Sina Moosavi Kashani, Sanaz Zargar Balaye Jame, Nader Markazi, Ali Omrani Nava
Background: One of the most critical challenges in the emergency department (ED) is overcrowding, which creates negative consequences for patients and staff. Therefore, predicting the rate of patients entering the ED can help manage resources in this department effectively. Objectives: According to the time of data collection, we intended to predict the volume of patient admissions to the ED in epidemic conditions, such as COVID-19 and non-epidemic. In addition, we planned to compare the performance of the LSTM and CNN models. Methods: The collected data consists of three main categories. The first category pertains to air pollutants, provided by the Tehran air quality control organization. The second type relates to data from the Iran Meteorological Organization, and the third category includes the number of patients admitted to the ED of a hospital in Tehran. We also incorporated binary indicators for epidemic and non-epidemic conditions in the dataset. The data collection period spans from February 2018 to March 2022. We employed the Dickey-Fuller test to assess the stationarity of the data. After preprocessing, we independently developed long short-term memory (LSTM) neural network and convolutional neural network (CNN) models, considering various time windows of previous days. Keras and Tensorflow libraries in Python, along with the Google Colab environment, were utilized to execute the models. Results: The LSTM model exhibited the lowest root mean square error (RMSE) and mean absolute error (MAE) with a time window of the last seven days, while the CNN model outperformed the LSTM model with a time window of the previous 13 days. Additionally, the CNN model required less execution time than the LSTM model. Conclusions: In conclusion, deep learning algorithms prove suitable for analyzing multivariate time series data. The CNN model demonstrated the lowest prediction error.
{"title":"Comparison of Long Short-Term Memory and Convolutional Neural Network Models for Emergency Department Patients’ Arrival Daily Forecasting","authors":"Sina Moosavi Kashani, Sanaz Zargar Balaye Jame, Nader Markazi, Ali Omrani Nava","doi":"10.5812/jamm-140888","DOIUrl":"https://doi.org/10.5812/jamm-140888","url":null,"abstract":"Background: One of the most critical challenges in the emergency department (ED) is overcrowding, which creates negative consequences for patients and staff. Therefore, predicting the rate of patients entering the ED can help manage resources in this department effectively. Objectives: According to the time of data collection, we intended to predict the volume of patient admissions to the ED in epidemic conditions, such as COVID-19 and non-epidemic. In addition, we planned to compare the performance of the LSTM and CNN models. Methods: The collected data consists of three main categories. The first category pertains to air pollutants, provided by the Tehran air quality control organization. The second type relates to data from the Iran Meteorological Organization, and the third category includes the number of patients admitted to the ED of a hospital in Tehran. We also incorporated binary indicators for epidemic and non-epidemic conditions in the dataset. The data collection period spans from February 2018 to March 2022. We employed the Dickey-Fuller test to assess the stationarity of the data. After preprocessing, we independently developed long short-term memory (LSTM) neural network and convolutional neural network (CNN) models, considering various time windows of previous days. Keras and Tensorflow libraries in Python, along with the Google Colab environment, were utilized to execute the models. Results: The LSTM model exhibited the lowest root mean square error (RMSE) and mean absolute error (MAE) with a time window of the last seven days, while the CNN model outperformed the LSTM model with a time window of the previous 13 days. Additionally, the CNN model required less execution time than the LSTM model. Conclusions: In conclusion, deep learning algorithms prove suitable for analyzing multivariate time series data. The CNN model demonstrated the lowest prediction error.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"8 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140082096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sina Moosavi Kashani, Elham Yavari, Toktam Khatibi
Background: Optimizing resource allocation in emergency departments (ED) is challenging due to limited resources and high costs. Objectives: The objective of this study was to utilize data mining algorithms and simulation modeling to predict the length of stay (LOS) of patients and compare scenarios for increasing bed productivity. Methods: Data mining algorithms, including Random Forest (RF) regression and CatBoost (CB) regression models, were used to predict the LOS based on patient demographic information and vital signs. The process of admission to discharge in the ED was simulated, and different scenarios were compared to identify strategies for increasing bed productivity. Results: The combination of RF regression and CB regression models performed better than other methods in predicting the LOS of patients. Simulation modeling demonstrated that optimal resource allocation and increased bed productivity could be achieved using predicted LOS values. Conclusions: This study demonstrates that a combined approach of data mining and simulation can effectively manage ED resources and reduce congestion. The findings highlight the potential of advanced analytical techniques for improving healthcare service delivery and patient outcomes.
背景：由于资源有限且成本高昂，优化急诊科（ED）的资源分配具有挑战性。研究目的本研究旨在利用数据挖掘算法和模拟建模来预测患者的住院时间（LOS），并对提高病床生产率的方案进行比较。方法：采用数据挖掘算法，包括随机森林（RF）回归和 CatBoost（CB）回归模型，根据患者人口统计学信息和生命体征预测住院时间。模拟急诊室从入院到出院的过程，并对不同情况进行比较，以确定提高病床生产率的策略。结果显示RF 回归和 CB 回归模型的组合在预测患者生命周期方面的表现优于其他方法。模拟建模表明，使用预测的 LOS 值可以实现最佳资源分配并提高病床生产率。结论：这项研究表明，数据挖掘和模拟相结合的方法可以有效管理急诊室资源，减少拥堵。研究结果凸显了先进分析技术在改善医疗服务和患者治疗效果方面的潜力。
{"title":"Optimizing Emergency Department Resource Allocation Using Discrete Event Simulation and Machine Learning Techniques","authors":"Sina Moosavi Kashani, Elham Yavari, Toktam Khatibi","doi":"10.5812/jamm-140645","DOIUrl":"https://doi.org/10.5812/jamm-140645","url":null,"abstract":"Background: Optimizing resource allocation in emergency departments (ED) is challenging due to limited resources and high costs. Objectives: The objective of this study was to utilize data mining algorithms and simulation modeling to predict the length of stay (LOS) of patients and compare scenarios for increasing bed productivity. Methods: Data mining algorithms, including Random Forest (RF) regression and CatBoost (CB) regression models, were used to predict the LOS based on patient demographic information and vital signs. The process of admission to discharge in the ED was simulated, and different scenarios were compared to identify strategies for increasing bed productivity. Results: The combination of RF regression and CB regression models performed better than other methods in predicting the LOS of patients. Simulation modeling demonstrated that optimal resource allocation and increased bed productivity could be achieved using predicted LOS values. Conclusions: This study demonstrates that a combined approach of data mining and simulation can effectively manage ED resources and reduce congestion. The findings highlight the potential of advanced analytical techniques for improving healthcare service delivery and patient outcomes.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"21 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139958462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: Chronic kidney disease (CKD) poses a significant health burden worldwide, affecting approximately 10 - 15% of the global population. As one of the leading non-communicable diseases, CKD is a major cause of morbidity and mortality. Early identification of CKD is crucial for reducing its adverse effects on patient health. Prompt detection can significantly lessen the harmful consequences and enhance health outcomes for individuals with CKD. Objectives: This study aimed to evaluate and compare the effectiveness of various machine learning models in predicting the occurrence of CKD. Methods: The study involved the collection of data from a sample of 400 patients. We applied the well-established cross-industry standard process (CRISP) methodology for data mining to analyze the data. As part of this process, we efficiently handled missing data using the mode approach and addressed outliers through the interquartile range (IQR) method. We utilized sophisticated techniques, such as CatBoost (CB), random forest (RF), and artificial neural network (ANN) models to predict outcomes. For evaluation, we used the receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC). Results: An analysis of 400 patient records in this study identified that variables like serum creatinine, packed cell volume, specific gravity, and hemoglobin were most influential in predicting CKD. The results indicated that the CB and RF models surpassed the ANN in predicting the disease. Ten critical predictors were pinpointed for accurate disease prediction. Conclusions: The ensemble models in this study not only showcased remarkable speed but also demonstrated superior accuracy. These findings suggest the potential of ensemble models as an effective tool for enhancing predictive performance in similar studies.
{"title":"Comparing the Performance of Machine Learning Models in Predicting the Risk of Chronic Kidney Disease","authors":"Sina Moosavi Kashani, Sanaz Zargar Balaye Jame","doi":"10.5812/jamm-140885","DOIUrl":"https://doi.org/10.5812/jamm-140885","url":null,"abstract":"Background: Chronic kidney disease (CKD) poses a significant health burden worldwide, affecting approximately 10 - 15% of the global population. As one of the leading non-communicable diseases, CKD is a major cause of morbidity and mortality. Early identification of CKD is crucial for reducing its adverse effects on patient health. Prompt detection can significantly lessen the harmful consequences and enhance health outcomes for individuals with CKD. Objectives: This study aimed to evaluate and compare the effectiveness of various machine learning models in predicting the occurrence of CKD. Methods: The study involved the collection of data from a sample of 400 patients. We applied the well-established cross-industry standard process (CRISP) methodology for data mining to analyze the data. As part of this process, we efficiently handled missing data using the mode approach and addressed outliers through the interquartile range (IQR) method. We utilized sophisticated techniques, such as CatBoost (CB), random forest (RF), and artificial neural network (ANN) models to predict outcomes. For evaluation, we used the receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC). Results: An analysis of 400 patient records in this study identified that variables like serum creatinine, packed cell volume, specific gravity, and hemoglobin were most influential in predicting CKD. The results indicated that the CB and RF models surpassed the ANN in predicting the disease. Ten critical predictors were pinpointed for accurate disease prediction. Conclusions: The ensemble models in this study not only showcased remarkable speed but also demonstrated superior accuracy. These findings suggest the potential of ensemble models as an effective tool for enhancing predictive performance in similar studies.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139959690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: Assessing the interpersonal communication skills of nursing students during the COVID-19 pandemic enables us to understand their communication challenges and needs in crises and devise appropriate solutions to address them effectively. Objectives: This study aimed to determine the interpersonal communication skills of nursing students at Islamic Azad University, Karaj Branch, amidst the COVID-19 pandemic. Methods: This descriptive cross-sectional study was conducted on 167 nursing students in the seventh and 8th semesters of the School of Nursing and Midwifery at Islamic Azad University, Karaj Branch, during the academic year 2020 - 2021. Sampling was performed using a purposeful sampling method. Data were collected through a demographic information form and the Interpersonal Communication Skills Test, which was completed via self-report. Data were analyzed using SPSS software version 26, employing descriptive statistics (mean, standard deviation, frequency, percentage) and inferential tests such as the Pearson correlation coefficient and t-test. Results: The majority (53.3%) of nursing students exhibited moderate interpersonal communication skills. The lowest mean score was related to assertiveness (13.72 ± 3.24), while the highest mean score was associated with the ability to receive and send messages (28.53 ± 4.62). A weak, significant inverse correlation was observed between the total score of interpersonal communication skills and age (r = -0.182, P = 0.019). Conclusions: The results indicate that most nursing students during the COVID-19 pandemic possessed moderate interpersonal communication skills. The area of greatest weakness was assertiveness. These findings underscore the necessity of attention and training to enhance assertiveness skills among nursing students. Additionally, teaching nursing students interpersonal communication skills, particularly in critical conditions, is essential.
{"title":"Interpersonal Communication Skills of Nursing Students: A Cross-Sectional Study During the COVID-19 Pandemic","authors":"Sharareh Zeighami Mohammadi, Batool Mohammadi, Soheila Moghimi Hanjani","doi":"10.5812/jamm-143468","DOIUrl":"https://doi.org/10.5812/jamm-143468","url":null,"abstract":"Background: Assessing the interpersonal communication skills of nursing students during the COVID-19 pandemic enables us to understand their communication challenges and needs in crises and devise appropriate solutions to address them effectively. Objectives: This study aimed to determine the interpersonal communication skills of nursing students at Islamic Azad University, Karaj Branch, amidst the COVID-19 pandemic. Methods: This descriptive cross-sectional study was conducted on 167 nursing students in the seventh and 8th semesters of the School of Nursing and Midwifery at Islamic Azad University, Karaj Branch, during the academic year 2020 - 2021. Sampling was performed using a purposeful sampling method. Data were collected through a demographic information form and the Interpersonal Communication Skills Test, which was completed via self-report. Data were analyzed using SPSS software version 26, employing descriptive statistics (mean, standard deviation, frequency, percentage) and inferential tests such as the Pearson correlation coefficient and t-test. Results: The majority (53.3%) of nursing students exhibited moderate interpersonal communication skills. The lowest mean score was related to assertiveness (13.72 ± 3.24), while the highest mean score was associated with the ability to receive and send messages (28.53 ± 4.62). A weak, significant inverse correlation was observed between the total score of interpersonal communication skills and age (r = -0.182, P = 0.019). Conclusions: The results indicate that most nursing students during the COVID-19 pandemic possessed moderate interpersonal communication skills. The area of greatest weakness was assertiveness. These findings underscore the necessity of attention and training to enhance assertiveness skills among nursing students. Additionally, teaching nursing students interpersonal communication skills, particularly in critical conditions, is essential.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"74 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139959980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: This article reports the measures related to the creation and establishment of a military field hospital by police medical workers in the procession of Arba'in as part of preventive preparation and national support in the field of health and treatment. After the multi-faceted investigations by the health deputy of the police, the University of Ilam province, Iran, and the governorate, considered to install four inflatable tents for the establishment of treatment areas in a land of 2 800 square meters in a part of the Arba'in walking path between the Mehran city and the border terminal with Iraq. The parking lot for the vehicles carrying troops, medical equipment, and ambulances was in the hospital area. The 40-bed military field hospital or compliance plan included the command room, men's and women's departments with two operation room beds, intensive care units, and support units, such as a pharmacy, drug storage, and medical equipment. Healthcare services were provided to more than two thousand five hundred pilgrims over 20 days. Telemedicine was connected with hospitals around the clock.
{"title":"Establishment of a Military Field Hospital by Police Medical Workers in Procession of Arba'in: Sharing an Experience","authors":"Z. Tabanejad, Mahdi Zareei, Morteza Mesri","doi":"10.5812/jamm-140573","DOIUrl":"https://doi.org/10.5812/jamm-140573","url":null,"abstract":": This article reports the measures related to the creation and establishment of a military field hospital by police medical workers in the procession of Arba'in as part of preventive preparation and national support in the field of health and treatment. After the multi-faceted investigations by the health deputy of the police, the University of Ilam province, Iran, and the governorate, considered to install four inflatable tents for the establishment of treatment areas in a land of 2 800 square meters in a part of the Arba'in walking path between the Mehran city and the border terminal with Iraq. The parking lot for the vehicles carrying troops, medical equipment, and ambulances was in the hospital area. The 40-bed military field hospital or compliance plan included the command room, men's and women's departments with two operation room beds, intensive care units, and support units, such as a pharmacy, drug storage, and medical equipment. Healthcare services were provided to more than two thousand five hundred pilgrims over 20 days. Telemedicine was connected with hospitals around the clock.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"35 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139777547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: This article reports the measures related to the creation and establishment of a military field hospital by police medical workers in the procession of Arba'in as part of preventive preparation and national support in the field of health and treatment. After the multi-faceted investigations by the health deputy of the police, the University of Ilam province, Iran, and the governorate, considered to install four inflatable tents for the establishment of treatment areas in a land of 2 800 square meters in a part of the Arba'in walking path between the Mehran city and the border terminal with Iraq. The parking lot for the vehicles carrying troops, medical equipment, and ambulances was in the hospital area. The 40-bed military field hospital or compliance plan included the command room, men's and women's departments with two operation room beds, intensive care units, and support units, such as a pharmacy, drug storage, and medical equipment. Healthcare services were provided to more than two thousand five hundred pilgrims over 20 days. Telemedicine was connected with hospitals around the clock.
{"title":"Establishment of a Military Field Hospital by Police Medical Workers in Procession of Arba'in: Sharing an Experience","authors":"Z. Tabanejad, Mahdi Zareei, Morteza Mesri","doi":"10.5812/jamm-140573","DOIUrl":"https://doi.org/10.5812/jamm-140573","url":null,"abstract":": This article reports the measures related to the creation and establishment of a military field hospital by police medical workers in the procession of Arba'in as part of preventive preparation and national support in the field of health and treatment. After the multi-faceted investigations by the health deputy of the police, the University of Ilam province, Iran, and the governorate, considered to install four inflatable tents for the establishment of treatment areas in a land of 2 800 square meters in a part of the Arba'in walking path between the Mehran city and the border terminal with Iraq. The parking lot for the vehicles carrying troops, medical equipment, and ambulances was in the hospital area. The 40-bed military field hospital or compliance plan included the command room, men's and women's departments with two operation room beds, intensive care units, and support units, such as a pharmacy, drug storage, and medical equipment. Healthcare services were provided to more than two thousand five hundred pilgrims over 20 days. Telemedicine was connected with hospitals around the clock.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"18 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139837253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: Patient’s shared decision-making (SDM) is an ethical standard for respecting patient autonomy. Objectives: This study aimed to investigate the level of SDM for emergency surgery and its related factors in hospitals affiliated with the Zanjan University of Medical Sciences, Iran. Methods: This cross-sectional study was performed on 306 patients candidates for emergency surgery in 2020. The research instruments included a 9-item SDM Questionnaire and an SDM-related factors questionnaire for surgery. Results: Our results showed that more than 50% of patients did not participate in choosing emergency surgery. Among the related factors, the SDM level of the family members, the patient's marital status, and systolic blood pressure were the main predictors of the patient’s SDM for surgery (P < 0.05). Conclusions: The emergency conditions of patients and the high workload of staff reduced participation in the decision-making of patients and their family members.
{"title":"Factors Related to Participation in Decision-making in Emergency Surgery Patients","authors":"Roya Mohammadi, Nasrin Hanifi, Nasrin Bahraminejad","doi":"10.5812/jamm-140840","DOIUrl":"https://doi.org/10.5812/jamm-140840","url":null,"abstract":"Background: Patient’s shared decision-making (SDM) is an ethical standard for respecting patient autonomy. Objectives: This study aimed to investigate the level of SDM for emergency surgery and its related factors in hospitals affiliated with the Zanjan University of Medical Sciences, Iran. Methods: This cross-sectional study was performed on 306 patients candidates for emergency surgery in 2020. The research instruments included a 9-item SDM Questionnaire and an SDM-related factors questionnaire for surgery. Results: Our results showed that more than 50% of patients did not participate in choosing emergency surgery. Among the related factors, the SDM level of the family members, the patient's marital status, and systolic blood pressure were the main predictors of the patient’s SDM for surgery (P < 0.05). Conclusions: The emergency conditions of patients and the high workload of staff reduced participation in the decision-making of patients and their family members.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"38 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135430520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: Diagnosing patient deterioration and preventing unexpected deaths in the emergency department is a complex task that relies on the expertise and comprehensive understanding of emergency physicians concerning extensive clinical data. Objectives: Our study aimed to predict emergency department mortality and compare different models. Methods: During a one-month period, demographic information and records were collected from 1,000 patients admitted to the emergency department of a selected hospital in Tehran. We rigorously followed The Cross Industry Standard Process for data mining and methodically progressed through its sequential steps. We employed Cat Boost and Random Forest models for prediction purposes. To prevent overfitting, Random Forest feature selection was employed. Expert judgment was utilized to eliminate features with an importance score below 0.0095. To achieve a more thorough and dependable assessment, we implemented a K-fold cross-validation method with a value of 5. Results: The Cat Boost model outperformed Random Forest significantly, showcasing an impressive mean accuracy of 0.94 (standard deviation: 0.03). Ejection fraction, urea (body waste materials), and diabetes had the greatest impact on prediction. Conclusions: This study sheds light on the exceptional accuracy and efficiency of machine learning in predicting emergency department mortality, surpassing the performance of traditional models. Implementing such models can result in significant improvements in early diagnosis and intervention. This, in turn, allows for optimal resource allocation in the emergency department, preventing the excessive consumption of resources and ultimately saving lives while enhancing patient outcomes.
{"title":"Mortality Prediction in Emergency Department Using Machine Learning Models","authors":"Sina Moosavi Kashani, Sanaz Zargar","doi":"10.5812/jamm-140442","DOIUrl":"https://doi.org/10.5812/jamm-140442","url":null,"abstract":"Background: Diagnosing patient deterioration and preventing unexpected deaths in the emergency department is a complex task that relies on the expertise and comprehensive understanding of emergency physicians concerning extensive clinical data. Objectives: Our study aimed to predict emergency department mortality and compare different models. Methods: During a one-month period, demographic information and records were collected from 1,000 patients admitted to the emergency department of a selected hospital in Tehran. We rigorously followed The Cross Industry Standard Process for data mining and methodically progressed through its sequential steps. We employed Cat Boost and Random Forest models for prediction purposes. To prevent overfitting, Random Forest feature selection was employed. Expert judgment was utilized to eliminate features with an importance score below 0.0095. To achieve a more thorough and dependable assessment, we implemented a K-fold cross-validation method with a value of 5. Results: The Cat Boost model outperformed Random Forest significantly, showcasing an impressive mean accuracy of 0.94 (standard deviation: 0.03). Ejection fraction, urea (body waste materials), and diabetes had the greatest impact on prediction. Conclusions: This study sheds light on the exceptional accuracy and efficiency of machine learning in predicting emergency department mortality, surpassing the performance of traditional models. Implementing such models can result in significant improvements in early diagnosis and intervention. This, in turn, allows for optimal resource allocation in the emergency department, preventing the excessive consumption of resources and ultimately saving lives while enhancing patient outcomes.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135645383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: This study aimed to compare blood culture and serum levels of anti-Brucella antibodies between pregnancies leading to abortion and successful pregnancies. Methods: In this case-control study, 60 women with spontaneous abortions were considered the case group, and 60 women with normal pregnancy outcomes were selected as the control group. Both groups were matched. The serology of IgM and IgG antibodies and blood culture was also compared using the enzyme-linked immuno-sorbent assay (ELISA) method. IgM and IgG levels above and equal to 12 were considered positive titers, and data were analyzed using SPSS software version 20. Results: The mean age of mothers (P ≤ 0.364), the frequency of positive blood cultures for Brucella (P ≤ 0.157), seropositivity of anti-Brucella IgG (P ≤ 0.300), and seropositivity of anti-Brucella IgM (P ≤ 0.057) showed no significant differences between case and control groups; however, mean serum levels of IgM were significantly higher in women with abortion than in the control group (P ≤ 0.042). Conclusions: This study shows that Brucella seropositivity and positive blood culture are no more common in women with spontaneous abortions than in women with normal pregnancy outcomes. However, screening pregnant women for diseases in endemic areas, starting antibiotic treatment, and developing educational strategies for women of childbearing age will help prevent the disease and its adverse complications in pregnancy.
{"title":"Comparison of Blood Culture and Serum Levels of Anti-Brucella Antibodies in Spontaneous Abortions with Successful Pregnancies: A Case Study of Southeastern Iran","authors":"Maysam Yousefi, Zakieh Ostad-Ahmadi, Maryam Farsi, Seyyid Mohammad Keyhan Sajadi, Anahital Behzadi","doi":"10.5812/jamm-139366","DOIUrl":"https://doi.org/10.5812/jamm-139366","url":null,"abstract":"Background: This study aimed to compare blood culture and serum levels of anti-Brucella antibodies between pregnancies leading to abortion and successful pregnancies. Methods: In this case-control study, 60 women with spontaneous abortions were considered the case group, and 60 women with normal pregnancy outcomes were selected as the control group. Both groups were matched. The serology of IgM and IgG antibodies and blood culture was also compared using the enzyme-linked immuno-sorbent assay (ELISA) method. IgM and IgG levels above and equal to 12 were considered positive titers, and data were analyzed using SPSS software version 20. Results: The mean age of mothers (P ≤ 0.364), the frequency of positive blood cultures for Brucella (P ≤ 0.157), seropositivity of anti-Brucella IgG (P ≤ 0.300), and seropositivity of anti-Brucella IgM (P ≤ 0.057) showed no significant differences between case and control groups; however, mean serum levels of IgM were significantly higher in women with abortion than in the control group (P ≤ 0.042). Conclusions: This study shows that Brucella seropositivity and positive blood culture are no more common in women with spontaneous abortions than in women with normal pregnancy outcomes. However, screening pregnant women for diseases in endemic areas, starting antibiotic treatment, and developing educational strategies for women of childbearing age will help prevent the disease and its adverse complications in pregnancy.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135834355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ali Miri, Mostafa Roshanzadeh, Reza Masoudi, Soleiman Kheiri, Ali Tajabadi, Shirmohammad Davoodvand
Background: The use of massage as a safe method to control and manage complications after major surgery is recommended. Objectives: This study aimed to determine the effect of this method on arterial blood oxygen saturation and temperature changes in patients after abdominal and thoracic surgery. Methods: This quasi-experimental study was conducted on 60 patients undergoing surgery in Shahrekord city in 2019. They were enrolled in the study by convenience sampling and assigned to the intervention and control groups by the blocking method. In the intervention group, a hand and foot massage was performed at 5-minute intervals for 4 sessions on each patient's limb 3 times a day. The control group received routine care. Data were collected by a demographic questionnaire, pulse-oximetry, and thermometer. They were analyzed using SPSS version 16 and descriptive and inferential statistical tests (t-test, paired t-test, and analysis of variance (ANOVA)). Results: The mean arterial blood oxygen saturation in the groups after the intervention did not show a significant difference compared to before (P = 0.95), but its mean was significantly higher in the intervention group after the intervention than before (P < 0.001). The mean temperature in the 2 groups after the intervention did not show a significant difference compared to before (P = 0.38), but the changes in the mean were significant in the massage group after the intervention compared to before (P = 0.019). Conclusions: The hand and foot massage can be used by nurses along with the required medical care to improve arterial blood oxygen saturation and reduce body temperature. Further research in this area is suggested.
背景:推荐使用按摩作为一种安全的方法来控制和处理大手术后的并发症。目的:本研究旨在确定该方法对腹胸外科术后患者动脉血氧饱和度和体温变化的影响。方法:对2019年在Shahrekord市接受手术治疗的60例患者进行准实验研究。本研究采用方便抽样的方法将其纳入研究，并采用分组法将其分为干预组和对照组。干预组每日对患者肢体进行3次手脚按摩，每次5分钟，共4次。对照组接受常规护理。通过人口调查问卷、脉搏血氧仪和体温计收集数据。使用SPSS version 16和描述性和推断性统计检验(t检验、配对t检验和方差分析)进行分析。结果:干预后各组动脉血氧饱和度均值与干预前比较差异无统计学意义(P = 0.95)，但干预组干预后动脉血氧饱和度均值明显高于干预前(P <0.001)。两组患者干预后平均体温与干预前比较差异无统计学意义(P = 0.38)，但按摩组干预后平均体温与干预前比较差异有统计学意义(P = 0.019)。结论:护理人员在进行必要的医疗护理的同时，采用手、足按摩可提高动脉血氧饱和度，降低体温。建议在这方面进行进一步的研究。
{"title":"The Effect of Limb Massage on Arterial Blood Oxygen Saturation and Body Temperature Changes in Patients Undergoing Surgery","authors":"Ali Miri, Mostafa Roshanzadeh, Reza Masoudi, Soleiman Kheiri, Ali Tajabadi, Shirmohammad Davoodvand","doi":"10.5812/jamm-138073","DOIUrl":"https://doi.org/10.5812/jamm-138073","url":null,"abstract":"Background: The use of massage as a safe method to control and manage complications after major surgery is recommended. Objectives: This study aimed to determine the effect of this method on arterial blood oxygen saturation and temperature changes in patients after abdominal and thoracic surgery. Methods: This quasi-experimental study was conducted on 60 patients undergoing surgery in Shahrekord city in 2019. They were enrolled in the study by convenience sampling and assigned to the intervention and control groups by the blocking method. In the intervention group, a hand and foot massage was performed at 5-minute intervals for 4 sessions on each patient's limb 3 times a day. The control group received routine care. Data were collected by a demographic questionnaire, pulse-oximetry, and thermometer. They were analyzed using SPSS version 16 and descriptive and inferential statistical tests (t-test, paired t-test, and analysis of variance (ANOVA)). Results: The mean arterial blood oxygen saturation in the groups after the intervention did not show a significant difference compared to before (P = 0.95), but its mean was significantly higher in the intervention group after the intervention than before (P < 0.001). The mean temperature in the 2 groups after the intervention did not show a significant difference compared to before (P = 0.38), but the changes in the mean were significant in the massage group after the intervention compared to before (P = 0.019). Conclusions: The hand and foot massage can be used by nurses along with the required medical care to improve arterial blood oxygen saturation and reduce body temperature. Further research in this area is suggested.","PeriodicalId":15058,"journal":{"name":"Journal of Archives in Military Medicine","volume":"326 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135538795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：