Cell-free DNA in maternal blood and artificial intelligence: accurate prenatal detection of fetal congenital heart defects

Rare pathogenic NR2F2 (COUP-TFII) variants as potential etiological causes in pediatric patients with congenital heart diseases (CHDs)

OBJECTIVES

Congenital heart diseases (CHDs) are complex genetic disorders, and their genetic basis is not yet fully understood. Nuclear receptor subfamily 2 group F member 2 (NR2F2 or COUP-TFII) encodes a transcription factor which is expressed at high levels during mammalian development. Few studies have identified heterozygous and rare variants in the NR2F2 gene in individuals with CHD. This study aimed to evaluate the association between pathogenic genetic alterations in NR2F2 with CHD risk.

METHODS

A case-control study was conducted on a group of 135 patients (83 boys and 52 girls) with various types of non-hereditary, isolated CHD who were undergoing open-heart surgery. Additionally, 95 matched healthy children without syndromic or isolated heart abnormalities were selected.

RESULTS

Using Sanger sequencing, we identified 5 heterozygous single nucleotide variants in exons 2 and 3 of the NR2F2 gene. These variations were novel and not present in any genomic variation databases. Four of the variations were missense mutations (p.Pro159Arg, p.Ser329Phe, p.Qln338Pro, and p.Tyr348Ser) and one was a synonymous variant (p.G361 = ) in the coding region. Importantly, in silico results indicated that the missense variants had pathogenic effects on protein function. Additionally, the missense variants substantially altered the predicted structure of COUP-TFII.

CONCLUSION

The results we obtained not only validate the correlation between NR2F2 mutations and CHDs but also have significant potential for guiding new preventive and therapeutic strategies. This could contribute to the advancement of medical interventions in the fields of cardiology and genetics.

The potential of circulating free DNA of methylated IGFBP as a biomarker for type 2 diabetes Mellitus: A Comprehensive review

T2DM detection methods are commonly used in teens and adults but are generally unsuitable to unborn fetuses in the context of non-invasive prenatal testing (NIPT). Biophysical and biochemical tests for fetuses are often invasive, carry risks, and have low sensitivity and specificity, with no direct method available to diagnose T2DM in utero. In contrast, cell-free DNA (cfDNA) is known have high sensitivity (93-98 %) and specificity (94-100 %) for cancer detection and fetal genetic disorders (trisomy 21, 8, and 13) making it applicable for fetal epigenetic and genetic analysis, including T2DM early detection. However, no study has explored its use for this purpose. Our review focuses on the potential of IGFBP methylation levels in cfDNA as biomarkers for NIPT of T2DM. Placental global hypomethylation in GDM may predict T2DM during the prenatal period, and a similar pattern potentially be detected in cfDNA. Targeted genes reliable for NIPT, such as IGFBPs are needed because their significant role in T2DM and GDM. Among these, IGFBP-1 and IGFBP-2 have shown potential as predictive genes, exhibiting hypermethylation in placental tissue from GDM cases. This hypermethylation reduces their expression and the formation of the IGF-1-IGFBP complex, leading to increased levels of free IGF-1, which is associated with T2DM in the fetus. Hypermethylation regions have longer fragment sizes in cfDNA, thus in T2DM cases, hypermethylation of IGFBP-1 and IGFBP-2 from fetus results in longer cfDNA fragments. Therefore, analyzing the methylation levels and fragment sizes of IGFBP-1 or IGFBP-2 cfDNA could be a promising biomarker for identifying fetal T2DM risk non-invasively.

Precision fetal cardiology detects cyanotic congenital heart disease using maternal saliva metabolome and artificial intelligence

Prenatal sonographic diagnosis of congenital heart disease (CHD) can lead to improved morbidity and mortality. However, the diagnostic accuracy of ultrasound, the sole prenatal screening tool, remains limited. Failed prenatal or early newborn detection of cyanotic CHD (CCHD) can have disastrous consequences. We therefore sought to use a Precision Fetal Cardiology based approach combining metabolomic profiling of maternal saliva and machine learning, a major branch of artificial intelligence (AI), for the prenatal detection of isolated, non-syndromic cyanotic CHD. Metabolomic analyses using Ultra-High Performance Liquid Chromatography/Mass Spectrometry identified 468 metabolites in the saliva. Six different AI platforms were utilized for the detection of CCHD and CHD overall. AI achieved excellent accuracy for the CCHD detection: Area Under the ROC curve: AUC (95% CI) = 0.819 (0.635-1.00) with a sensitivity and specificity of 92.5% and 87.0%, and for CHD overall: AUC (95% CI) = 0.828 (0.635-1.00) with a sensitivity of 90.5% and specificity of 88.0%. Similarly high accuracies were achieved for the detection of CHD overall: AUC (95% CI) = 0.8488 (0.635-1.00) with a sensitivity of 92.5% and specificity of 91.0%. Pathway analysis showed significant alterations in Arachidonic Acid, Alpha-linoleic acid, and Tryptophan metabolism indicating significant lipid dysfunction in cyanotic CHD. In summary, we report for the first time, the accurate detection of non-syndromic cyanotic CHD using maternal salivary metabolomics. Further, analysis revealed significant alteration of lipid metabolism.

DNA methylation of the Lamin A/C gene is associated with congenital heart disease

BACKGROUND

Prior studies report associations of maternal serum Lamin A, encoded by the LMNA gene, with fetal congenital heart disease (CHD). It is unknown whether DNA methylation (DNAm) of cytosine-phosphate-guanine (CpG) sites in LMNA impacts the CHD susceptibility.

METHODS

We investigated the associations of LMNA DNAm with CHD using publicly available data of CHD cases (n = 197) and controls (n = 134) from the Gene Expression Omnibus repository. Peripheral blood DNAm was measured using Illumina 850 K BeadChip for cases and 450 K BeadChip for controls. We tested 31 LMNA CpGs to identify differences in DNAm between cases and controls using linear regression correcting for multiple testing with false discovery rate (FDR). In a case-only analysis, we tested the variations in LMNA DNAm between CHD subtypes. To identify the consistency of DNAm across tissue types we compared peripheral blood (n = 197) and heart tissue DNAm (n = 20) in CHD cases.

RESULTS

After adjusting for age, sex, and cell types there were significant differences in 17 of the 31 LMNA CpGs between CHD cases and controls (FDR p ≤ .05). We identified lower DNAm of cg09820673 at 3' UTR for hypoplastic left heart syndrome compared to other CHD subtypes. Three CpGs exhibited uniform DNAm in blood and heart tissues in cases. Eleven CpGs showed changes in the same direction in blood and heart tissues in cases compared to controls.

CONCLUSION

We identify statistically significant differences in LMNA DNAm between CHD cases and controls. Future studies should investigate the role of maternal LMNA DNAm in CHD development.

Advancing Breast Cancer Research Through Collaborative Computing: Harnessing Google Colab for Innovation

This investigation explores the potential efficacy of machine learning algorithms (MLAs), particularly convolutional neural networks (CNNs), in distinguishing between benign and malignant breast cancer tissue through the analysis of 1000 breast cancer images gathered from Kaggle.com, a domain of publicly accessible data. The dataset was meticulously partitioned into training, validation, and testing sets to facilitate model development and evaluation. Our results reveal promising outcomes, with the developed model achieving notable precision (92%), recall (92%), accuracy (92%), sensitivity (89%), specificity (96%), an F1 score of 0.92, and an area under the curve (AUC) of 0.944. These metrics underscore the model's ability to accurately identify malignant breast cancer images. Because of limitations such as sample size and potential variations in image quality, further research, data collection, and integration of theoretical models in a real-world clinical setting are needed to expand the reliability and generalizability of these MLAs. Nonetheless, this study serves to highlight the potential use of artificial intelligence models as supporting tools for physicians to utilize in breast cancer detection.

The Lifelong Impact of Artificial Intelligence and Clinical Prediction Models on Patients With Tetralogy of Fallot

Medical advancements in the diagnosis, surgical techniques, perioperative care, and continued care throughout childhood have transformed the outlook for individuals with tetralogy of Fallot (TOF), improving survival and shifting the perspective towards lifelong care. However, with a growing population of survivors, longstanding challenges have been accentuated, and new challenges have surfaced, necessitating a re-evaluation of TOF care. Availability of prenatal diagnostics, insufficient information from traditional imaging techniques, previously unforeseen medical complications, and debates surrounding optimal timing and indications for reintervention are among the emerging issues. To address these challenges, the integration of artificial intelligence and machine learning holds great promise as they have the potential to revolutionize patient management and positively impact lifelong outcomes for individuals with TOF. Innovative applications of artificial intelligence and machine learning have spanned across multiple domains of TOF care, including screening and diagnosis, automated image processing and interpretation, clinical risk stratification, and planning and performing cardiac interventions. By embracing these advancements and incorporating them into routine clinical practice, personalized medicine could be delivered, leading to the best possible outcomes for patients. In this review, we provide an overview of these evolving applications and emphasize the challenges, limitations, and future potential for integrating them into clinical care.

Precision oncology: Artificial intelligence, circulating cell-free DNA, and the minimally invasive detection of pancreatic cancer-A pilot study

BACKGROUND

Pancreatic cancer (PC) is among the most lethal cancers. The lack of effective tools for early detection results in late tumor detection and, consequently, high mortality rate. Precision oncology aims to develop targeted individual treatments based on advanced computational approaches of omics data. Biomarkers, such as global alteration of cytosine (CpG) methylation, can be pivotal for these objectives. In this study, we performed DNA methylation profiling of pancreatic cancer patients using circulating cell-free DNA (cfDNA) and artificial intelligence (AI) including Deep Learning (DL) for minimally invasive detection to elucidate the epigenetic pathogenesis of PC.

METHODS

The Illumina Infinium HD Assay was used for genome-wide DNA methylation profiling of cfDNA in treatment-naïve patients. Six AI algorithms were used to determine PC detection accuracy based on cytosine (CpG) methylation markers. Additional strategies for minimizing overfitting were employed. The molecular pathogenesis was interrogated using enrichment analysis.

RESULTS

In total, we identified 4556 significantly differentially methylated CpGs (q-value < 0.05; Bonferroni correction) in PC versus controls. Highly accurate PC detection was achieved with all 6 AI platforms (Area under the receiver operator characteristics curve [0.90-1.00]). For example, DL achieved AUC (95% CI): 1.00 (0.95-1.00), with a sensitivity and specificity of 100%. A separate modeling approach based on logistic regression-based yielded an AUC (95% CI) 1.0 (1.0-1.0) with a sensitivity and specificity of 100% for PC detection. The top four biological pathways that were epigenetically altered in PC and are known to be linked with cancer are discussed.

CONCLUSION

Using a minimally invasive approach, AI, and epigenetic analysis of circulating cfDNA, high predictive accuracy for PC was achieved. From a clinical perspective, our findings suggest that that early detection leading to improved overall survival may be achievable in the future.

Integration of epigenetic regulatory mechanisms in heart failure

The number of "omics" approaches is continuously growing. Among others, epigenetics has appeared as an attractive area of investigation by the cardiovascular research community, notably considering its association with disease development. Complex diseases such as cardiovascular diseases have to be tackled using methods integrating different omics levels, so called "multi-omics" approaches. These approaches combine and co-analyze different levels of disease regulation. In this review, we present and discuss the role of epigenetic mechanisms in regulating gene expression and provide an integrated view of how these mechanisms are interlinked and regulate the development of cardiac disease, with a particular attention to heart failure. We focus on DNA, histone, and RNA modifications, and discuss the current methods and tools used for data integration and analysis. Enhancing the knowledge of these regulatory mechanisms may lead to novel therapeutic approaches and biomarkers for precision healthcare and improved clinical outcomes.