Search published articles
Volume 67, Issue 4 (7-2009)
Background: Previous studies suggested that stressful events that release Glucocorticoid from adrenal cortex and also injection of agonists of glucocorticoids receptors probably affect emotional learning and memory process and modulate them. The aim of this study was to determine the effects of acute stress and systemic injection of Corticosterone (as agonist of glucocorticoid receptors) on acquisition (ACQ), consolidation (CONS) and retrieval (RET) of emotional memory in rat.
Methods: In this experimental study we used 180 male Wistar rats (220-250). At the first rats was training in one trial inhibitory avoidance task. On the retention test given 48 h after training, the latency to re-enter the dark compartment of the apparatus (Step-through latency, STL) and the time spent in light chamber (TLC) were recorded during 10 min test. Intraperitoneal corticosterone in doses of 0.5, 1 and 3mg/kg injected 30min before, immediately after instruction and 30min before retrieval test. Also some groups received 10min stressful stimulation by restrainer at the same time. At the end locomotor's activity was measured for all animals.
Results: The data indicated that administration of corticosterone 30min before ACQ (1mg/kg), and immediately after CONS (1, 3mg/kg) enhance and 30min before RET (1, 3mg/kg) impair emotional memory (p<0.05). Acute stress impaired emotional memory in all phases (p<0.05). Also acute stress and injection of Corticosterone have not significantly affect motor activity.
Conclusions: These findings show that Glucocorticoid receptors in activation dependently plays an important role in modulation of emotional spatial memory processes (ACQ, CONS and RET in new information) for emotional events and these effects varies in different phases.
Volume 67, Issue 5 (8-2009)
Background: Learning and memory are the complicated agents of central nervous system that various regions of brain can be involved in these phenomena, especially regions like hippocamp. Various agents like nitric oxide and morphine can influence learning and memory. About the effects of morphine with other components there was not clear reports so in this study the effect of co-administration of L-Arginine (precursor of nitric oxide) and morphine in hippocampal CA3 area on spatial learning and memory in male rats was investigated.
Methods: Male rats were deeply anaesthetized with ketamine and xylazine and cannula were implanted bilaterally in CA3 of hippocampus by using streotaxic technique, Then male rats were used in seven groups that received saline, L-Arginine (0/3M), L-Arginine (3μg/rat), L-NAME (0/3M), morphine (10mg/rat), L-Arginine (3μg/rat) with morphine or L-NAME with morphine for five days that they were trained in morris water maze to evaluate spatial learning and memory. There was a control group too.
Results: Our results showed that L-Arginine (3μg/rat) improved spatial learning and memory. L-NAME (inhibitor of nitric oxide) decreased spatial learning and memory in male rats. Injection of morphine also decreased spatial learning and memory in male rats. Co-administeration of L-NAME and morphine decreased learning more than morphine individually in male rats.
Conclusion: We concluded that precursor of nitric oxide improved learning and memory in male rats and inhibitor of it and morphine impaired this phenomena and coadministration of inhibitor of nitric oxide and morphine also impaired learning in rats.
Volume 68, Issue 1 (4-2010)
Normal
0
false
false
false
EN-US
X-NONE
AR-SA
MicrosoftInternetExplorer4
Background: Ascorbic
acid improves cognitive impairments in several experimental models. Diabetes
causes learning and memory deficits. In this study we hypothesized that chronic
treatment with ascorbic acid (100mg/kg, p.o) would affect on the passive avoidance
learning (PAL) and memory in control and streptozocin-induced
diabetic rats.
Methods: Diabetes was induced by a single i.p. injection of STZ (60mg/kg). The
rats were considered diabetic if plasma glucose levels exceeded 250mg/dl on three
days after STZ injection. Treatment was begun at the onset of
hyperglycemia. PAL was assessed 30 days later. Retention test was done 24 h after
training. At the end, animals were weighted and blood samples were drawn for
plasma glucose measurement.
Results: Diabetes caused impairment in acquisition and
retrieval processes of PAL and memory in rats. Ascorbic acid treatment improved
learning and memory in control rats and reversed learning and memory deficits
in diabetic rats. Ascorbic acid administration also improved the body weight
loss and hyperglycemia of diabetics. Hypoglycemic and antioxidant properties of
the vitamin may be involved in the memory improving effects of such treatment.
Conclusion: These results show that ascorbic acid administration
to rats for 30
days from onset of diabetes alleviated the negative influence of diabetes on
learning and memory. Comparing with other nootropic drugs, vitamins have fewer
side effects. Therefore, this regimen may provide a new potential alternative
for prevention of the impaired cognitive functions associated with diabetes
after confirming by clinical trials.
Volume 68, Issue 10 (1-2011)
Background: Numerous evidences indicate that various environmental stresses during pregnancy affect physiological behavior of the offspring. This experimental study was designed to investigate the effect of noise stress during prenatal period of rats on spatial learning and memory and plasma corticostrone level in postnatal life.
Methods: Three groups of pregnant rats were given daily noise stress with durations of two and/ or four hours in last week of pregnancy period. The fourth group was left unstressed. The male offspring from the unstressed and different stressed groups were assigned as controls and stressed groups. The animals were introduced to a spatial task in Morris water maze 4 trials/day for five consecutive days. The probe test was performed on the 5th day of the experiment. The delay in findings and the distance passed to locate the target platform were assessed as the spatial learning.
Results: Our results showed that prenatal exposure to noise stress for two and/ or four hours a day, leads to impaired acquisition of spatial learning in the postnatal animals. The plasma level of corticostrone in the two stressed groups of rats markedly matched with their behavioral function. Prenatal exposure to 1- hour noise stress revealed no effects on the offsprings' behavior and plasma corticostrone level.
Conclusion: Based on our study results, it seems that applied range of stress which is executed through the noise stress could increase the plasma corticostrone level and could decrease spatial learning and memory of adult male offspring.
Volume 70, Issue 9 (12-2012)
Background: Diabetes mellitus affects numerous intracellular metabolic processes, which are reflected by changes in the concentration of some plasma constituents. Particularly, the disease may indirectly undermine some functions of the nervous system including learning and memory through altering oxidative stress status. On the other hand, probiotics can enhance the antioxidant capacity. This study was designed to evaluate the effects of probiotics on spatial memory, maze learning and indices of oxidative stress in diabetic rats.
Methods: In this experimental study, 40 male Wistar rats were randomly allocated to 4 groups (n=10 for each): Control (CO), Control probiotic (CP), Control diabetic (DC), and Diabetic probiotic (DP). The probiotic supplement, including Lactobacillus acidophilus, Lactobacillus fermentum, Bifidobacterium lactis (334 mg of each with a CFU of ~1010), was administered through drinking water every 12 hours for 8 weeks. Using morris water maze (MWM), spatial learning and memory were evaluated. Serum insulin and oxidative stress indices, including superoxide dismutase (SOD) and 8-hydroxy-2'-deoxyguanosine (8-OHdG), were measured by standard laboratory kits.
Results: Oral administration of probiotics improved impairment of spatial learning (P=0.008) and consolidated memory (P=0.01) in the rats. Moreover, probiotic treatment increased serum insulin (P<0.0001) and serum superoxide dismutase activity (P=0.007) while it decreased their blood glucose (P=0.006) and 8-OHdG (P<0.0001).
Conclusion: Probiotic supplementation reversed the serum concentrations of insulin and glucose along with an increase in antioxidant capacity in diabetic rats. It also improved spatial learning and memory in the animals. Relevancy of the metabolic changes and behavioral functions need to be further studied.
Volume 70, Issue 12 (3-2013)
Background: Extremely low frequency (0-300 Hz) fields from power lines, electronic equipment and medical devices, have been reported to produce various biological effects. Global system for mobile (GSM) is most largely used in everybody's life. This system utilizes a low frequency band as well as a high frequency range of electromagnetic field. This study investigated the effects of 217 Hz electromagnetic field (the modulating signal in GSM) on spatial learning and memory in rat.
Methods: Twenty four male Wistar rat (200- 250 g) were randomly divided in to three groups as: test, sham and control. Using a Helmholtz coil system, the test group was exposed to a uniform pulsed EMF of 200 µT (micro Tesla) intensity for 4 h/day for 21 days (2 time in a day). This procedure was repeated for the sham group but with no field. All groups were trained prior to the day 21 on the 15th day for five days four trial per day in Morris Water-Maze system. Then the probe test was carried out for 60 seconds with no platform.
Results: The ANOVA test revealed that no significant differences were found between control and exposed rats in all day of learning acquisition. Also, in probe test for investigating the memory, no significant differences observed. (P≤0.05 is accepted for significant level.
Conclusion: This finding is in consistent with previous studies and indicates low frequency band of electromagnetic fields (EMF) (200 µT intensity) in cell phone may not have any effect on the learning acquisition and spatial memory in rat.
Volume 73, Issue 8 (11-2015)
Background: Multiple Sclerosis (MS) is a neurodegenerative disease of the central nervous system (CNS). The hippocampus is a vital center for learning and memory it is extremely vulnerable to neurodegenerative diseases. The male hormones could be neuroprotective for the CNS. The current study is an attempt to investigate the effect of testosterone on learning and spatial memory following the demyelination of CA1 area by the injection of ethidium bromide in the rats' hippocampus. Methods: This experimental study has been conducted on healthy rats in the faculty of science of the Urmia University from September 2013 to February 2015. For demyelination in all previously gonadectomized healthy rats, 3µl ethidium bromide was injected into the CA1 area of rats by stereotaxic surgery. In addition, the treatment groups received 1µl testosterone (6µg/µl) during a 20-day timeframe on a daily basis after demyelination by the ethidium bromide. The control groups had no drug injection. The process of the learning and spatial memory of the rats were closely monitored by the radial Maze. The demyelination and remyelination in the hippocampus were checked by the myelin-specific coloring (Luxol fast blue and Cresyl violet). Results: The histological results suggest that the testosterone is capable of minimizing the destructive impacts of ethidium bromide in the treatment group as well as enhancing the remyelination process. In the group treated by testosterone, the percentage of the pyknotic cells 20 days after demyelination induction, represented a significant reduction compared to that of ethidium bromide group (P=0.008). The behavioral studies analyses show that the amount of the food finding time in those groups received ethidium bromide was significantly longer than those of the control groups (P=0.001). Furthermore, the application of the testosterone in the treatment groups reduced the extent of demyelination while the memory impairment induced by the ethidium bromide was significantly improved (P=0.001). Conclusion: Testosterone can act as a neuroprotective factor that reduces the extent of demyelination and the number of pyknotic cells. It also may improve the learning and memory impairment induced by ethidium bromide.
Volume 76, Issue 12 (3-2019)
Methods: This is a descriptive-analytic study that was conducted as a cross-sectional study. The study population included people referring to health centers in Mohammadieh City in Qazvin Province, Iran, from April to June 2015 for screening for diabetes. The 5-step CRISP method was used to implement this study. Data were collected from March 2015 to June 2015. In this study, 1055 persons with complete information were included in the study. Of these, 159 were healthy and 896 were diabetic. A total of 11 characteristics and risk factors were examined, including the age, sex, systolic and diastolic blood pressure, family history of diabetes, BMI, height, weight, waistline, hip circumference and diagnosis. The results obtained by support vector machine (SVM), decision tree (DT) and the k-nearest neighbors algorithm (k-NN) were compared with each other. Data was analyzed using MATLAB® software, version 3.2 (Mathworks Inc., Natick, MA, USA).
Results: Data analysis showed that in all criteria, the best results were obtained by decision tree with accuracy (0.96) and precision (0.89). The k-NN methods were followed by accuracy (0.96) and precision (0.83) and support vector machine with accuracy (0.94) and precision (0.85). Also, in this study, decision tree model obtained the highest degree of class accuracy for both diabetes classes and healthy in the analysis of confusion matrix.
Conclusion: Based on the results, the decision tree represents the best results in the class of test samples which can be recommended as a model for predicting diabetes type 2 using risk factor data.
Volume 77, Issue 7 (10-2019)
Methods: A myoelectric system based on convolutional neural networks (CNN) is proposed, as an alternative to conventional classification methods that depend on feature engineering. The proposed model was validated with 10 able-bodied subjects during single and combined wrist motions. Eight EMG channels were recorded using eight pairs of surface electrodes attached around the subject’s dominant forearm. The raw EMG data from windows of 167ms (200 samples) in 8 channels were arranged as 200×8 matrices. For each subject, a CNN was trained using the EMG matrices as the input and the corresponding motion classes as the target. The resulting model was tested using a 4-fold cross-validation. The performance of the proposed approach was compared to that of a standard SVM-based model that used a set of time-domain (TD) features including mean absolute value, zero crossings, slope sign changes, waveform length, and mean frequency.
Results: In spite of the proven performance and popularity of the TD features, no significant difference (P=0.19) was found between the classification accuracies of the two methods. The advantage of the proposed model is that it does not need manual extraction of features, as the CNN can automatically learn and extract required representations from the EMG data.
Conclusion: These results indicate the capacity of CNNs to learn and extract rich and complex information from biological signals. Because both amplitude and frequency of EMG increases with increasing muscle force, both temporal and spectral characteristics of EMG are needed for efficient estimation of motor intent. The TD set, also includes these types of features. The high performance of the CNN model shows its capability to learn temporal and spectral representations from raw EMG data.
Volume 78, Issue 3 (6-2020)
Methods: In this analytic study, the database of HAM10000 (human against machine with 10000 training images) dermoscopy images, 1000 melanocytic nevi and 1000 melanoma images were employed, where in each category 900 images were selected randomly and were designated as the training set. The remaining 100 images in each category were considered as the test set. A deep learning convolutional neural network (CNN) was deployed with AlexNet (Krizhevsky et al., 2012) as a pretrained model. The network was trained with 1800 dermoscope images and subsequently was validated with 200 test images. The proposed method removes the need for cumbersome tasks of lesion segmentation and feature extraction. Instead, the CNN can automatically learn and extract useful features from the raw images. Therefore, no image preprocessing is required. Study was conducted at Shahid Beheshti University of Medical Sciences, Tehran, Iran from January to February, 2020.
Results: The proposed model achieved an area under the receiver operating characteristic (ROC) curve of 0.98. Using a confidence score threshold of 0.5, a classification accuracy of 93%, sensitivity of 94%, and specificity of 92% was attained. The user can adjust the threshold to change the model performance according to preference. For example, if sensitivity is the main concern; i.e. false negative is to be avoided, then the threshold must be reduced to improve sensitivity at the cost of specificity. The ROC curve shows that to achieve sensitivity of 100%, specificity is decreased to 83%.
Conclusion: The results show the strength of convolutional neural networks in melanoma detection in dermoscopy images. The proposed method can be deployed to help dermatologists in identifying melanoma. It can also be implemented for self diagnosis of photographs taken from skin lesions. This may facilitate early detection of melanoma, and hence substantially reduce the mortality chance of this dangerous malignancy.
Volume 78, Issue 4 (7-2020)
Methods: In this analytic study, 327 AKIEC, 513 BCC, and 840 benign keratosis images from human against machine with 10000 training dermoscopy images (HAM10000) were extracted. From each of these three types, 90% of the images were designated as the training set and the remaining images were considered as the test set. A deep learning convolutional neural network (CNN) was developed for skin cancer detection by using AlexNet (Krizhevsky, et al., 2012) as a pretrained network. First, the model was trained on the training images to discriminate between benign and malignant lesions. In comparison with conventional methods, the main advantage of the proposed approach is that it does not need cumbersome and time-consuming procedures of lesion segmentation and feature extraction. This is because CNNs have the capability of learning useful features from the raw images. Once the system was trained, it was validated with test data to assess the performance. Study was carried out at Shahid Beheshti University of Medical Sciences, Tehran, Iran, in January and February, 2020.
|
Results: The proposed deep learning network achieved an AUC (area under the ROC curve) of 0.97. Using a confidence score threshold of 0.5, a classification accuracy of 90% was attained in the classification of images into malignant and benign lesions. Moreover, a sensitivity of 94% and specificity of 86% were obtained. It should be noted that the user can change the threshold to adjust the model performance based on preference. For example, reducing the threshold increase sensitivity while decreasing specificity.
Conclusion: The results highlight the efficacy of deep learning models in detecting non-melanoma skin cancer. This approach can be employed in computer-aided detection systems to assist dermatologists in identification of malignant lesions. |
Volume 79, Issue 1 (4-2021)
Methods: In this analytic study, which is done from April to November 2020 in Tehran, ultrasound images of 55 obese people who have undergone laparoscopic surgery have been used and the histological result of a liver biopsy has been employed as a reference for liver fat. First, 88 texture-based features were extracted from the images using the Gray-Level Co-Occurrence Matrix (GLCM) method. In the next step, using the method of minimum redundancy and maximum correlation, the top features were selected from among 88 features and applied to the classifier input. Finally, using the three classifiers of linear discriminant analysis, support vector machine and AdaBoost, the images were classified into 4 groups based on the amount of liver fat.
Results: The accuracy of the automatic liver fat prediction model from ultrasound images for AdaBoost classification was 92.72%. However, the accuracies obtained for support vector machine and linear discriminant analysis classification were 87.88% and 75.76%, respectively.
|
Conclusion: The proposed approach based on texture features using the GLCM and the AdaBoost classification from ultrasound images automatically detects the amount of liver fat with high accuracy and can help physicians and radiologists in the final diagnosis.
|
Volume 79, Issue 2 (5-2021)
Methods: In this article, which was done from April to November 2020 in Tehran, after pre-processing the fMRI data, 116 brain regions were extracted using an Automated Anatomical Labeling atlas. Then, the functional connectivity matrix between the time signals of 116 brain regions was calculated using Pearson correlation and mutual information methods. Using functional connectivity calculations, the brain graph network was formed, followed by thresholding of the brain connectivity network to keep significant and strong edges while eliminating weaker edges that were likely noise. Finally, 11 global features were extracted from the graph network and after performing statistical analyses and selecting optimal features; the classification of 14 healthy individuals and 11 patients with mild cognitive impairment was performed using a support vector machine classifier.
|
Results: Calculations were showed that the mutual information algorithm as a functional connectivity method and five global features of the graph network, including average strength, eccentricity, local efficiency, coefficient clustering and transitivity, using the support vector machine classifier achieved the best performance with the accuracy, sensitivity and specificity of 84, 86 and 93 percent, respectively.
|
Volume 79, Issue 5 (8-2021)
Breast cancer is one of the most common types of cancer in women. Screening mammography is a low‑dose X‑ray examination of breasts, which is conducted to detect breast cancer at early stages when the cancerous tumor is too small to be felt as a lump. Screening mammography is conducted for women with no symptoms of breast cancer, for early detection of cancer when the cancer is most treatable and consequently greatly reduce the death rate from the breast cancer. Screening mammography should be performed every year for women age 45-54, and every two years for women age 55 and older who are in good health. A mammogram is read by a radiologist to diagnose cancer.
To assist radiologists in reading mammograms, computer-aided detection (CAD) systems have been developed which can identify suspicious lesions on mammograms. CADs can improve the accuracy and confidence level of radiologists in decision making and have been approved by FDA for clinical use. Traditional CAD systems work based on conventional machine learning (ML) and image processing algorithms. With recent advances in software and hardware resources, a great breakthrough in deep learning (DL) algorithms was followed, which revolutionized various engineering areas including medical technologies. Recently, DL models have been applied in CAD systems in mammograms and achieved outstanding performance. In contrast to conventional ML, DL algorithms eliminate the need for the tedious task of human-designed feature engineering, as they are capable of learning useful features automatically from the raw data (mammogram). One of the most common DL frameworks is the convolutional neural network (CNN). To localize lesions in a mammogram, a CNN should be applied in region‑based algorithms such as R‑CNN, Fast R‑CNN, Faster R‑CNN, and YOLO.
| Proper training of a DL‑based CAD requires a large amount of annotated mammogram data, where cancerous lesions have been marked by an experienced radiologist. This highlights the importance of establishing a large, annotated mammogram dataset for the development of a reliable CAD system. This article provides a brief review of the state‑of‑the‑art techniques for DL‑based CAD in mammography. |
Volume 80, Issue 4 (7-2022)
Methods: This is a fundamental-applied study that was conducted from May 2020 to September 2021 using multimodal MRI images of 285 patients with glioma tumors from the BraTS 2018 Database. This database was collected from 19 different MRI imaging centers, including multimodal MRI images of 210 HGG patients, and 75 LGG patients. In this study, a 2D U-Net architecture was designed with a patch-based method for training, which comprises an encoding path for feature extraction and a symmetrical decoding path. The training of this network was performed in three separate stages, using data from high-grade gliomas (HGG), and low-grade gliomas (LGG), and combining two groups of 210, 75, and 220 patients, respectively.
|
Results: The proposed model estimated the Dice Similarity Coefficient (DSC) results in HGG datasets 0.85, 0.85, 0.77, LGG datasets 0.80, 0.66, 0.51, and the combination of the two groups 0.88, 0.79, 0.77 for regions the whole tumor, tumor core, and enhancing region in the training dataset, respectively. The results related to Hussdorf Distance (HD) for HGG datasets were 8.24, 9.92, 4.43, LGG datasets 11.5, 11.31, 2.23, and the combination of the two groups 7.20, 8.82, 4.43 for regions the whole tumor, tumor core, and enhancing region in the training dataset, respectively.
Conclusion: Using the U-Net network can help physicians in the accurate segmentation of the tumor and its various areas, as well as increase the survival rate of these patients and improve their quality of life through accurate diagnosis and early treatment. |
Volume 80, Issue 10 (1-2023)
Methods: This cross-sectional study was conducted at Isfahan University of Medical Sciences, School of Advanced Technologies in Medicine, from February 2020 to June 2022. In the pre-processing block, segmentation of brain signals, selection of suitable channels and filtering by Butterworth filter have been done; then data has transformed to the time-frequency domain by three different kinds of mother wavelets including Cmor, Mexicanhat, and Cgaus. In the classification step, two types of convolutional neural networks (one-dimensional and two-dimensional) were applied whereas each one of them was utilized in two different architectures. Finally, the performance of the networks has been investigated by each one of these three types of input data.
|
Results: Three channels were selected as the best ones for nine subjects. To separate 8-30 Hz, a 5th degree Butterworth filter was used. After finding the optimal parameters in the proposed networks, wavelet transform with Cgauss mother wavelet has the highest percentage in the both proposed architectures. Two-dimensional convolutional neural network has higher convergence speed, higher accuracy and more complexity of calculations. In terms of accuracy, precision, sensitivity and F1-score, two-dimensional convolutional neural network has performed better than one-dimensional convolutional neural network. The accuracy of 92.53%, which is obtained from the second architecture, as the best result, is reported.
Conclusion: The results obtained from the proposed network indicate that suitable, and well-designed deep learning networks can be utilized as an accurate tool for data classification in application of motion perception. |
Volume 80, Issue 12 (3-2023)
Methods: This study was conducted as a systematic review and meta-analysis. Searching for articles in this study was done from September 24 to October 15, 2022 in databases: Proquest, PubMed, Iran medex, Scopus, Sid, Magiran, Google Scholar, Eric and medical education journals. The research environment of Iran has been Mashhad. Using the PICOTS model, the keywords: learning styles, clubs, medical students were used to search the mentioned databases. OR, AND operators and possible combinations of keywords were used when searching for articles in databases. The extracted articles were first evaluated in terms of the research title, then the abstract of the article, and finally the text of the article using the "PRISMA Checklist". In each stage, repetitive articles and articles that did not mention the percentage of learning styles were excluded from the study, and the articles that met the inclusion criteria were stored in the (EndNote software, version 20, Clarivate, USA), and at the end, 53 articles were analyzed.
|
Results: The results of the study showed that the most used learning styles among students of medical sciences in Iran was convergent learning style (32% with 95% confidence interval). In the investigation of the adaptive learning style in the fields of basic sciences during the years 2006 to 2021, the percentage of using this style increased and this trend was statistically significant (P=0.0078).
Conclusion: According to the findings of the study, the most used learning style in medical sciences in Iran is convergent learning style, and considering the characteristics of convergent people, it is necessary to provide effective and efficient training in medical sciences to Students' learning styles should be given special attention so that training can be guided based on their learning styles. |
Volume 81, Issue 5 (8-2023)
Background: The use of artificial intelligence algorithms to help with accurate diagnosis in medical images is one of the most important applications of this technology in the field of medical imaging. In this research, the possibility of replacing simple chest radiography instead of CT scan using machine learning models to detect pneumothorax was investigated in cases where CT is usually requested.
Methods: This study is analytical and was conducted from November 2022 to May 2023 at Kermanshah University of Medical Sciences. The data used in this research was extracted from the files of 350 patients suspected of pneumothorax. The collected images were pre-processed in MATLAB software. Then, three machine learning algorithms, including Logistic elastic net regression (LENR), Logistic lasso regression (LLR) and Adaptive Boosting (AdaBoost) were used. To evaluate the performance of these models, the criteria of precision, accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), F1 score, and misclassification were used.
| Results: In the AdaBoost model, the accuracy value in radiographic and CT images was calculated as 98.89% and 98.63%, respectively, and the precision value was calculated as 99.17% and 98.27%, respectively. In radiographic images, the AUC value for AdaBoost model was calculated as 100% and in CT scan images as 96.96%. The F1 score for the same model in radiographic was 99% and in CT images was 98.68%. The specificity value for the AdaBoost model was calculated as 99.45% in radiographic images and 94.67% in CT scan images. In the LLR model, the AUC value for radiographic and CT scan images was 99.87% and 99.02%, respectively. Conclusion: According to the criteria evaluated in the present study, two LLR and AdaBoost models have similar performance in radiographic and CT images in terms of pneumothorax detection ability, so that this complication can also be diagnosed with high precision level using machine learning techniques on the radiographic images and thus receiving higher levels of radiation doses due to CT scan can be avoided in these patients. |
Volume 81, Issue 10 (1-2024)
|
Methods: This study used machine learning systems and similarity metrics to determine the behavior pattern of COVID-19 in different seasons of the year. The location of research was the Mousa ibn Ja'far Hospital in Mashhad, and the time was from May 2020 to August 2021. The symptoms of affected patients were compared with the compiled dataset, and the similarity of patients was prepared in a similarity matrix, and the Jaccard correlation coefficient was calculated on the data. Finally, the analysis of strains from the beginning of emergence to the latest strain was examined. The performance indicators of the algorithm in the Jaccard similarity method showed a recall metric with a value of 0.94, a precision metric with a value of 1, an F1 score with a value of 0.86, and remove accuracy metric with a value of 0.76. The most important factors in the investigation include white blood cells, platelets, RT-PCR, CT SCAN, shortness of breath, fever, SPO2, and respiratory rate.
Results: The transmission of the COVID-19 virus depends on several factors, including human interaction. The evidence of the collected data shows that people with COVID-19 have low lymphocyte count and it is very consistent with the results of recent studies. Due to the lack of a dataset, a comparative study was conducted and a dataset was collected. Conclusion: This study, leveraging machine learning algorithms, identified a clear seasonal correlation in the spread of COVID-19. Considering geographical and seasonal variations among patients, distinct symptoms were observed in each season corresponding to the prevalent strain during that period. |
| Page 1 from 1 |
Related Websites
Site Keywords
Cardiology, Anatomy, Biology, Epidemiology, Immunology, Neuroscience, Physical therapy, Physiology, Dermatology, Endocrinology and metabolicSite Statistics
- Registered users: 7722 users
- Online users: 2 users
- Guest users: 301 users
- All visits: 15245090 visits
- Visits in 24 Hours: 14765 visits
- Total articles: 11209 articles
- Published articles: 4922 articles
© 2024 , Tehran University of Medical Sciences, CC BY-NC 4.0
Designed & Developed by : Yektaweb