Search

Background: Intensive Care Unit (ICU) has the highest mortality rate in the world. ICU has special equipment that leads to the hospital's most costly parts. The length of stay in the ICU is a special issue, and reducing this time is a practical approach. We aimed to use artificial intelligence to help early and timely diagnosis of the disease to help with health. Methods: We designed a rule-based intelligent system to predict the length of stay and the mortality rate of trauma patients in ICU. A neuro-Fuzzy and eight machine learning models were used to predict the mortality rate in trauma patients in ICU. The performances of these techniques were evaluated with accuracy, sensitivity, specificity, and area under the ROC curve. Decision-Table was used to predict the length of stay in trauma patients in ICU. For comparison, eight machine learning models were used. The method is compared based on Mean absolute error and relative absolute error (%). Results: Neuro-Fuzzy expert system and Decision-Table showed better results than other techniques. Accuracy, sensitivity, specificity, and ROC Area of Nero-Fuzzy are 83.6735, 0.9744, 0.3000, 0.8379, and 1, respectively. The mean absolute error and Relative absolute error (%) of the Decision-Table model are 4.5426 and 65.4391, respectively. Conclusion: Neuro-Fuzzy expert system with the highest level of accuracy and a Decision-Table with the lowest Mean absolute error, which are rule-based models, are the best models. Therefore, these models are recommended as a valuable tool for prediction parameters of ICU as well as medical decision-making.

The study was conducted to investigate the correlation between vase life and biochemical parameters in sunflower. The experiment was arranged in a randomized complete block design with five replications. Plants were sprayed by 50/100 mg L−1 salicylic acid, 50/100 mg L−1 thiamine, 100/200 mg L−1 ascorbic acid, and distilled water as control group at the eight-leaf stage. After one month, the spray treatments were repeated. The effects of preharvest spray treatment on vase life, protein, lipid peroxidation, peroxidase, polyphenol oxidase, and catalase were investigated. The result showed that thiamine by the most prolonged vase life was the most effective treatment at 50 mg L−1 with 25 days. Its vase life was more than twice the vase life of the control treatment. Also, the application of both concentrations of salicylic acid, ascorbic acid, and thiamine increased the amount of protein content, catalase, and peroxidase activity, and decreased polyphenol oxidase activity and lipid peroxidation among petals and leaves. Besides, while the vase life exhibited a positive correlation with peroxidase, catalase, and protein activity, it showed a negative correlation with polyphenol oxidase and lipid peroxidation.

Background The tripartite motif containing (TRIM)-22 participates in innate immune responses and exhibits antiviral activities. The present study aimed to assess of the relationship between TRIM22 single-nucleotide polymorphisms and clinical parameters with the coronavirus disease 2019 (COVID-19) infection severity. Methods TRIM22 polymorphisms (rs7113258, rs7935564, and rs1063303) were genotyped using TaqMan polymerase chain reaction (PCR) assay in 495 dead and 497 improved severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-positive patients. Results In this study, the frequencies of TRIM22 rs1063303 GG, rs7935564 GG, and rs7113258 TT were significantly higher in dead patients than in improved patients, and higher viral load with low PCR Ct value was noticed in dead patients. The multivariate logistic regression analysis revealed that the lower levels of low-density lipoprotein (LDL), cholesterol, PCR Ct value, and lower 25-hydroxyvitamin D, and also higher levels of erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), and TRIM22 rs1063303 GG, rs7113258 TT, and rs3824949 GG genotypes were related to the COVID-19 infection severity. Conclusion Our finding proved the probable relationship between the COVID-19 infection severity with the genotypes of TRIM22 SNPs and clinical parameters. More research is required worldwide to show the association between the COVID-19 infection severity and host genetic factors.

Introduction: Our aim in this study was to summarize information on the use of intelligent models for predicting and diagnosing the Coronavirus disease 2019 (COVID-19) to help early and timely diagnosis of the disease.Material and Methods: A systematic literature search included articles published until 20 April 2020 in PubMed, Web of Science, IEEE, ProQuest, Scopus, bioRxiv, and medRxiv databases. The search strategy consisted of two groups of keywords: A) Novel coronavirus, B) Machine learning. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. Studies were critically reviewed for risk of bias using prediction model risk of bias assessment tool.Results: We gathered 1650 articles through database searches. After the full-text assessment 31 articles were included. Neural networks and deep neural network variants were the most popular machine learning type. Of the five models that authors claimed were externally validated, we considered external validation only for four of them. Area under the curve (AUC) in internal validation of prognostic models varied from .94 to .97. AUC in diagnostic models varied from 0.84 to 0.99, and AUC in external validation of diagnostic models varied from 0.73 to 0.94. Our analysis finds all but two studies have a high risk of bias due to various reasons like a low number of participants and lack of external validation.Conclusion: Diagnostic and prognostic models for COVID-19 show good to excellent discriminative performance. However, these models are at high risk of bias because of various reasons like a low number of participants and lack of external validation. Future studies should address these concerns. Sharing data and experiences for the development, validation, and updating of COVID-19 related prediction models is needed.

Schizophrenia and bipolar disorder (BD) are critical and high-risk inherited mental disorders with debilitating symptoms. Worldwide, 3% of the population suffers from these disorders. The mortality rate of these patients is higher compared to other people. Current procedures cannot effectively diagnose these disorders because it takes an average of 10 years from the onset of the first symptoms to the definitive diagnosis of the disease. Machine learning (ML) techniques are used to meet this need. This study aimed to summarize information on the use of ML techniques for predicting schizophrenia and BD to help early and timely diagnosis of the disease.A systematic literature search included articles published until January 19, 2020 in 3 databases. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. PRISMA guidelines were followed to conduct the study, and the Prediction Model Risk of Bias Assessment Tool (PROBAST) to assess included papers.In this review, 1243 papers were retrieved through database searches, of which 15 papers were included based on full-text assessment. ML techniques were used to predict schizophrenia and BDs. The main algorithms applied were support vector machine (SVM) (10 studies), random forests (RF) (5 studies), and gradient boosting (GB) (3 studies). Input and output characteristics were very diverse and have been kept to enable future research. RFs algorithms demonstrated significantly higher accuracy and sensitivity than SVM and GB. GB demonstrated significantly higher specificity than SVM and RF. We found no significant difference between RF and SVM in terms of specificity.ML can precisely predict results and assist in making clinical decisions-concerning schizophrenia and BD. RF often performed better than other algorithms in supervised learning tasks. This study identified gaps in the literature and opportunities for future psychological ML research.

Early and effective integration of titanium-based materials into bone tissue is of vital importance for long-term stability of implants. Surface modification is commonly used to enhance cell-substrate interactions for improving cell adhesion, proliferation, and activity. Here, the surface of titanium substrates and commercial implants were coated with blood (TiB), fetal bovine serum (TiF), and phosphate-buffered saline (TiP) solution using a spin coating process. Surface roughness and wettability of samples were measured using contact angle measurements and atomic force microscopy. The samples were then exposed to human osteoblast-like MG63 cells in order to evaluate adhesion, growth, differentiation, and morphology on the surface of modified samples. Untreated titanium disks were used as controls. The lowest roughness and wettability values were found in unmodified titanium samples followed by TiP, TiF, and TiB. The percentage of cellular attachment and proliferation for each sample was measured using an MTT (3-[4,5-dimethylthiazol-2yl] 2,5diphenyl-2H-tetrazoliumbromide) assay. Cell adhesion and proliferation were most improved on TiB followed closely by TiF. The results of this study revealed an increased expression of the osteogenic marker protein alkaline phosphatase on TiB and the coated commercial titanium implants. These results suggested that precoating titanium samples with blood may improve cellular response by successfully mimicking a physiological environment that could be beneficial for clinical implant procedures.

BACKGROUND: Breast cancer is one of the most common cancers with a high mortality rate among women. With the early diagnosis of breast cancer survival will increase from 56% to more than 86%. Therefore, an accurate and reliable system is necessary for the early diagnosis of this cancer. The proposed model is the combination of rules and different machine learning techniques. Machine learning models can help physicians to reduce the number of false decisions. They try to exploit patterns and relationships among a large number of cases and predict the outcome of a disease using historical cases stored in datasets. OBJECTIVE: The objective of this study is to propose a rule-based classification method with machine learning techniques for the prediction of different types of Breast cancer survival. METHODS: We use a dataset with eight attributes that include the records of 900 patients in which 876 patients (97.3%) and 24 (2.7%) patients were females and males respectively. Naive Bayes (NB), Trees Random Forest (TRF), 1-Nearest Neighbor (1NN), AdaBoost (AD), Support Vector Machine (SVM), RBF Network (RBFN), and Multilayer Perceptron (MLP) machine learning techniques with 10-cross fold technique were used with the proposed model for the prediction of breast cancer survival. The performance of machine learning techniques were evaluated with accuracy, precision, sensitivity, specificity, and area under ROC curve. RESULTS: Out of 900 patients, 803 patients and 97 patients were alive and dead, respectively. In this study, Trees Random Forest (TRF) technique showed better results in comparison to other techniques (NB, 1NN, AD, SVM and RBFN, MLP). The accuracy, sensitivity and the area under ROC curve of TRF are 96%, 96%, 93%, respectively. However, 1NN machine learning technique provided poor performance (accuracy 91%, sensitivity 91% and area under ROC curve 78%). CONCLUSIONS: This study demonstrates that Trees Random Forest model (TRF) which is a rule-based classification model was the best model with the highest level of accuracy. Therefore, this model is recommended as a useful tool for breast cancer survival prediction as well as medical decision making.

Feature selection is a problem of finding efficient features among all features in which the final feature set can improve accuracy and reduce complexity. In feature selection algorithms search strategies are key aspects. Since feature selection is an NP-Hard problem; therefore heuristic algorithms have been studied to solve this problem. In this paper, we have proposed a method based on memetic algorithm to find an efficient feature subset for a classification problem. It incorporates a filter method in the genetic algorithm to improve classification performance and accelerates the search in identifying core feature subsets. Particularly, the method adds or deletes a feature from a candidate feature subset based on the multivariate feature information. Empirical study on commonly data sets of the university of California, Irvine shows that the proposed method outperforms existing methods., Comment: M., Montazeri, H. R. Naji, M. Montazeri, A. Faraahi. A novel memetic feature selection algorithm. In Information and Knowledge Technology (IKT), 2013 5th Conference on. 2013