Application of logistic regression, support vector machine and random forest on the effects of titanium dioxide nanoparticles using macroalgae in treatment of certain risk factors associated with kidney injuries

• Published in: Environmental research Vol. 220; p. 115167
• Main Authors: Tu, Jianxin, Hu, Lingzhen, Mohammed, Khidhair Jasim, Le, Binh Nguyen, Chen, Peirong, Ali, Elimam, Ali, H. Elhosiny, Sun, Li
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.03.2023
• Subjects: Acute kidney injury (AKI); Acute Kidney Injury - chemically induced; Body Weight; Humans; Kidney; Kidney disease (KD); Logistic Models; Machine learning; Macroalgae; MLR; Patients; Random Forest; Risk Factors; Seaweed; Support Vector Machine; SVM; MLR; RF; Macroalgae; Machine learning; Acute kidney injury (AKI); SVM; Kidney disease (KD); Patients; Kidney
• ISSN: 0013-9351; 1096-0953
• DOI: 10.1016/j.envres.2022.115167

The use of titanium dioxide (TiO2) nanoparticles in many biological and technical domains is on the rise. There hasn't been much research on the toxicity of titanium dioxide nanoparticles in biological systems, despite their ubiquitous usage. In the current investigation, samples were exposed to various dosages of TiO2 nanoparticles for 4 days, 1 month, and 2 months following treatment. ICP-AES was used to dose TiO2 into the tissues, and the results showed that the kidney had a significant TiO2 buildup. On the other hand, apoptosis of renal tubular cells is one of the most frequent cellular processes contributing to kidney disease (KD). Nevertheless, the impact of macroalgal seaweed extract on KD remains undetermined. In this work, machine learning (ML) approaches have been applied to develop prediction algorithms for acute kidney injury (AKI) by use of titanium dioxide and macroalgae in hospitalized patients. Fifty patients with (AKI) and 50 patients (non-AKI group) have been admitted and considered. Regarding demographic data, and laboratory test data as input parameters, support vector machine (SVM), and random forest (RF) are utilized to build models of AKI prediction and compared to the predictive performance of logistic regression (LR). Due to its strong antioxidant and anti-inflammatory powers, the current research ruled out the potential of using G. oblongata red macro algae as a source for a variety of products for medicinal uses. Despite a high and fast processing of algorithms, logistic regression showed lower overfitting in comparison to SVM, and Random Forest. The dataset is subjected to algorithms, and the categorization of potential risk variables yields the best results. AKI samples showed significant organ defects than non-AKI ones. Multivariate LR indicated that lymphocyte, and myoglobin (MB) ≥ 1000 ng/ml were independent risk parameters for AKI samples. Also, GCS score (95% CI 1.4–8.3 P = 0.014) were the risk parameters for 60-day mortality in samples with AKI. Also, 90-day mortality in AKI patients was significantly high (P < 0.0001). In compared to the control group, there were no appreciable changes in the kidney/body weight ratio or body weight increases. Total thiol levels in kidney homogenate significantly decreased, and histopathological analysis confirmed these biochemical alterations. According to the results, oral TiO2 NP treatment may cause kidney damage in experimental samples. •Toxicity of titanium dioxide nanoparticles in biological systems assessed.•ICP-AES was used to dose TiO2 into the tissues.•Kidney had a significant TiO2 buildup.•Apoptosis of renal tubular cells is one of the most frequent cellular processes contributing to kidney disease (KD).•Impact of macroalgal seaweed extract on KD remains undetermined.