20%). We applied 5 ML algorithms and further explored the relationship between features and the risk of malnutrition by using the Shapley additive explanations visualization method.

RESULTS : The proposed ML models were capable to identify older patients with malnutrition. In the external validation cohort, the top 3 models by the area under the receiver operating characteristic curve were light gradient boosting machine (92.1%), extreme gradient boosting (91.9%), and the random forest model (91.5%). Additionally, the analysis of the importance of features revealed that BMI, weight loss, and calf circumference were the strongest predictors to affect GLIM. A BMI of below 21 kg/m2 was associated with a higher risk of GLIM in older people.

CONCLUSIONS : We developed ML models for assisting diagnosis of malnutrition based on the GLIM criteria. The cutoff values of laboratory tests generated by Shapley additive explanations could provide references for the identification of malnutrition.

TRIAL REGISTRATION : Chinese Clinical Trial Registry ChiCTR-EPC-14005253; https://www.chictr.org.cn/showproj.aspx?proj=9542.

Wang Xue, Yang Fengchun, Zhu Mingwei, Cui Hongyuan, Wei Junmin, Li Jiao, Chen Wei

2023-Mar-14

GLIM, SHAP, Shapley additive explanation, XGBoost, algorithm, diagnose, diagnosis, diagnostic, disease-related malnutrition, elder, global leadership initiative on malnutrition, machine learning, malnutrition, model, nutrition, older adult, older inpatients, risk, visualization

General General

The Effectiveness of Wearable Devices Using Artificial Intelligence for Blood Glucose Level Forecasting or Prediction: Systematic Review.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : In 2021 alone, diabetes mellitus, a metabolic disorder primarily characterized by abnormally high blood glucose (BG) levels, affected 537 million people globally, and over 6 million deaths were reported. The use of noninvasive technologies, such as wearable devices (WDs), to regulate and monitor BG in people with diabetes is a relatively new concept and yet in its infancy. Noninvasive WDs coupled with machine learning (ML) techniques have the potential to understand and conclude meaningful information from the gathered data and provide clinically meaningful advanced analytics for the purpose of forecasting or prediction.

OBJECTIVE : The purpose of this study is to provide a systematic review complete with a quality assessment looking at diabetes effectiveness of using artificial intelligence (AI) in WDs for forecasting or predicting BG levels.

METHODS : We searched 7 of the most popular bibliographic databases. Two reviewers performed study selection and data extraction independently before cross-checking the extracted data. A narrative approach was used to synthesize the data. Quality assessment was performed using an adapted version of the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.

RESULTS : From the initial 3872 studies, the features from 12 studies were reported after filtering according to our predefined inclusion criteria. The reference standard in all studies overall (n=11, 92%) was classified as low, as all ground truths were easily replicable. Since the data input to AI technology was highly standardized and there was no effect of flow or time frame on the final output, both factors were categorized in a low-risk group (n=11, 92%). It was observed that classical ML approaches were deployed by half of the studies, the most popular being ensemble-boosted trees (random forest). The most common evaluation metric used was Clarke grid error (n=7, 58%), followed by root mean square error (n=5, 42%). The wide usage of photoplethysmogram and near-infrared sensors was observed on wrist-worn devices.

CONCLUSIONS : This review has provided the most extensive work to date summarizing WDs that use ML for diabetic-related BG level forecasting or prediction. Although current studies are few, this study suggests that the general quality of the studies was considered high, as revealed by the QUADAS-2 assessment tool. Further validation is needed for commercially available devices, but we envisage that WDs in general have the potential to remove the need for invasive devices completely for glucose monitoring in the not-too-distant future.

TRIAL REGISTRATION : PROSPERO CRD42022303175; https://tinyurl.com/3n9jaayc.

Ahmed Arfan, Aziz Sarah, Abd-Alrazaq Alaa, Farooq Faisal, Househ Mowafa, Sheikh Javaid

2023-Mar-14

artificial intelligence, blood glucose, diabetes, forecasting, machine learning, prediction, wearable devices

Surgery Surgery

Effectiveness of artificial intelligence-assisted colonoscopy in early diagnosis of colorectal cancer: a systematic review.

In International journal of surgery (London, England)

INTRODUCTION : As AI-assisted diagnosis gained immense popularity, it is imperative to consider its utility and efficiency in the early diagnosis of colorectal cancer, responsible for over 1.8 million cases and 881,000 deaths globally, as reported in 2018. Improved adenoma detection rate, as well as better characterizations of polyps, are significant advantages of AIC. This systematic review investigates the effectiveness of AIC in the early diagnosis of CRC as compared to conventional colonoscopy.

METHODS : Electronic databases such as PubMed/Medline, SCOPUS, and Web of Science (WOS) were reviewed for original studies (randomized controlled trials, observational studies), systematic reviews, and meta-analysis between 2017-2022 utilizing MESH terminology in a broad search strategy. All searches were performed and analyzed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology and were conducted from November,2022. A data extraction form based on the Cochrane Consumers and Communication Review group's extraction template for quality assessment and evidence synthesis was used for data extraction. All included studies considered for bias and ethical criteria and provided valuable evidence to answer the research question.

RESULTS : The database search identified 218 studies, including 87 from PubMed, 60 from SCOPUS, and 71 from Web of Science databases. The retrieved studies from the databases were imported to Rayyan software and a duplicate article check was performed, all duplicate articles were removed after careful evaluation of the data. The abstract and full-text screening was performed in accordance with the following eligibility criteria: STROBE for observational studies; PRISMA for review articles, ENTREQ for narrative studies; and modified JADAD for randomized controlled trials (RCT). This yielded 15 studies that met the requirements for our systematic review and were finally included in the review.

CONCLUSION : AIC is a safe, highly effective screening tool that can increase the detection rate of adenomas, and polyps resulting in early diagnosis of colorectal cancer in adults when compared to conventional colonoscopy. The results of this systematic review prompt further large-scale research to investigate the effectiveness in accordance with gender, race, and socioeconomic status as well as its influence on prognosis and survival rate.

Mehta Aashna, Kumar Harendra, Yazji Katia, Wireko Andrew Awuah, Sivanandan Nagarajan Jai, Ghosh Bikona, Nahas Ahmad, Morales Ojeda Luis, Chandra Ayush, Sharath Medha, Huang Helen, Garg Tulika, Isik Arda

2023-Mar-15

Ophthalmology Ophthalmology

Morphometric Analysis of Retinal Ganglion Cell Axons in Normal and Glaucomatous Brown Norway Rats Optic Nerves.

In Translational vision science & technology

PURPOSE : A reference atlas of optic nerve (ON) retinal ganglion cell (RGC) axons could facilitate studies of neuro-ophthalmic diseases by detecting subtle RGC axonal changes. Here we construct an RGC axonal atlas for normotensive eyes in Brown Norway rats, widely used in glaucoma research, and also develop/evaluate several novel metrics of axonal damage in hypertensive eyes.

METHODS : Light micrographs of entire ON cross-sections from hypertensive and normotensive eyes were processed through a deep learning-based algorithm, AxoNet2.0, to determine axonal morphological properties and were semiquantitatively scored using the Morrison grading scale (MGS) to provide a damage score independent of AxoNet2.0 outcomes. To construct atlases, ONs were conformally mapped onto an ON "template," and axonal morphometric data was computed for each region. We also developed damage metrics based on myelin morphometry.

RESULTS : In normotensive eyes, average axon density was ∼0.3 axons/µm2 (i.e., ∼80,000 axons in an ON). We measured axoplasm diameter, eccentricity, cross-sectional area, and myelin g-ratio and thickness. Most morphological parameters exhibited a wide range of coefficients of variation (CoV); however, myelin thickness CoV was only ∼2% in normotensive eyes. In hypertensive eyes, increased myelin thickness correlated strongly with MGS (P < 0.0001).

CONCLUSIONS : We present the first comprehensive normative RGC axon morphometric atlas for Brown Norway rat eyes. We suggest objective, repeatable damage metrics based on RGC axon myelin thickness for hypertensive eyes.

TRANSLATIONAL RELEVANCE : These tools can evaluate regional changes in RGCs and overall levels of damage in glaucoma studies using Brown Norway rats.

Goyal Vidisha, Read A Thomas, Brown Dillon M, Brawer Luke, Bateh Kaitlyn, Hannon Bailey G, Feola Andrew J, Ethier C Ross

2023-Mar-01

Ophthalmology Ophthalmology

AxoNet 2.0: A Deep Learning-Based Tool for Morphometric Analysis of Retinal Ganglion Cell Axons.

In Translational vision science & technology

PURPOSE : Assessment of glaucomatous damage in animal models is facilitated by rapid and accurate quantification of retinal ganglion cell (RGC) axonal loss and morphologic change. However, manual assessment is extremely time- and labor-intensive. Here, we developed AxoNet 2.0, an automated deep learning (DL) tool that (i) counts normal-appearing RGC axons and (ii) quantifies their morphometry from light micrographs.

METHODS : A DL algorithm was trained to segment the axoplasm and myelin sheath of normal-appearing axons using manually-annotated rat optic nerve (ON) cross-sectional micrographs. Performance was quantified by various metrics (e.g., soft-Dice coefficient between predicted and ground-truth segmentations). We also quantified axon counts, axon density, and axon size distributions between hypertensive and control eyes and compared to literature reports.

RESULTS : AxoNet 2.0 performed very well when compared to manual annotations of rat ON (R2 = 0.92 for automated vs. manual counts, soft-Dice coefficient = 0.81 ± 0.02, mean absolute percentage error in axonal morphometric outcomes < 15%). AxoNet 2.0 also showed promise for generalization, performing well on other animal models (R2 = 0.97 between automated versus manual counts for mice and 0.98 for non-human primates). As expected, the algorithm detected decreased in axon density in hypertensive rat eyes (P ≪ 0.001) with preferential loss of large axons (P < 0.001).

CONCLUSIONS : AxoNet 2.0 provides a fast and nonsubjective tool to quantify both RGC axon counts and morphological features, thus assisting with assessing axonal damage in animal models of glaucomatous optic neuropathy.

TRANSLATIONAL RELEVANCE : This deep learning approach will increase rigor of basic science studies designed to investigate RGC axon protection and regeneration.

Goyal Vidisha, Read A Thomas, Ritch Matthew D, Hannon Bailey G, Rodriguez Gabriela Sanchez, Brown Dillon M, Feola Andrew J, Hedberg-Buenz Adam, Cull Grant A, Reynaud Juan, Garvin Mona K, Anderson Michael G, Burgoyne Claude F, Ethier C Ross

2023-Mar-01