Newborn skin maturity models for gestational age prediction

A multicenter clinical trial evaluated the accuracy of a novel device to detect preterm newborns. A portable multiband reflectance photometric device assessed 781 newborns’ skin maturity and used machine learning models to predict reference gestational age, adjusting it to birth weight and antenatal corticosteroid therapy exposure. The day difference between the reference and the test had a median of -1.4 (IQR: -2.1). Using established methods such as comparator ultrasound and last menstrual period (LMP), the medians were 0 (IQR: 4) and 0.01 (IQR: 4), respectively. For prematurity discrimination, the area under the receiver operating characteristic curve (AUROC) was 0.986 (95% CI: 0.977 to 0.994). In newborns with absent or unreliable LMP, the intent-to-discriminate analysis showed that the test generated correct classifications 95.8% of the time. The assessment of the newborn's skin maturity adjusted by learning models promises accurate pregnancy dating at birth without the use of antenatal ultrasound reference.

Evaluation of Epigenetic Age Based on DNA Methylation Analysis of Several CpG Sites in Ukrainian Population

Epigenetic clocks are the models, which use CpG methylation levels for the age prediction of an organism. Although there were several epigenetic clocks developed there is a demand for development and evaluation of the relatively accurate and sensitive epigenetic clocks that can be used for routine research purposes. In this study, we evaluated two epigenetic clock models based on the 4 CpG sites and 2 CpG sites in the human genome using the pyrosequencing method for their methylation level estimation. The study sample included 153 people from the Ukrainian population with the age from 0 to 101. Both models showed a high correlation with the chronological age in our study sample (R2 = 0.85 for the 2 CpG model and R2 = 0.92 for the 4 CpG model). We also estimated the accuracy metrics of the age prediction in our study sample. For the age group from 18 to 80 MAD was 5.1 years for the 2 CpG model and 4.1 years for the 4 CpG model. In this regard, we can conclude, that the models evaluated in the study have good age predictive accuracy, and can be used for the epigenetic age evaluation due to the relative simplicity and time-effectiveness.

Newborn skin maturity models for gestational age prediction

A multicenter clinical trial evaluated the accuracy of a novel device to detect preterm newborns. A portable multiband reflectance photometric device assessed 781 newborns’ skin maturity and used machine learning models to predict reference gestational age, adjusting it to birth weight and antenatal corticosteroid therapy exposition. The day difference between the reference and the test had a median of -1.4 (IQR: -2.1). Using established methods such as comparator ultrasound and last menstrual period (LMP), the medians were 0 (IQR: 4) and 0.01 (IQR: 4), respectively. For prematurity discrimination, the area under the receiver operating characteristic curve (AUROC) was 0.986 (95% CI: 0.977 to 0.994). In newborns with absent or unreliable LMP, the intent-to-discriminate analysis showed that the test generated correct classifications 95.8% of the time. The assessment of the newborn's skin maturity adjusted by learning models promises accurate pregnancy dating at birth without the use of antenatal ultrasound reference.

Age determination through DNA methylation patterns of fingernails and toenails

Over the past decade, age prediction based on DNA methylation has become a vastly investigated topic; many age prediction models have been developed based on different DNAm markers and using various tissues. However, the potential of using nails to this end has not yet been explored. Their inherent resistance to decay and ease of sampling would offer an advantage in cases where post-mortem degradation poses challenges concerning sample collection and DNA-extraction. In the current study, clippings from both fingernails and toenails were collected from 108 living test subjects (age range: 0 – 96 years). The methylation status of 15 CpGs located in 4 previously established age-related markers (ASPA, EDARADD, PDE4C, ELOVL2) was investigated through pyrosequencing of bisulphite converted DNA. Significant dissimilarities in methylation levels were observed between all four limbs, hence limb-specific age prediction models were developed using ordinary least squares, weighted least squares and quantile regression analysis. When applied to their respective test sets, these models yielded a mean absolute deviation between predicted and chronological age ranging from 6.71 to 8.48 years. In addition, the assay was tested on methylation data derived from 5 nail samples collected from deceased individuals, demonstrating its feasibility for application in post-mortem cases. In conclusion, this study provides the first proof that chronological age can be assessed through DNA methylation patterns in nails.

A Blood–Bone–Tooth Model for Age Prediction in Forensic Contexts

The development of age prediction models (APMs) focusing on DNA methylation (DNAm) levels has revolutionized the forensic age estimation field. Meanwhile, the predictive ability of multi-tissue models with similar high accuracy needs to be explored. This study aimed to build multi-tissue APMs combining blood, bones and tooth samples, herein named blood–bone–tooth-APM (BBT-APM), using two different methodologies. A total of 185 and 168 bisulfite-converted DNA samples previously addressed by Sanger sequencing and SNaPshot methodologies, respectively, were considered for this study. The relationship between DNAm and age was assessed using simple and multiple linear regression models. Through the Sanger sequencing methodology, we built a BBT-APM with seven CpGs in genes ELOVL2, EDARADD, PDE4C, FHL2 and C1orf132, allowing us to obtain a Mean Absolute Deviation (MAD) between chronological and predicted ages of 6.06 years, explaining 87.8% of the variation in age. Using the SNaPshot assay, we developed a BBT-APM with three CpGs at ELOVL2, KLF14 and C1orf132 genes with a MAD of 6.49 years, explaining 84.7% of the variation in age. Our results showed the usefulness of DNAm age in forensic contexts and brought new insights into the development of multi-tissue APMs applied to blood, bone and teeth.

Comparison of Biological Age Prediction Models Using Clinical Biomarkers Commonly Measured in Clinical Practice Settings: AI Techniques Vs. Traditional Statistical Methods

In this work, we used the health check-up data of more than 111,000 subjects for analysis, using only the data with all 35 variables entered. For the prediction of biological age, traditional statistical methods and four AI techniques (RF, XGB, SVR, and DNN), which are widely used recently, were simultaneously used to compare the predictive power. This study showed that AI models produced about 1.6 times stronger linear relationship on average than statistical models. In addition, the regression analysis on the predicted BA and CA revealed similar differences in terms of both the correlation coefficients (linear model: 0.831, polynomial model: 0.996, XGB model: 0.66, RF model: 0.927, SVR model: 0.787, DNN model: 0.998) and R2 values. Through this work, we confirmed that AI techniques such as the DNN model outperformed traditional statistical methods in predicting biological age.