Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study

An artificial intelligence approach to predict infants' health status at birth

BACKGROUND

Machine learning could be used for prognosis/diagnosis of maternal and neonates' diseases by analyzing the data sets and profiles obtained from a pregnant mother.

PURPOSE

We aimed to develop a prediction model based on machine learning algorithms to determine important maternal characteristics and neonates' anthropometric profiles as the predictors of neonates' health status.

METHODS

This study was conducted among 1280 pregnant women referred to healthcare centers to receive antenatal care. We evaluated several machine learning methods, including support vector machine (SVM), Ensemble, K-Nearest Neighbor (KNN), Naïve Bayes (NB), and Decision tree classifiers, to predict newborn health state.

RESULTS

The minimum redundancy-maximum relevance (MRMR) algorithm revealed that variables, including head circumference of neonates, pregnancy intention, and drug consumption history during pregnancy, were top-scored features for classifying normal and unhealthy infants. Among the different classification methods, the SVM classifier had the best performance. The average values of accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC) in the test group were 75%, 75%, 76%, 76%, and 65%, respectively, for SVM model.

CONCLUSION

Machine learning methods can efficiently forecast the neonate's health status among pregnant women. This study proposed a new approach toward the integration of maternal data and neonate profiles to facilitate the prediction of neonates' health status.

Identification of Molecular Mechanisms in Radiation Cystitis: Insights from RNA Sequencing

Pelvic cancer survivors who were treated with radiation therapy are at risk for developing (hemorrhagic) radiation cystitis (RC) many years after completion of radiation therapy. Patients with RC suffer from lower urinary tract symptoms, including frequency, nocturia, pelvic pain, and incontinence. In advanced stages, hematuria can occur, potentially escalating to life-threatening levels. Current therapeutic options for RC are limited, partly due to ethical concerns regarding bladder biopsy in patients with fragile bladder tissue. This study aimed to leverage our established preclinical model to elucidate the molecular pathways implicated in radiation-induced tissue changes in the bladder. Female C57Bl/6 mice received a single dose of 40 Gy using CT-guided imaging and a two-beam irradiation approach using the SARRP irradiator. Bladders from irradiated and age-matched littermate controls were harvested at 1 week [n = 5/group] or 6 months [n = 5/group] after irradiation, RNA was harvested, and mRNA sequencing was performed at paired-end 150bp on the Illumina NovaSeq6000 with a target of 30 million reads per sample. Following RNA sequencing, thorough bioinformatics analysis was performed using iPathwayGuide v2012 (ADVAITA Bioinformatics). Findings of the RNA sequencing were validated using qPCR analysis. At 1 week post-irradiation, altered gene expression was detected in genes involved in DNA damage response, apoptosis, and transcriptional regulation. By 6 months post-irradiation, significant changes in gene expression were observed in inflammation, collagen catabolism, and vascular health. Affected pathways included the p53, JAK-STAT, and PI3K-Akt pathways. These findings were validated in vivo in bladder tissues from our preclinical model. This is the first study to determine the molecular changes in the bladder in response to radiation treatment. We have successfully pinpointed several pathways and specific genes that undergo modification, thereby contributing to the progression of radiation cystitis. These insights enhance our understanding of the pathophysiology of radiation cystitis and may ultimately pave the way to the identification of potential new therapeutic targets.