Isfahan University of Medical SciencesJournal of Isfahan Medical School1027-75954279620250120Application of Deep Learning Models in the Detection Depression Using Time-Frequency Transformation of Electroencephalogram SignalsApplication of Deep Learning Models in the Detection Depression Using Time-Frequency Transformation of Electroencephalogram Signals112311283136310.48305/jims.v42.i796.1123FAMohsen SadatShahabiPhD, Department of Physics and Biomedical Engineering, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran0000-0002-0734-1188AhmadShalbafAssociate Professor, Department of Physics and Biomedical Engineering, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran0000-0002-1595-7281Journal Article20240707<strong>Background:</strong><em> </em>Major Depressive Disorder (MDD) is a prevalent mental disorder worldwide, and timely diagnosis is necessary for efficient treatment. In the present study, an electroencephalogram (EEG) signal was utilized to automatically and precisely detect MDD using deep learning models.
<strong>Methods:</strong><strong> </strong>Thirty MDD and twenty-eight healthy subjects participated, and their psychological evaluation was conducted by a specialist psychiatrist using the standard Beck questionnaire. 19-channel EEG signals were acquired from all participants in a resting state with eyes closed. Short-Time Fourier Transform (STFT) was applied to the sequential segments of the EEG signals and resulted two-dimensional matrix fed to the deep learning models. DeepEEGNet model was developed based on the EEGNet model utilized for the MDD classification and Healthy subjects. A holdout data was used to test the final model.
<strong>Findings:</strong><strong> </strong>The DeepEEGNet model proposed in this study classified MDD and healthy participants with 84.1% accuracy, 86% sensitivity, and 82.7% specificity.
<strong>Conclusion:</strong> The deep learning model proposed in this study could accurately classify Healthy subjects and MDD patients using EEG signals and can be utilized as a helpful tool by psychiatrists.<strong>Background:</strong><em> </em>Major Depressive Disorder (MDD) is a prevalent mental disorder worldwide, and timely diagnosis is necessary for efficient treatment. In the present study, an electroencephalogram (EEG) signal was utilized to automatically and precisely detect MDD using deep learning models.
<strong>Methods:</strong><strong> </strong>Thirty MDD and twenty-eight healthy subjects participated, and their psychological evaluation was conducted by a specialist psychiatrist using the standard Beck questionnaire. 19-channel EEG signals were acquired from all participants in a resting state with eyes closed. Short-Time Fourier Transform (STFT) was applied to the sequential segments of the EEG signals and resulted two-dimensional matrix fed to the deep learning models. DeepEEGNet model was developed based on the EEGNet model utilized for the MDD classification and Healthy subjects. A holdout data was used to test the final model.
<strong>Findings:</strong><strong> </strong>The DeepEEGNet model proposed in this study classified MDD and healthy participants with 84.1% accuracy, 86% sensitivity, and 82.7% specificity.
<strong>Conclusion:</strong> The deep learning model proposed in this study could accurately classify Healthy subjects and MDD patients using EEG signals and can be utilized as a helpful tool by psychiatrists.https://jims.mui.ac.ir/article_31363_d6367279eb84bf8e1e10b10a04bd4292.pdfIsfahan University of Medical SciencesJournal of Isfahan Medical School1027-75954279620250120The Impact of Improving the Clinical Ethics of Delivery Agents on Childbirth Experiences of Primiparous Mothers in Ardabil CityThe Impact of Improving the Clinical Ethics of Delivery Agents on Childbirth Experiences of Primiparous Mothers in Ardabil City112811363136810.48305/jims.v42.i796.1129FASaeedehRahmatiStudents Research Committee, School of Nursing and Midwifery, Ardabil University of Medical Sciences, Ardabil, Iran0000-0003-1438-4781RafatKazemzadehDepartment of Midwifery, School of Nursing and Midwifery, Ardabil University of Medical Sciences, Ardabil, Iran0000-0003-1007-5236SohrabIranpourDepartment of Community Medicine, School of Medicine, Ardabil University of Medical Sciences, Ardabil, Iran0000-0002-0802-087XPouranAkhavanakbariDepartment of Midwifery, School of Nursing and Midwifery, Ardabil University of Medical Sciences, Ardabil, Iran0000-0002-5579-7438Journal Article20240907<strong>Background:</strong> Clinical ethics of health care providers play an important role in shaping women’s childbirth experiences. This study aimed to examine the impact of improving delivery agents' clinical ethics on primiparous mothers' childbirth experiences.<br /><strong>Methods:</strong><strong> </strong>This semi-experimental study involved 120 primiparous mothers at Alavi Hospital in Ardabil. The samples of the first and second groups were selected using convenience and purposeful methods, respectively. In the first phase, the childbirth experience questionnaire (CEQ) was completed for 60 primiparous mothers (first group) enrolled before the delivery agents ethics training workshop. After 4 weeks of the workshop, the second 60 primiparous mothers entered the study. The collected data were analyzed using Spearman and Pearson correlation tests and t-tests (P < 0.05).<br /><strong>Findings:</strong> The mean score of childbirth experience among the first group was 45.7 ± 8, which increased to 37.6 ± 6.9 in the second group after conducting a training workshop for the delivery agents. There was a significant correlation between the improvements in the clinical ethics of delivery agents and the enhancement of mothers' childbirth experiences (P < 0.001).<br /><strong>Conclusion:</strong> Positive childbirth experiences of mothers can be enhanced by improving the clinical ethics of delivery agents.<strong>Background:</strong> Clinical ethics of health care providers play an important role in shaping women’s childbirth experiences. This study aimed to examine the impact of improving delivery agents' clinical ethics on primiparous mothers' childbirth experiences.<br /><strong>Methods:</strong><strong> </strong>This semi-experimental study involved 120 primiparous mothers at Alavi Hospital in Ardabil. The samples of the first and second groups were selected using convenience and purposeful methods, respectively. In the first phase, the childbirth experience questionnaire (CEQ) was completed for 60 primiparous mothers (first group) enrolled before the delivery agents ethics training workshop. After 4 weeks of the workshop, the second 60 primiparous mothers entered the study. The collected data were analyzed using Spearman and Pearson correlation tests and t-tests (P < 0.05).<br /><strong>Findings:</strong> The mean score of childbirth experience among the first group was 45.7 ± 8, which increased to 37.6 ± 6.9 in the second group after conducting a training workshop for the delivery agents. There was a significant correlation between the improvements in the clinical ethics of delivery agents and the enhancement of mothers' childbirth experiences (P < 0.001).<br /><strong>Conclusion:</strong> Positive childbirth experiences of mothers can be enhanced by improving the clinical ethics of delivery agents.https://jims.mui.ac.ir/article_31368_dba76338497e2ebab41d96388c47ff26.pdfIsfahan University of Medical SciencesJournal of Isfahan Medical School1027-75954279620250120Investigating the Relationship between Water Pollution (Arsenic) and Preterm BirthInvestigating the Relationship between Water Pollution (Arsenic) and Preterm Birth113711423136710.48305/jims.v42.i796.1137FAMinooMohvahediAssociate Professor, Department of Obstetrics & Gynecology, School of Medicine, Al-Zahra Hospital, Isfahan University of Medical Sciences, Isfahan, Iran0000-0002-4035-2647MaryamDehghanAssistant Professor, Department of Gynecology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran0000-0002-7497-7012MinaGolvarinejadDepartment of Gynecology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran0009-0004-9260-9768Journal Article20241103
<strong>Background:</strong> Many adverse pregnancy outcomes, such as preterm birth, are believed to be caused by environmental pollution. One of the most significant polluters is arsenic in the water. In this study, we aimed to evaluate the relationship between arsenic and the development of preterm birth.
<strong>Methods:</strong><strong> </strong>This cross-sectional study was conducted on patients with preterm birth compared with a normal control group. All patients underwent urine samples to assess arsenic levels.
<strong>Findings:</strong><strong> </strong>The mean age in the group of mothers without preterm birth was 24.45 ± 4.63, and the mean age in the group of mothers with preterm birth was 25.18 ± 3.94 (P = 0.231). The mean arsenic level in mothers without preterm birth was 20.44 ± 8.24, and the mean arsenic level in the group of mothers with preterm birth was 22.75 ± 7.05 (P = 0.368). In late preterm birth, the mean Arsenic level was higher with slight significance, with a mean of 24.15 ± 4.63 (P = 0.045). This observation didn’t exist in early preterm birth with the mean Arsenic level of 21.05 ± 6.12 (P = 0.78).
<strong>Conclusion:</strong> We couldn’t find any significant relationship between urine arsenic levels and the occurrence of preterm birth. However, our data showed a relationship between late preterm birth and Arsenic levels. More comprehensive trials are recommended.
<strong>Background:</strong> Many adverse pregnancy outcomes, such as preterm birth, are believed to be caused by environmental pollution. One of the most significant polluters is arsenic in the water. In this study, we aimed to evaluate the relationship between arsenic and the development of preterm birth.
<strong>Methods:</strong><strong> </strong>This cross-sectional study was conducted on patients with preterm birth compared with a normal control group. All patients underwent urine samples to assess arsenic levels.
<strong>Findings:</strong><strong> </strong>The mean age in the group of mothers without preterm birth was 24.45 ± 4.63, and the mean age in the group of mothers with preterm birth was 25.18 ± 3.94 (P = 0.231). The mean arsenic level in mothers without preterm birth was 20.44 ± 8.24, and the mean arsenic level in the group of mothers with preterm birth was 22.75 ± 7.05 (P = 0.368). In late preterm birth, the mean Arsenic level was higher with slight significance, with a mean of 24.15 ± 4.63 (P = 0.045). This observation didn’t exist in early preterm birth with the mean Arsenic level of 21.05 ± 6.12 (P = 0.78).
<strong>Conclusion:</strong> We couldn’t find any significant relationship between urine arsenic levels and the occurrence of preterm birth. However, our data showed a relationship between late preterm birth and Arsenic levels. More comprehensive trials are recommended.https://jims.mui.ac.ir/article_31367_bb0a0a81b9924f16bc0b81e8e042be09.pdf