Prediction of impacts on liver enzymes from the exposure of low-dose medical radiations through artificial intelligence algorithms

Abstract

OBJECTIVES: This study aimed to develop artificial intelligence and machine learning-based models to predict alterations in liver enzymes from the exposure of low annual average effective doses in radiology and nuclear medicine personnel of Institute of Nuclear Medicine and Oncology Hospital. METHODS:Ninety workers from the Radiology and Nuclear Medicine departments were included. A high-capacity thermoluminescent was used for annual average effective radiation dose measurements. The liver function tests were conducted for all subjects and controls. Three supervised learning models (multilayer precentron; logistic regression; and random forest) were applied and crossvalidated to predict any alteration in liver enzymes. The t-test was applied to see if subjects and controls were significantly different in liver function tests. RESULTS:The annual average effective doses were in the range of 0.07-1.15 mSv. Alanine transaminase was 50% high and aspartate transaminase was 20% high in radiation workers. There existed a significant difference (p=0.0008) in Alanine-aminotransferase between radiation-exposed and radiation-unexposed workers. Random forest model achieved 90-96.6% accuracies in Alanineaminotransferase and Aspartate-aminotransferase predictions. The second best classifier model was the Multilayer perceptron (65.5-80% accuracies). CONCLUSION:As there is a need of regular monitoring of hepatic function in radiation-exposed people, our artificial intelligence-based predicting model random forest is proved accurate in prediagnosing alterations in liver enzymes.

Potential activity of silver/hydroxyapatite nano composite against damaged liver consequence to irradiation

“…This interaction leads to the damage of different components in the cell resulting in biochemical and histological changes [20]. The liver is a radiosensitive organ and exposure to irradiation can induce liver damage and can increase the risk of hepatic cancers [21].…”

Prediction of Radiation-Induced Abnormality in Liver Enzymes from Machine Learning (ML) Algorithms

“…Although the exposed radiation dose was less than the limit, still chronic or long-term exposure can pose serious late health effects. Therefore, a caution of protection from radiation exposure should be taken 17 . Shahid et al also applied three supervised learning machine learning models such as multilayer perceptron, logistic regression, and random forest to check if the radiation-exposed subjects were having altered liver functions from their radiation works.…”

Artificial Intelligence Aided Lipase Production and Engineering for Enzymatic Performance Improvement

“…34 The AI algorithms were applied to predict changes in liver enzymes in radiologists and nuclear medicine staff at the Institute of Nuclear Medicine and Oncology Hospital (Pakistan) after exposure to low annual mean effective doses. 35 As biocatalysts with industrial value, lipases (EC 3.1.1.3) are versatile enzymes commonly found in living organisms and have attracted much attention as the third most important enzymes in the market for the hydrolysis of triglycerides in different media. 36−38 Following hydrolysis, acylglycerols and associated substances such as alcohols (e.g., glycerol) and acids (e.g., fatty acids) are converted to a variety of hydrolysates and esters.…”

“…The great popularity of AI has led to it being extremely active in various fields as well, and like enzymes, it has a place of its own in other areas, e.g., healthcare, logistics, and education . The AI algorithms were applied to predict changes in liver enzymes in radiologists and nuclear medicine staff at the Institute of Nuclear Medicine and Oncology Hospital (Pakistan) after exposure to low annual mean effective doses …”