algorithms

We aimed to evaluate the performance of the current algorithm the HIV diagnosis that has been performed for four years. Results of HIV Ag/Ab tests, anti-HIV 1/2 confirmatory tests, HIV-1 RNA tests and the time for official results to be approved were evaluated.

The relationship of HIV Ag/Ab tests, anti-HIV 1/2 confirmation tests and HIV-1 RNA PCR tests, their result times and suitability to the algorithm were examined at Izmir Dokuz Eylül University between May 2017 and June 2021.

HIV Ag/Ab ELISA was reactive repetitively in 165/54628 (0.30%) serum samples. Anti-HIV 1/2 confir-mation test was reactive in 54.42% (80/147) of samples. The most common pattern (18.2%) in the con-firmation tests was the positivity of the antibodies against gp160 - gp41 envelope glycoproteins together. The mean reporting time of the confirmation test result was 3h 50 min after the ELISA test. The mean reporting time of the HIV-1 RNA PCR was 12.79 d (±10.22) after the ELISA test and 12.63 (± 10.12) day after the confirmation test. In ROC analysis, the estimated rate of the ELISA test for the confirmation test was highest when S/CO was >13.16 (sensitivity: 97.59 %, specificity: 97.59%).

The confirmation test in the current algorithm enabled the rapid test results, early diagnosis of HIV and early antiretroviral therapy. To use the new algorithm effectively, decentralization of the validation tests would be appropriate.

Smart hospitals today use Artificial Intelligence to improve the quality of their services. In this sense, optimizing the patient's electronic medical record is one of the most significant issues that these hospitals face.

This study aimed to determine the role of AI in patient electronic records in a smart hospital.

This study was a systematic review, with keywords searched in PubMed, Scopus, Google Scholar, and SID databases. In Persian and English, the keywords were artificial intelligence algorithms, electronic medical records, service quality, and hospital. The inclusion criteria included publication in Persian or English, full-text papers, current publications, and a focus on the use of AI in electronic medical records. Finally, about 57 papers related to the investigation were picked.

After reviewing previous related studies, it was discovered that AI can play a role in various aspects of electronic patient records, such as disease diagnosis, predicting relapse and recovery periods, improving treatment accuracy and reducing medical errors, digital care, and decision-support systems. This can result in a 20-30% improvement in resource planning, a 30% decrease in wait times, better resource use, and more accurate predictions.

Leveraging AI in electronic patient records is critical for maximizing benefits while minimizing hazards. Despite the limitations, AI has the potential to become a critical tool for smart hospitals in improving healthcare delivery and efficiency. Accordingly, healthcare leaders that incorporate AI algorithms into their systems can give more effective and up-to-date care to their patients.

In Radiotherapy, computation of dose is important since in a small field with heterogeneity, dose is usually computed with discrepancies. The present study was aimed to evaluate the dosimetry of treatment planning algorithms in lung equivalent heterogeneous medium for Volumetric Modulated Arc Therapy (VMAT) with step and shoot Intensity-Modulated Radiation Therapy (ss-IMRT), and dynamic Intensity-Modulated Radiation Therapy (d-IMRT). In this experimental study, Computerized Imaging Reference System (CIRS) phantom was used with an inhomogeneous Racemosa wood cylinder for two types of tumors, namely, Left Lung Central Tumor (LCT) and Left Lung Peripheral Tumor (LPT) in the CIRS left lung cavity. The computed tomography (CT) datasets were employed with the generation of VMAT, d-IMRT and ss-IMRT plans for the LCT and LPT irradiated with 6 MV photon beams. In this study, the accuracy and efficacy of two algorithms: Monte Carlo (MC) and the Pencil Beam (PB), from the Monaco treatment planning system (TPS), were tested by using Gafchromic EBT3 films and CIRS thorax phantom. Regardless of treatment techniques, both algorithms exhibited higher divergence in LPT than LCT. In both LCT and LPT, the highest deviation was near the tumor-lung junction. However, the deviation was higher in the PB algorithm than MC algorithm, with a minimally acceptable variation of -0.8%.  The MC algorithm shows more consistency for EBT3 measured dose in lung equivalent heterogeneous medium. However, accurate dose predictions are complicated due to electronic disequilibrium within and at the interface of inhomogeneity. These constraints may cause variations from the anticipated outcomes of the treatments.

Early diagnosis and interceptive treatment of the maxillary canine impaction is crucial as it reduces treatment complexity and decreases complications and adverse outcomes. The aim of the study was to the prediction of impacted maxillary canines, and early diagnosis by using panoramic.

This investigation was a cross-sectional study performed on 385 panoramic radiographs, which were evaluated to assess the position of canines. Two methods Ericson and Kurol (EK/L) and the Power and Short (PS) geometric measurement analyses used in each radiograph. Thus, the prevalence was calculated from each method. The normality of the data was subsequently analyzed by application of a one-sample non-parametric Kolmogorov-Smirnov test. Thereafter, Fisher’s exact and Mann-Whitney U tests were conducted to determine differences in the permanent tooth impaction of the subjects.

Five permanent canines were classified as high risk through the EK/L method. While the PS method was used, 20 high risks of impaction were found. The statistical difference is detected between the right and left sides. It was found statistical difference detected between EK/L and Ps methods (p = 0.004). 

The EK/L method determined a canine impaction prevalence on pa noramic radiographs of 1.3%, while in the PS Method, the prevalence was 5. 2%. In addition, a significant predilection of canine impaction to the gender was not found.

Artificial Inteligence (AI) application in emergency medicine is subject to ethical and legal inconsisten-cies. The purposes of this study were to map the extent of AI applications in emergency medicine, to identify ethicalissues related to the use of AI, and to propose an ethical framework for its use.

A comprehensive literature col-lection was compiled through electronic databases/internet search engines (PubMed, Web of Science Platform, MED-LINE, Scopus, Google Scholar/Academia, and ERIC) and reference lists. We considered studies published between 1January 2014 and 6 October 2022. Articles that did not self-classify as studies of an AI intervention, those that were notrelevant to Emergency Departments (EDs), and articles that did not report outcomes or evaluations were excluded. De-scriptive and thematic analyses of data extracted from the included articles were conducted.

A total of 137 outof the 2175 citations in the original database were eligible for full-text evaluation. Of these articles, 47 were included inthe scoping review and considered for theme extraction. This review covers seven main areas of AI techniques in emer-gency medicine: Machine Learning (ML) Algorithms (10.64%), prehospital emergency management (12.76%), triage,patient acuity and disposition of patients (19.15%), disease and condition prediction (23.40%), emergency departmentmanagement (17.03%), the future impact of AI on Emergency Medical Services (EMS) (8.51%), and ethical issues (8.51%).

There has been a rapid increase in AI research in emergency medicine in recent years. Several studies havedemonstrated the potential of AI in diverse contexts, particularly when improving patient outcomes through predic-tive modelling. According to the synthesis of studies in our review, AI-based decision-making lacks transparency. Thisfeature makes AI decision-making opaque.

Coronary artery disease (CAD) is known as the most common cardiovascular disease. The development of CAD is influenced by several risk factors. Diagnostic and therapeutic methods of this disease have many and costly side effects. Therefore, researchers are looking for cost‑effective and accurate methods to diagnose this disease. Machine learning algorithms can help specialists diagnose the disease early. The aim of this study is to detect CAD using machine learning algorithms.

In this study, three data mining algorithms support vector machine (SVM), artificial neural network (ANN), and random forest were used to predict CAD using the Isfahan Cohort Study dataset of Isfahan Cardiovascular Research Center. 19 features with 11495 records from this dataset were used for this research.

All three algorithms achieved relatively close results. However, the SVM had the highest accuracy compared to the other techniques. The accuracy was calculated as 89.73% for SVM. The ANN algorithm also obtained the high area under the curve, sensitivity and accuracy and provided acceptable performance. Age, sex, Sleep satisfaction, history of stroke, history of palpitations, and history of heart disease were most correlated with target class. Eleven rules were also extracted from this dataset with high confidence and support.

In this study, it was shown that machine learning algorithms can be used with high accuracy to detect CAD. Thus, it allows physicians to perform timely preventive treatment in patients with CAD.

Conventional optimization techniques are based on the planning approach in which positions and weights are varied to generate the desired dose distribution. Inverse planning simulated annealing (IPSA) is an advanced optimization method developed to automatically determine a suitable combination of positions to design an acceptable plan.  In this study, three optimization techniques namely IPSA, graphical optimization (GROPT), and geometrical optimization (GOPT) methods are compared in high-dose-rate interstitial brachytherapy of cervical carcinoma. In this retrospective study, twenty computed tomography (CT) data sets of 10 cervical cancer patients treated with Martinez Universal Perineal Interstitial Template-based interstitial brachytherapy were studied. The treatment plans generated were optimized using the IPSA, and GOPT methods. The prescribed dose was 24 Gy in 4 fractions. Plans produced using IPSA, GrOPT, and GOPT techniques were analyzed for comparison of dosimetric parameters, including target coverage, homogeneity, conformity, and organs at risk (OAR) doses.  V100 values for IPSA, GrOPT and GOPT plans were 95.81±2.33%, 93.12±2.76% and 88.90±4.95%, respectively. The mean D90 values for the IPSA, GrOPT, and GOPT plans were 6.45±0.15 Gy, 6.12±0.21 Gy, and 5.85±0.57 Gy, respectively. Significantly lower doses of OAR were in the IPSA plans that were more homogeneous (HI=0.66). Conformity was comparatively higher in IPSA-based plans (CI=0.75).   IPSA plans were superior and resulted in better target coverage, homogeneity, conformity, and minimal OAR doses.

Modern radiotherapy techniques are using advanced algorithms; however, phantoms used for quality assurance have homogeneous density; accordingly, the development of heterogeneous phantom mimicking human body sites is imperative to examine variation between planned and delivered doses. This study aimed to analyze the accuracy of planned dose by different algorithms using indigenously developed heterogeneous thoracic phantom (HT). In this experimental study, computed tomography (CT) of HT was done, and the density of different parts was measured. The plan was generated on CT images of HCP with 6 and 15 Megavoltage (MV) photon beams using different treatment techniques, including three-dimensional conformal radiotherapy (3D-CRT), intensity-modulated radiation therapy (IMRT), and volumetric modulated arc therapy (VMAT). Plans were delivered by the linear accelerator, and the dose was measured using the ion chamber (IC) placed in HT; planned and measured doses were compared. Density patterns for different parts of the fabricated phantom, including rib, spine, scapula, lung, chest wall, and heart were 1.849, 1.976, 1.983, 0.173, 0.855, and 0.833 g/cc, respectively. Variation between planned and IC estimated doses with the tolerance (±5%) for all photon energies using different techniques. Acuros-XB (AXB) showed a slightly higher variation between computed and IC estimated doses using HCP compared to the analytical anisotropic algorithm (AAA). The indigenous heterogeneous phantom can accurately simulate the dosimetric scenario for different algorithms (AXB or AAA) and be also utilized for routine patient-specific QA.

The ability of ambulance centers to respond to emergency calls is an important factor in the recovery of patients' health. This study aimed to provide a model for the establishment of emergency relief in the road network in 2020 in East Azerbaijan province.

This applied-descriptive and experimental research with an explanatory modelling approach used the comments of 70 experts to run a model, which was based on the use of a metaheuristic (genetic) algorithm ,Simulation for the number of ambulances and the composition of the monitoring list simultaneously , objective and subjective data combined ,the agent and environmental variables, were determined and modelled through a meta-hybrid approach during the agent-based simulation and the metaheuristic algorithm.

To travel the initial structure for 40 dangerous points and five stations, the initial time was equal to 7860 Minutes, which reached a number between 2700 and 4000 Minutes after genetic optimization, production of a new list, and the mutation of ambulances from one station to another.

This type of optimization can be used to accelerate activities and reduce costs. Due to the dissimilar traffic of the areas, the ambulance does not arrive at dangerous points at equal times. The travel time of all dangerous points can be reduced by changing the location of points, moving forward or backwards depending on the conditions, customizing the features of ambulances and dangerous points, and combining the list of areas to find the best location for emergencies according to the interaction between agents, environmental constraints, and different behavioral features.

The Electrocardiogram (ECG) is an important measure for diagnosing the presence or absence of heart arrhythmias. Premature ventricular contractions (PVC) is a relatively large arrhythmia occurring outside the normal tract and being triggered outside the Sino atrial (SA) node of heart. This study has focused on tunable Q-factor wavelet transform (TQWT) algorithm and statistical methods to detect PVC. In this analytical and statistical study, 22 ECGs records were selected from the MIT/BIH arrhythmia database. In the first stage the noise of signal remove and then five sub-bands create by TQWT. In the second stage nine features (minimum, maximum, root mean square, mean, interquartile range, standard deviation (SD), skewness, and variance) extracted of ECG and then the best features selected by using analysis of variance (ANOVA) test. Finally, the system is evaluated by using the learning machines of support vector machine (SVM), the K-Nearest Neighbor (KNN), and artificial neural network (ANN). The best results were verified with KNN learning machine: the sensitivity Se= 98.23% and accuracy Ac= 97.81%. A comparative analysis with the related existing methods shows the method proposed in this study is higher than the other method for classification PVC and can help physicians to classify normal and PVC heart signals in the screening of the patients with coronary artery diseases (CADs).

Bolus-type materials are needed in case of superficial lesions radiotherapy. This work determined the dosimetric accuracy of two commercial treatment planning systems (TPS) for calculating photon dose distribution in the presence of eXaSkin bolus.
Dose calculations were performed on collapsed cone convolution/superposition (CCC) and anisotropic analytical algorithm (AAA) using computed tomography (CT) images of heterogeneous CIRS phantom. EBT3 film was used to obtain percentage depth dose (PDD) curves and gamma index was utilized to compare the accuracy of the two algorithms. The passing rate of the global gamma index with the passing criterion of 3mm/3% as the standard criterion was considered 95% in this study.
Surface dose in PDD curves increased in the presence of 0.5 cm thick eXaSkin bolus. The passing rates of gamma index with standard passing criterion between AAA algorithm and EBT3 film measurements without and with bolus were 95% and 95.5%, respectively, while they were equal to 96% and 97.5% for CCC algorithm.
There was a good agreement in dose calculation between AAA and CCC algorithms. Furthermore, eXaSkin bolus increased the surface dose by a factor of 25%.

Dynamic protein-protein interaction networks (DPPIN) can confirm the conditional and temporal features of proteins and protein complexes. In addition, the relation of protein complexes in dynamic networks can provide useful information in understanding the dynamic functionality of PPI networks. In this paper, an algorithm is presented to discover the temporal association rule from the dynamic PPIN dataset. In this analytical study, the static protein-protein interaction network is transformed into a dynamic network using the gene expression thresholding to extract the protein complex relations. The number of presented proteins of the dynamic network is large at each time point. This number will increase for extraction of multidimensional rules at different times. By mapping the gold standard protein complexes as reference protein complexes, the number of items decreases from active proteins to protein complexes at each transaction. Extracted sub graphs as protein complexes, at each time point, are weighted according to the reference protein complexes similarity degrees. Mega-transactions and extended items are created based on occurrence bitmap matrix of the reference complexes. Rules will be extracted based on Mega-transactions of protein complexes. The proposed method has been evaluated using gold standard protein complex rules. The amount of extracted rules from Biogrid datasets and protein complexes are 281, with support 0.2. The characteristic of the proposed algorithm is the simultaneous extraction of intra-transaction and inter-transaction rules. The results evaluation using EBI data shows the efficiency of the proposed algorithm.

A simple noise reduction algorithm, i.e. a selective mean filter (SMF), had been previously introduced. The aim of this study is to investigate the image qualities filtered by a SMF and its comparison to an adaptive statistical iterative reconstruction (ASIR).
To assess the basic image quality, an American Association of Physicists in Medicine Computed Tomography (AAPM CT) performance phantom was used. The phantom was scanned by 128 Multiple Slices Computed Tomography. The tube current varied from 50 mA to 100, 150, and 200 mA. The images of a phantom were reconstructed by filtered back projection (FBP) followed by SMF and ASIR (20, 40, 60, 80, and 100%). The image quality assessment was in terms of noise level, noise power spectrum (NPS), and modulation transfer function (MTF).
The noise level and NPS of SMF was similar with ASIR 100%. The values of the MTF10 of the ASIR filter at any level and SMF were comparable. The MTF10 values of ASIR 60%, and SMF with 50 mA (low) were 0.76 ± 0.02 and 0.75 ± 0.02 cycle/mm, respectively. Meanwhile, the MTF10 of ASIR 60% and SMF with 200 mA (high) were 0.74 ± 0.00 and 0.73 ± 0.00 cycles/mm, respectively.
Our results indicated that the performance of the SMF in reducing noise is equivalent to the maximum level of ASIR strength, i.e., ASIR 100%.

QT-interval prolongation is an important parameter for heart arrhythmia diagnosis. It is the time interval from QRS-onset to the T-end of electrocardiogram (ECG). Manual measurement of QT-interval, especially for 12-leads ECG, is time-consuming. Hence, an automatic QT-interval measurement is necessary. A new method for automatic QT-interval measurement is presented in this paper, which mainly consists of three parts, including QRS-complex detection, determination of QRS-onset, and T-end determination. The QRS-complex detection is based on the modified Pan-Tompkins algorithm. The T-end is defined based on Region of Interest (ROI) maximum limit. We compare and test our proposed QT-interval measurement method with reference measurement in term of correlation coefficient and range of 95% LoA. The correlation coefficient and the range of 95% LoA are 0.575 and 0.290, respectively. The proposed method is successfully implemented in ECG monitoring system using smartphone with high performance. The accuracy, positive predictive, and sensitivity of the QRS-complex detection in the system are 99.70%, 99.78%, and 99.92%, respectively. The range of 95% LoA for the comparison between manual and the system’s QT-interval measurement is 0.216. The results show that the proposed method is dependable on the measure of the QT-interval and outperforms the other methods in term of correlation coefficient and range of 95% LoA.

Estimation of eye lens dose is important in head computed tomography (CT) examination since the eye lens is a sensitive organ to ionizing radiation. The purpose of this study is to compare estimations of eye lens dose in head CT examinations using local size-specific dose estimate (SSDE) based on size-conversion factors of the American Association of Physicists in Medicine (AAPM) Report No. 293 with those based on size-conversion factors of the AAPM Report No. 220. This experimental study is conducted on a group of patients who had undergone nasopharyngeal CT examination. Due to the longitudinal (z-axis) dose fluctuation, the average global SSDE and average local SSDE (i.e. particular slices where the eyes are located) were investigated. All estimates were compared to the measurement results using thermo-luminescent dosimeters (TLDs). The estimated and measured doses were implemented for 14 patients undergoing nasopharyngeal CT examination. It was found that the percentage differences of the volume CT dose index (CTDIvol), average global SSDE based on AAPM No. 220 (SSDEo,g), average local SSDE based on AAPM No. 220 (SSDEo,l), average global SSDE based on AAPM No. 293 (SSDEn,g) and average local SSDE based on AAPM No. 293 (SSDEn,l) against the measured TLD doses were 22.5, 21.7, 15.0, 9.3, and 2.1%, respectively. All comparisons between dose estimates and TLD measurements gave p -values less than 0.001, except for SSDEn,l (p -value = 0.566). SSDE based on AAPM Report No. 293 can be used to accurately estimate eye lens radiation doses by performing the calculations on a number of specific slices containing the eyes.

This paper presents open-source computer simulation programs developed for simulating, tracking, and estimating the COVID-19 outbreak.

The programs consisted of two separate parts: one set of programs built in Simulink with a block diagram display, and another one coded in MATLAB as scripts. The mathematical model used in this package was the SIR, SEIR, and SEIRD models represented by a set of differential-algebraic equations. It can be easily modified to develop new models for the problem. A generalized method was adopted to simulate worldwide outbreaks in an efficient, fast, and simple way.

To get a good tracking of the virus spread, a sum of sigmoid functions was proposed to capture any dynamic changes in the data. The parameters used for the input (infection and recovery rate functions) were computed using the parameter estimation tool in MATLAB. Several statistic methods were applied for the rate function including linear, mean, root-mean-square, and standard deviation. In addition, an adaptive neuro-fuzzy inference system (ANFIS) was employed and proposed to train the model and predict its output.

This procedure is presented in such a way that it can be generalized and applied in other parts and applications of estimating the scenarios of an event, including the potential of several models, including SIR, which is sensitive to pollution, etc. This program can be used as an educational tool or for research studies and this article promises some lasting contributions to field of COVID-19.