Employing feature engineering strategies to improve the performance of machine learning algorithms on echocardiogram dataset.

Objectives: This study mainly uses machine learning (ML) to make predictions by inputting features during training and inference. The method of feature selection is an important factor affecting the accuracy of ML models, and the process includes data extraction, which is the collection of all data required for ML. It also needs to import the concept of feature engineering, namely, this study needs to label the raw data of the cardiac ultrasound dataset with one or more meaningful and informative labels so that the ML model can learn from it and predict more accurate target values. Therefore, this study will enhance the strategies of feature selection methods from the raw dataset, as well as the issue of data scrubbing. Methods: In this study, the ultrasound dataset was cleaned and critical features were selected through data standardization, normalization, and missing features imputation in the field of feature engineering. The aim of data scrubbing was to retain and select critical features of the echocardiogram dataset while making the prediction of the ML algorithm more accurate. Results: This paper mainly utilizes commonly used methods in feature engineering and finally selects four important feature values. With the ML algorithms available on the Azure platform, namely, Random Forest and CatBoost, a Voting Ensemble method is used as the training algorithm, and this study also uses visual tools to gain a clearer understanding of the raw data and to improve the accuracy of the predictive model. Conclusion: This paper emphasizes feature engineering, specifically on the cleaning and analysis of missing values in the raw dataset of echocardiography and the identification of important critical features in the raw dataset. The Azure platform is used to predict patients with a history of heart disease (individuals who have been under surveillance in the past three years and those who haven't). Through data scrubbing and preprocessing methods in feature engineering, the model can more accurately predict the future occurrence of heart disease in patients.

Folate deficiency triggers an oxidative-nitrosative stress-mediated apoptotic cell death and impedes insulin biosynthesis in RINm5F pancreatic islet ß-cells: relevant to the pathogenesis of diabetes.

It has been postulated that folic acid (folate) deficiency (FD) may be a risk factor for the pathogenesis of a variety of oxidative stress-triggered chronic degenerative diseases including diabetes, however, the direct evidence to lend support to this hypothesis is scanty. For this reason, we set out to study if FD can trigger the apoptotic events in an insulin-producing pancreatic RINm5F islet ß cells. When these cells were cultivated under FD condition, a time-dependent growth impediment was observed and the demise of these cells was demonstrated to be apoptotic in nature proceeding through a mitochondria-dependent pathway. In addition to evoke oxidative stress, FD condition could also trigger nitrosative stress through a NF-κB-dependent iNOS-mediated overproduction of nitric oxide (NO). The latter compound could then trigger depletion of endoplasmic reticulum (ER) calcium (Ca(2+)) store leading to cytosolic Ca(2+) overload and caused ER stress as evidence by the activation of CHOP expression. Furthermore, FD-induced apoptosis of RINm5F cells was found to be correlated with a time-dependent depletion of intracellular glutathione (GSH) and a severe down-regulation of Bcl-2 expression. Along the same vein, we also demonstrated that FD could severely impede RINm5F cells to synthesize insulin and their abilities to secret insulin in response to glucose stimulation were appreciably hampered. Even more importantly, we found that folate replenishment could not restore the ability of RINm5F cells to resynthesize insulin. Taken together, our data provide strong evidence to support the hypothesis that FD is a legitimate risk factor for the pathogenesis of diabetes.

Glucose-regulated protein 78 is a novel contributor to acquisition of resistance to sorafenib in hepatocellular carcinoma.

BACKGROUND: Sorafenib is a newly established cancer drug found to be an effective systemic treatment for advanced hepatocellular carcinoma (HCC). However, little is known about any potential effectors that modify tumor cell sensitivity towards sorafenib. Here, we present the first evidence that glucose-regulated protein 78 (GRP78) is intimately associated with acquisition of resistance towards sorafenib. METHODS: The role of GRP78 in acquisition of resistance towards sorafenib was determined using HepJ5 (a GRP78-overexpressing subline) and HepG2 as its pair-matched control. RNA interference in cancer cells was applied to determine the influence of GRP78 expression on sensitivity to sorafenib treatment. RESULTS: We found that HepG2 cells exhibited higher sensitivity toward sorafenib, with 50% inhibition concentration (IC(50)) >20 microMu for HepJ5 and 4.8 microM for HepG2. Specifically, when HepG2 cells received 20 microM sorafenib treatment for 24 h, over 80% of cells underwent apoptosis compared with only 32% of HepJ5 cells under similar experimental conditions. Similarly, GRP78 knockdown in HepJ5 cells by small interfering RNA (siRNA) technique enhanced the efficacy of sorafenib-mediated cell death. This was reflected by a shift of IC(50) values from >20 microM to 4.8 microM. CONCLUSIONS: GRP78 is a positive modifier for sorafenib resistance acquisition in HCC and represents a prime target for overcoming sorafenib resistance.

Verteporfin-photoinduced apoptosis in HepG2 cells mediated by reactive oxygen and nitrogen species intermediates.

Photodynamic therapy (PDT) is a rapidly evolving treatment modality with diverse usages in the field of cancer therapy. Most of PDT is based on free radical-mediated photo-killing of cancer cells. This study aimed to elucidate the detailed cascade of events that lead to apoptotic cell death of HepG2 cells resulting from the photodynamic effect (PDE) of verteporfin. PDE of verteporfin could rapidly provoke hyper-oxidative stress and caspase activity. Glutathione (GSH) depletion and lipid peroxidation phenomena could simultaneously be evoked. The membrane integrity was decreased and permeability as reflected by the depolarization of the mitochondrial membrane potential (Deltapsi(m)) increased, resulting in a sudden influx of cytosolic calcium into the mitochondria. Altogether, it is suggested that these events serve as the final arbitrator to initiate the lethal apoptotic process of HepG2 cells under PDE. In addition, the data are consistent with the notion that GSH depletion is an effective strategy to sensitize cancer cells to undergo apoptosis.

Sorafenib induces preferential apoptotic killing of a drug- and radio-resistant Hep G2 cells through a mitochondria-dependent oxidative stress mechanism.

Sorafenib (Nexavar, BAY43-9006), a bi-arylurea, is a newly established anti-cancer drug and its functional attribute of cytotoxicity is based on the multi-kinase inhibitory action. Here, we report yet another novel pathway in which sorafenib can induce apoptotic cell death preferentially and efficaciously on an experimentally proven drug- and radio-resistant human Hep G2 cells via a mitochondria-dependent oxidative stress mechanism. A real time confocal imaging assay revealed that sorafenib could rapidly provoke the production of ROS plethorically, mainly concentrating in the mitochondria, albeit substantial amounts of ROS could also be detected in cytosol and nucleus. The rapid production of ROS could simultaneously induce intracellular glutathione (iGSH) depletion. A nearly 90% of iGSH was found to be depleted in 1h period after the cells received the drug treatment. Besides mitochondria, iGSH depletion could also be detected in other cellular compartment including cytoplasm and nucleus. Interestingly, we also demonstrated that sorafenib could trigger mitochondrial Ca(2+) overload. All these events compoundedly serve as the final arbitrator to initiate lethal apoptotic process through the release of cytochrome c and caspase 3/7 activation. Collectively, we provide first evidence here that sorafenib can provoke an alternative pathway for apoptosis induction of Hep G2 cells through a mitochondria-dependent oxidative stress mechanism which is independent of original kinase inhibitory attribute of the drug action. Most importantly, we also demonstrate that sorafenib can effectively eradicate a highly drug- and radio-resistant HCC cells. Thus, our data can provide the basis for a potential applicability of sorafenib in a combined treatment modality.