Publications by authors named "S Khazaei"

285 Publications

A full pipeline of diagnosis and prognosis the risk of chronic diseases using deep learning and Shapley values: The Ravansar county anthropometric cohort study.

PLoS One 2022 20;17(1):e0262701. Epub 2022 Jan 20.

Cellular and Molecular Research Center, Gerash University of Medical Sciences, Gerash, Iran.

Anthropometry is a Greek word that consists of the two words "Anthropo" meaning human species and "metery" meaning measurement. It is a science that deals with the size of the body including the dimensions of different parts, the field of motion and the strength of the muscles of the body. Specific individual dimensions such as heights, widths, depths, distances, environments and curvatures are usually measured. In this article, we investigate the anthropometric characteristics of patients with chronic diseases (diabetes, hypertension, cardiovascular disease, heart attacks and strokes) and find the factors affecting these diseases and the extent of the impact of each to make the necessary planning. We have focused on cohort studies for 10047 qualified participants from Ravansar County. Machine learning provides opportunities to improve discrimination through the analysis of complex interactions between broad variables. Among the chronic diseases in this cohort study, we have used three deep neural network models for diagnosis and prognosis of the risk of type 2 diabetes mellitus (T2DM) as a case study. Usually in Artificial Intelligence for medicine tasks, Imbalanced data is an important issue in learning and ignoring that leads to false evaluation results. Also, the accuracy evaluation criterion was not appropriate for this task, because a simple model that is labeling all samples negatively has high accuracy. So, the evaluation criteria of precession, recall, AUC, and AUPRC were considered. Then, the importance of variables in general was examined to determine which features are more important in the risk of T2DM. Finally, personality feature was added, in which individual feature importance was examined. Performing by Shapley Values, the model is tuned for each patient so that it can be used for prognosis of T2DM risk for that patient. In this paper, we have focused and implemented a full pipeline of Data Creation, Data Preprocessing, Handling Imbalanced Data, Deep Learning model, true Evaluation method, Feature Importance and Individual Feature Importance. Through the results, the pipeline demonstrated competence in improving the Diagnosis and Prognosis the risk of T2DM with personalization capability.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0262701PLOS
January 2022

The applications of ultrasound, and ultrasonography in dentistry: a scoping review of the literature.

Clin Oral Investig 2022 Jan 14. Epub 2022 Jan 14.

Faculty of Dentistry, University of Toronto, 124 Edward Street, Toronto, ON, CA, M5G 1G6, USA.

Objectives: This scoping review aims to summarize the available literature on the clinical applications of ultrasonography and ultrasound in diagnostic, therapeutic, and interventional dental applications.

Materials And Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, Extension for Scoping Reviews checklist and conducted a protocol-driven scoping review of randomized controlled trials, cohort studies, cross-sectional studies, case-control studies, and case series that assessed ultrasonography or ultrasound use as a stand-alone diagnostic, therapeutic, and interventional tool in dentistry. We included studies published after 1980, study samples ≥ 10, with diagnostic, concordance, or therapeutic outcomes. We searched Ovid MEDLINE, Embase, and others (up to April 2021) and extracted information regarding study level, patient level, test or treatment level, and outcome level data.

Results: Five interventional studies (related to oral medicine, temporomandibular disorders, and dental anesthesia), eight therapeutic studies (related to surgery and orthodontics), and seventy-five diagnostic studies (related to orthodontics, surgery, endodontics, oral medicine, temporomandibular disorders, restorative dentistry, and periodontology) were identified and presented in this review.

Conclusion: Ultrasonography has a well-established niche in diagnostic dentistry, while therapeutic and interventional ultrasounds have a smaller, yet present, niche in dentistry. However, further research is needed to report the precise estimates of the diagnostic, therapeutic, and interventional effects.

Clinical Significance: Dentists are mostly unfamiliar with ultrasonography and ultrasound and their potential uses. This review maps the diagnostic and therapeutic applications of ultrasonography and ultrasound technology in dentistry and highlights the current challenges, gaps of knowledge, and research status of ultrasound technology in this regard.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00784-021-04340-6DOI Listing
January 2022

Monitoring heavy metal contamination on the Iranian coasts of the Persian Gulf using biological indicators: risk assessment for the consumers.

Environ Monit Assess 2022 Jan 11;194(2):83. Epub 2022 Jan 11.

Department of Natural Resources, Bushehr University of Persian Gulf, Bushehr, Iran.

This research was conducted to determine the concentration of heavy metals (Cu, Pb, and Ni) in the sediments as well as the gill and muscle tissue of Siganus javus and two species of algae (Padina australis and Sargassum vulgare) collected from the Persian Gulf coasts of Bushehr province, which were studied using standard laboratory methods. The general form and trend of metal uptake at different stations in the gill and muscle tissue was Cu > Ni > Pb. The results of the study of metal uptake in both algae showed that the uptake of all three metals was higher in Padina species (Pb ˂ Cu ˂ Ni). The estimated daily intake (EDI), estimated weekly intake (EWI), allowable fish consumption rate limit (CR), and the target hazard quotients (THQ) for the consumption of this fish were also calculated. It was found that the concentration of heavy metals in the edible parts of the fish did not exceed the permissible limits proposed by the WHO, MAFF, JECFA, and NHMRC for human consumption, but the Ni concentration was higher than standard. The consumer risk indexes for non-cancerous diseases due to all metals were lower than standard. Also, the total risk index (HI) in this study was 0.065.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10661-022-09755-6DOI Listing
January 2022

Predictors of death in patients with COVID-19: A cross-sectional study in West of Iran.

Med J Islam Repub Iran 2021 11;35:103. Epub 2021 Aug 11.

Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran.

Coronavirus disease 2019 (COVID-19) is a contagious disease caused by a newly identified coronavirus. Our knowledge about the survival rate and prognostic factors of the disease is not established well. The purpose of this study was to evaluate the predictors of COVID-19 mortality in Hamadan province in western Iran. In this study, we included all laboratory-confirmed COVID-19 cases with known treatment outcomes in Hamadan province, Iran, between 20, 2020, to May 10, 2020. Demographic, clinical, laboratory data, and treatment outcomes were obtained from computerized medical records and compared between survived cases and patients with death outcomes. Univariable and multivariable logistic regression models were used to determine the predictors of death. From 749 investigated patients, 77 patients (10.28%) died during the treatment. The Mean age of patients was 53.97±19.04 years. Multivariable logistic regression showed that males had 2.07 (95% CI: 1.73, 2.54) fold higher odds of death. Those with 60 years old and more had 6.49 (95% CI: 4.53, 7.93) fold higher odds of death. Patients with an underlying disease had 7.14 (95% CI: 6.94, 7.38) fold higher odds of death, and patients who were hospitalized in the ICU ward had 2.24 (95% CI: 1.75, 2.90) times higher odds of COVID-19 related mortality. The potential predictors of death in COVID-19 cases, including the male gender, older age, and having an underlying disease could help physicians to identify patients with poor prognoses at an early stage and better management of them.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.47176/mjiri.35.103DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8683832PMC
August 2021

Evaluation of maternal risk factors for preterm delivery in Fatemieh Hospital of Hamadan, Iran, 2019: A case-control study.

J Family Med Prim Care 2021 Oct 5;10(10):3832-3837. Epub 2021 Nov 5.

Department of Epidemiology and Biostatistics, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran.

Background: The present study aimed to evaluate maternal risk factors of preterm delivery in Fatemieh Hospital in Hamadan, Iran, 2019.

Methods: In this case-control study, 7,478 hospital files of live-born neonates and their mothers in Hamadan Fatemieh Hospital in 2019 were examined. According to statistical estimates, 261 preterm deliveries and 736 term deliveries were studied. Information files of neonates and mothers were used to complete the study questionnaire. The data were compared in two separate groups and logistic regression was performed to estimate the crude relationship between demographic and clinical characteristics of term and preterm delivery.

Results: The mean age of women was 27.89 ± 6.48 years. Analysis of data revealed that academic education (OR: 2.02, = 0.014), age group 25-34 years (OR: 1.5, = 0.016), age of 35 years and above (OR: 1.66, = 0.018), previous history of preterm delivery (OR: 5.3, < 0.001), history of abortion (OR: 1.67, = 0.004), history of surgery (OR: 1.54, = 0.007), history of infertility ( = 0.016), and a history of cesarean (OR: 2.11, < 0.001) were potentially associated with a higher odds of preterm delivery ( < 0.2).

Conclusion: Based on the results, it is important to identify potential risk factors of preterm delivery in mothers and corrective interventions in strengthening consultation and education of pregnant women during pregnancy. Such a measure helps select the type of delivery and strengthen prenatal care in identifying mothers in high-risk groups and performing timely interventions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.4103/jfmpc.jfmpc_1032_21DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8653452PMC
October 2021
-->