Noninvasive early diagnosis of intestinal diseases based on artificial intelligence in genomics and microbiome

Zhang, Weitong; Chen, Xingjian; Wong, Ka-Chun

doi:10.1111/jgh.15500

Cited by 18 publications

(8 citation statements)

References 48 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, if any significant alteration in the functional capacity of a microbial community potentially results in meaningful biological implications on the equilibrium and the stability of the microbiome, such perturbation would lead to the change of the host phenotype (i.e., the clinical condition). Therefore, the adequate analyses of metagenomic data acquired from clinical samples 67–73 may lead to the discovery of microbiome markers that give hints on novel diagnostic and therapeutic approaches, as we demonstrated in our study.…”

Section: Discussionmentioning

confidence: 70%

Functional profile of host microbiome indicates Clostridioides difficile infection

Nzabarushimana

Tang

2022

Gut Microbes

View full text Add to dashboard Cite

Clostridioides difficile infection (CDI) is a gastro-intestinal (GI) infection that illustrates how perturbations in symbiotic host–microbiome interactions render the GI tract vulnerable to the opportunistic pathogens. CDI also serves as an example of how such perturbations could be reversed via gut microbiota modulation mechanisms, especially fecal microbiota transplantation (FMT). However, microbiome-mediated diagnosis of CDI remains understudied. Here, we evaluated the diagnostic capabilities of the fecal microbiome on the prediction of CDI. We used the metagenomic sequencing data from ten previous studies, encompassing those acquired from CDI patients treated by FMT, CDI-negative patients presenting other intestinal health conditions, and healthy volunteers taking antibiotics. We designed a hybrid species/function profiling approach that determines the abundances of microbial species in the community contributing to its functional profile. These functionally informed taxonomic profiles were then used for classification of the microbial samples. We used logistic regression (LR) models using these features, which showed high prediction accuracy (with an average ), substantiating that the species/function composition of the gut microbiome has a robust diagnostic prediction of CDI. We further assessed the confounding impact of antibiotic therapy on CDI prediction and found that it is distinguishable from the CDI impact. Finally, we devised a log-odds score computed from the output of the LR models to quantify the likelihood of CDI in a gut microbiome sample and applied it to evaluating the effectiveness of FMT based on post-FMT microbiome samples. The results showed that the gut microbiome of patients exhibited a gradual but steady improvement after receiving successful FMT, indicating the restoration of the normal microbiome functions.

show abstract

Section: Discussionmentioning

confidence: 70%

Functional profile of host microbiome indicates Clostridioides difficile infection

Nzabarushimana

Tang

2022

Gut Microbes

View full text Add to dashboard Cite

show abstract

“…Therefore, we attempted to predict the probability of cancer in CAD patients. The traditional method of most cancer diagnoses is tissue biopsy or imaging examination ( 33 , 34 ). However, these are invasive, demanding, and time-consuming.…”

Section: Discussionmentioning

confidence: 99%

Coronary Atherosclerotic Disease and Cancer: Risk Factors and Interrelation

Zhao

Lei

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

BackgroundIn our clinical work, we found that cancer patients were susceptible to coronary atherosclerotic heart disease (CAD). However, less is known about the relationship between CAD and cancer. The present study aimed to identify the risk factors for CAD and cancer, as well as the relationship between CAD and cancer.MethodsIn this retrospective study, 1600 patients between January 2012 and June 2019 were enrolled and divided into groups according to whether they had CAD or cancer. Single-factor and multivariate analysis methods were applied to examine the risk factors for CAD and cancer.Results(1) Cancer prevalence was significantly higher in patients with CAD than in patients without CAD (47.2 vs. 20.9%). The prevalence of CAD in cancer and non-cancer patients was 78.9 and 52.4%, respectively. (2) Multivariable logistic regression showed that patients with cancer had a higher risk of developing CAD than non-cancer patients (OR: 2.024, 95% CI: 1.475 to 2.778, p < 0.001). Respiratory (OR: 1.981, 95% CI: 1.236–3.175, p = 0.005), digestive (OR: 1.899, 95% CI: 1.177–3.064, p = 0.009) and urogenital (OR: 3.595, 95% CI: 1.696–7.620, p = 0.001) cancers were significantly associated with a higher risk of CAD compared with no cancer. (3) Patients with CAD also had a higher risk of developing cancer than non-CAD patients (OR = 2.157, 95% CI: 1.603 to 2.902, p < 0.001). Patients in the Alanine aminotransferase (ALT) level ≥ 40 U/L group had a lower risk of cancer than patients in the ALT level < 20 U/L group (OR: 0.490, 95% CI: 0.333–0.722, p < 0.001). (4) An integrated variable (Y = 0.205 × 10–1 age − 0.595 × 10–2 HGB − 0.116 × 10–1 ALT + 0.135 FIB) was identified for monitoring the occurrence of cancer among CAD patients, with an AUC of 0.720 and clinical sensitivity/specificity of 0.617/0.711.Conclusion(1) We discovered that CAD was an independent risk factor for cancer and vice versa. (2) Digestive, respiratory and urogenital cancers were independent risk factors for CAD. (3) We created a formula for the prediction of cancer among CAD patients. (4) ALT, usually considered a risk factor, was proven to be a protective factor for cancer in this study.

show abstract

“…With the advancement of bioinformatics and artificial intelligence (AI), there is a growing interest in research on machine-learning-enabled big data disease diagnosis because of its cost-effectiveness and high accuracy. ,− ,,− Machine learning algorithms possess unique advantages in solving problems like classification and regression by automatically learning from data sets. ,− In the context of disease diagnosis, appropriate application of machine learning algorithms enables the extraction of logical rules from complex and extensive disease data for establishing training models that can identify, classify, or predict unknown samples. ,, …”

Section: Machine Learning Algorithmmentioning

confidence: 99%

Advances in Machine Learning Processing of Big Data from Disease Diagnosis Sensors

Lu,

Yang,

et al. 2024

ACS Sens.

View full text Add to dashboard Cite

Exploring accurate, noninvasive, and inexpensive disease diagnostic sensors is a critical task in the fields of chemistry, biology, and medicine. The complexity of biological systems and the explosive growth of biomarker data have driven machine learning to become a powerful tool for mining and processing big data from disease diagnosis sensors. With the development of bioinformatics and artificial intelligence (AI), machine learning models formed by data mining have been able to guide more sensitive and accurate molecular computing. This review presents an overview of big data collection approaches and fundamental machine learning algorithms and discusses recent advances in machine learning and molecular computational disease diagnostic sensors. More specifically, we highlight existing modular workflows and key opportunities and challenges for machine learning to achieve disease diagnosis through big data mining.

show abstract

Noninvasive early diagnosis of intestinal diseases based on artificial intelligence in genomics and microbiome

Cited by 18 publications

References 48 publications

Functional profile of host microbiome indicates Clostridioides difficile infection

Functional profile of host microbiome indicates Clostridioides difficile infection

Coronary Atherosclerotic Disease and Cancer: Risk Factors and Interrelation

Advances in Machine Learning Processing of Big Data from Disease Diagnosis Sensors

Contact Info

Product

Resources

About