Determining the minimum data set of geriatric assessment at the Iran primary health care referral system: shifting from fragmentation to integration care for older people.

BACKGROUND: Geriatric assessment (GA) is a multidimensional process that disrupts the primary health care (PHC) referral system. Accessing consistent data is central to the provision of integrated geriatric care across multiple healthcare settings. However, due to poor-quality data and documentation of GA, developing an agreed minimum data set (MDS) is required. Therefore, this study aimed to develop a GA-MDS in the PHC referral system to improve data quality, data exchange, and continuum of care to address the multifaceted necessities of older people. METHODS: In our study, the items to be included within GA-MDS were determined in a three-stepwise process. First, an exploratory literature search was done to determine the related items. Then, we used a two-round Delphi survey to obtain an agreement view on items to be contained within GA-MDS. Finally, the validity of the GA-MDS content was evaluated. RESULTS: Sixty specialists from different health geriatric care disciplines scored data items. After, the Delphi phase from the 230 selected items, 35 items were removed by calculating the content validity index (CVI), content validity ratio (CVR), and other statistical measures. Finally, GA-MDS was prepared with 195 items and four sections including administrative data, clinical, physiological, and psychological assessments. CONCLUSIONS: The development of GA-MDS can serve as a platform to inform the geriatric referral system, standardize the GA process, and streamline their referral to specialized levels of care. We hope GA-MDS supports clinicians, researchers, and policymakers by providing aggregated data to inform medical practice and enhance patient-centered outcomes.

Establishing machine learning models to predict the early risk of gastric cancer based on lifestyle factors.

BACKGROUND: Gastric cancer is one of the leading causes of death worldwide. Screening for gastric cancer greatly relies on endoscopy and pathology biopsy, which are invasive and pose financial burdens. Thus, the prevention of the disease by modifying lifestyle-related behaviors and dietary habits or even the prevention of risk factor formation is of great importance. This study aimed to construct an inexpensive, non-invasive, fast, and high-precision diagnostic model using six machine learning (ML) algorithms to classify patients at high or low risk of developing gastric cancer by analyzing individual lifestyle factors. METHODS: This retrospective study used the data of 2029 individuals from the gastric cancer database of Ayatollah Taleghani Hospital in Abadan City, Iran. The data were randomly separated into training and test sets (ratio 0.7:0.3). Six  ML methods, including multilayer perceptron (MLP), support vector machine (SVM) (linear kernel), SVM (RBF kernel), k-nearest neighbors (KNN) (K = 1, 3, 7, 9), random forest (RF), and eXtreme Gradient Boosting (XGBoost), were trained to construct prognostic models before and after performing the relief feature selection method. Finally, to evaluate the models' performance, the metrics derived from the confusion matrix were calculated via a test split and cross-validation. RESULTS: This study found 11 important influence factors for the risk of gastric cancer, such as Helicobacter pylori infection, high salt intake, and chronic atrophic gastritis, among other factors. Comparisons indicated that the XGBoost had the best performance for the risk prediction of gastric cancer. CONCLUSIONS: The results suggest that based on simple baseline patient data, the ML techniques have the potential to start the prescreening of gastric cancer and identify high-risk individuals who should proceed with invasive examinations. Our model could also considerably lessen the number of cases that need endoscopic surveillance. Future studies are required to validate the efficacy of the models in a larger and multicenter population.

Which are best for successful aging prediction? Bagging, boosting, or simple machine learning algorithms?

BACKGROUND: The worldwide society is currently facing an epidemiological shift due to the significant improvement in life expectancy and increase in the elderly population. This shift requires the public and scientific community to highlight successful aging (SA), as an indicator representing the quality of elderly people's health. SA is a subjective, complex, and multidimensional concept; thus, its meaning or measuring is a difficult task. This study seeks to identify the most affecting factors on SA and fed them as input variables for constructing predictive models using machine learning (ML) algorithms. METHODS: Data from 1465 adults aged ≥ 60 years who were referred to health centers in Abadan city (Iran) between 2021 and 2022 were collected by interview. First, binary logistic regression (BLR) was used to identify the main factors influencing SA. Second, eight ML algorithms, including adaptive boosting (AdaBoost), bootstrap aggregating (Bagging), eXtreme Gradient Boosting (XG-Boost), random forest (RF), J-48, multilayered perceptron (MLP), Naïve Bayes (NB), and support vector machine (SVM), were trained to predict SA. Finally, their performance was evaluated using metrics derived from the confusion matrix to determine the best model. RESULTS: The experimental results showed that 44 factors had a meaningful relationship with SA as the output class. In total, the RF algorithm with sensitivity = 0.95 ± 0.01, specificity = 0.94 ± 0.01, accuracy = 0.94 ± 0.005, and F-score = 0.94 ± 0.003 yielded the best performance for predicting SA. CONCLUSIONS: Compared to other selected ML methods, the effectiveness of the RF as a bagging algorithm in predicting SA was significantly better. Our developed prediction models can provide, gerontologists, geriatric nursing, healthcare administrators, and policymakers with a reliable and responsive tool to improve elderly outcomes.

Using an adaptive network-based fuzzy inference system for prediction of successful aging: a comparison with common machine learning algorithms.

INTRODUCTION: The global society is currently facing a rise in the elderly population. The concept of successful aging (SA) appeared in the gerontological literature to overcome the challenges and problems of population aging. SA is a subjective and multidimensional concept with many ambiguities regarding its meaning or measuring. This study aimed to propose an intelligent predictive model to predict SA. METHODS: In this retrospective study, the data of 784 elderly people were used to develop and validate machine learning (ML) methods. Data pre-processing was first performed. First, an adaptive neuro-fuzzy inference system (ANFIS) was proposed to predict SA. Then, the predictive performance of the proposed model was compared with three ML algorithms, including multilayer perceptron (MLP) neural network, support vector machine (SVM), and random forest (RF) based on accuracy, sensitivity, precision, and F-score metrics. RESULTS: The findings indicated that the ANFIS model with gauss2mf built-in membership function (MF) outperformed the other models with accuracy, sensitivity, precision, and F-score of 91.57%, 95.18%, 92.31%, and 92.94%, respectively. CONCLUSIONS: The predictive performance of ANFIS is more efficient than the other ML models in SA prediction. The development of a decision support system (DSS) using our prediction model can provide healthcare administrators and policymakers with a reliable and responsive tool to improve elderly outcomes.

Optimizing prognostic factors of five-year survival in gastric cancer patients using feature selection techniques with machine learning algorithms: a comparative study.

BACKGROUND: Gastric cancer is the most common malignant tumor worldwide and a leading cause of cancer deaths. This neoplasm has a poor prognosis and heterogeneous outcomes. Survivability prediction may help select the best treatment plan based on an individual's prognosis. Numerous clinical and pathological features are generally used in predicting gastric cancer survival, and their influence on the survival of this cancer has not been fully elucidated. Moreover, the five-year survivability prognosis performances of feature selection methods with machine learning (ML) classifiers for gastric cancer have not been fully benchmarked. Therefore, we adopted several well-known feature selection methods and ML classifiers together to determine the best-paired feature selection-classifier for this purpose. METHODS: This was a retrospective study on a dataset of 974 patients diagnosed with gastric cancer in the Ayatollah Talleghani Hospital, Abadan, Iran. First, four feature selection algorithms, including Relief, Boruta, least absolute shrinkage and selection operator (LASSO), and minimum redundancy maximum relevance (mRMR) were used to select a set of relevant features that are very informative for five-year survival prediction in gastric cancer patients. Then, each feature set was fed to three classifiers: XG Boost (XGB), hist gradient boosting (HGB), and support vector machine (SVM) to develop predictive models. Finally, paired feature selection-classifier methods were evaluated to select the best-paired method using the area under the curve (AUC), accuracy, sensitivity, specificity, and f1-score metrics. RESULTS: The LASSO feature selection algorithm combined with the XG Boost classifier achieved an accuracy of 89.10%, a specificity of 87.15%, a sensitivity of 89.42%, an AUC of 89.37%, and an f1-score of 90.8%. Tumor stage, history of other cancers, lymphatic invasion, tumor site, type of treatment, body weight, histological type, and addiction were identified as the most significant factors affecting gastric cancer survival. CONCLUSIONS: This study proved the worth of the paired feature selection-classifier to identify the best path that could augment the five-year survival prediction in gastric cancer patients. Our results were better than those of previous studies, both in terms of the time required to form the models and the performance measurement criteria of the algorithms. These findings may be very promising and can, therefore, inform clinical decision-making and shed light on future studies.

Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19.

BACKGROUND: The exponential spread of coronavirus disease 2019 (COVID-19) causes unexpected economic burdens to worldwide health systems with severe shortages in hospital resources (beds, staff, equipment). Managing patients' length of stay (LOS) to optimize clinical care and utilization of hospital resources is very challenging. Projecting the future demand requires reliable prediction of patients' LOS, which can be beneficial for taking appropriate actions. Therefore, the purpose of this research is to develop and validate models using a multilayer perceptron-artificial neural network (MLP-ANN) algorithm based on the best training algorithm for predicting COVID-19 patients' hospital LOS. METHODS: Using a single-center registry, the records of 1225 laboratory-confirmed COVID-19 hospitalized cases from February 9, 2020 to December 20, 2020 were analyzed. In this study, first, the correlation coefficient technique was developed to determine the most significant variables as the input of the ANN models. Only variables with a correlation coefficient at a P-value < 0.2 were used in model construction. Then, the prediction models were developed based on 12 training algorithms according to full and selected feature datasets (90% of the training, with 10% used for model validation). Afterward, the root mean square error (RMSE) was used to assess the models' performance in order to select the best ANN training algorithm. Finally, a total of 343 patients were used for the external validation of the models. RESULTS: After implementing feature selection, a total of 20 variables were determined as the contributing factors to COVID-19 patients' LOS in order to build the models. The conducted experiments indicated that the best performance belongs to a neural network with 20 and 10 neurons in the hidden layer of the Bayesian regularization (BR) training algorithm for whole and selected features with an RMSE of 1.6213 and 2.2332, respectively. CONCLUSIONS: MLP-ANN-based models can reliably predict LOS in hospitalized patients with COVID-19 using readily available data at the time of admission. In this regard, the models developed in our study can help health systems to optimally allocate limited hospital resources and make informed evidence-based decisions.

Establishing a minimum data set for suicide and attempted suicide registry system in Iran.

BACKGROUND: Suicidal behavior is a major cause of mortality and disability worldwide. Accurate and consistent collection of data on suicide, suicide ideation, and suicide attempts presents many challenges for public health practitioners, policymakers, and researchers. This study aimed to establish a minimum data set (MDS) for integrating data across suicide registries and other data sources. METHODS: The MDS proposed in this study was developed in two-stepwise stages. First, an extensive literature review was performed in order to identify the potential data items. Then, we conducted a two-round Delphi stage to reach a consensus among experts regarding essential data items and a supplementary one-round Delphi stage for validating the content of the final MDS by calculating the individual item content validity index (CVI) and content validity ratio (CVR) and using other statistical tests. RESULTS: After the literature review, 189 data items were extracted and sent to a panel of experts in the form of a questionnaire. In the Delphi stage and CVI calculation, 55 and 10 experts participated in kappa and CVR calculation, respectively. Finally, the MDS of the suicide registry was finalized with 84 data elements that were classified into four categories, including patient profile, socio-economic status, clinical and psychopathological status, and suicide circumstances. CONCLUSIONS: The suicide MDS can become a standardized and consistent infrastructure for meaningful evaluations, reporting, and benchmarking of suicidal behaviors across regions and countries. We hope this MDS will facilitate epidemiological surveys and support policymakers by providing higher quality data capture to guide clinical practice and improve patient-centered outcomes.

Developing the minimum data set of the corrosive ingestion registry system in Iran.

BACKGROUND: Corrosive ingestion is still a major health problem, and its outcomes are often unpredicted. The implementation of a registry system for poisoning with corrosive substances may improve the quality of patient care and might be useful to manage this type of poisoning and its complications. Therefore, our study aimed to establish a minimum data set (MDS) for corrosive ingestion. METHODS: This was an applied study performed in 2022. First, a literature review was conducted to identify the potential data items to be included in the corrosive ingestion MDS. Then, a two-round Delphi survey was performed to attain an agreement among experts regarding the MDS content, and an additional Delphi step was used for confirming the final MDS by calculating the individual item content validity index (CVI) and content validity ratio (CVR) and by using other statistical tests. RESULTS: After the literature review, 285 data items were collected and sent to a two-round Delphi survey in the form of a questionnaire. In total, 75 experts participated in the Delphi stage, CVI, kappa, and CVR calculation. Finally, the MDS of the corrosive ingestion registry system was identified in two administrative and clinical sections with 21 and 152 data items, respectively. CONCLUSIONS: The development of an MDS, as the first and most important step towards developing the corrosive ingestion registry, can become a standard basis for data collection, reporting, and analysis of corrosive ingestion. We hope this MDS will facilitate epidemiological surveys and assist policymakers by providing higher quality data capture to guide clinical practice and improve patient-centered outcomes.

Prediction of successful aging using ensemble machine learning algorithms.

BACKGROUND: Aging is a chief risk factor for most chronic illnesses and infirmities. The growth in the aged population increases medical costs, thus imposing a heavy financial burden on families and communities. Successful aging (SA) is a positive and qualitative view of aging. From a biomedical perspective, SA is defined as the absence of diseases or disability disorders. This is distinct from normal aging, which is associated with age-related deterioration in physical and cognitive functions. From a social perspective, SA highlights life satisfaction and individual well-being, usually attained through socialization. It is an abstract and multidimensional concept surrounded by imprecision about its definition and measurement. Our study attempted to find the most effective features of SA as defined by Rowe and Kahn's theory. The determined features were used as input parameters of six machine learning (ML) algorithms to create and validate predictive models for SA. METHODS: In this retrospective study, the raw data set was first pre-processed; then, based on the data of a sample of 983, five basic ML techniques including artificial neural network, decision tree, support vector machine, Naïve Bayes, and k-nearest neighbors (K-NN) with one ensemble method (that gathers 30 K-NN algorithms as weak learners) were trained. Finally, the prediction result was yielded using the majority vote method based on the output of the generated base models. RESULTS: The experimental results revealed that the predictive system has been more successful in predicting SA with a 93% precision, 92.40% specificity, 87.80% sensitivity, 90.31% F-measure, 89.62% accuracy, and a ROC of 96.10%, using a five-fold cross-validation procedure. CONCLUSIONS: Our results showed that ML techniques potentially have satisfactory performance in supporting the SA-related decisions of social and health policymakers. The KNN-based ensemble algorithm is superior to the other ML models in classifying people into SA and non-SA classes.

Comparing machine learning algorithms for predicting COVID-19 mortality.

BACKGROUND: The coronavirus disease (COVID-19) hospitalized patients are always at risk of death. Machine learning (ML) algorithms can be used as a potential solution for predicting mortality in COVID-19 hospitalized patients. So, our study aimed to compare several ML algorithms to predict the COVID-19 mortality using the patient's data at the first time of admission and choose the best performing algorithm as a predictive tool for decision-making. METHODS: In this study, after feature selection, based on the confirmed predictors, information about 1500 eligible patients (1386 survivors and 144 deaths) obtained from the registry of Ayatollah Taleghani Hospital, Abadan city, Iran, was extracted. Afterwards, several ML algorithms were trained to predict COVID-19 mortality. Finally, to assess the models' performance, the metrics derived from the confusion matrix were calculated. RESULTS: The study participants were 1500 patients; the number of men was found to be higher than that of women (836 vs. 664) and the median age was 57.25 years old (interquartile 18-100). After performing the feature selection, out of 38 features, dyspnea, ICU admission, and oxygen therapy were found as the top three predictors. Smoking, alanine aminotransferase, and platelet count were found to be the three lowest predictors of COVID-19 mortality. Experimental results demonstrated that random forest (RF) had better performance than other ML algorithms with accuracy, sensitivity, precision, specificity, and receiver operating characteristic (ROC) of 95.03%, 90.70%, 94.23%, 95.10%, and 99.02%, respectively. CONCLUSION: It was found that ML enables a reasonable level of accuracy in predicting the COVID-19 mortality. Therefore, ML-based predictive models, particularly the RF algorithm, potentially facilitate identifying the patients who are at high risk of mortality and inform proper interventions by the clinicians.

Predictive modeling for COVID-19 readmission risk using machine learning algorithms.

INTRODUCTION: The COVID-19 pandemic overwhelmed healthcare systems with severe shortages in hospital resources such as ICU beds, specialized doctors, and respiratory ventilators. In this situation, reducing COVID-19 readmissions could potentially maintain hospital capacity. By employing machine learning (ML), we can predict the likelihood of COVID-19 readmission risk, which can assist in the optimal allocation of restricted resources to seriously ill patients. METHODS: In this retrospective single-center study, the data of 1225 COVID-19 patients discharged between January 9, 2020, and October 20, 2021 were analyzed. First, the most important predictors were selected using the horse herd optimization algorithms. Then, three classical ML algorithms, including decision tree, support vector machine, and k-nearest neighbors, and a hybrid algorithm, namely water wave optimization (WWO) as a precise metaheuristic evolutionary algorithm combined with a neural network were used to construct predictive models for COVID-19 readmission. Finally, the performance of prediction models was measured, and the best-performing one was identified. RESULTS: The ML algorithms were trained using 17 validated features. Among the four selected ML algorithms, the WWO had the best average performance in tenfold cross-validation (accuracy: 0.9705, precision: 0.9729, recall: 0.9869, specificity: 0.9259, F-measure: 0.9795). CONCLUSIONS: Our findings show that the WWO algorithm predicts the risk of readmission of COVID-19 patients more accurately than other ML algorithms. The models developed herein can inform frontline clinicians and healthcare policymakers to manage and optimally allocate limited hospital resources to seriously ill COVID-19 patients.

Comparing machine learning algorithms to predict 5-year survival in patients with chronic myeloid leukemia.

INTRODUCTION: Chronic myeloid leukemia (CML) is a myeloproliferative disorder resulting from the translocation of chromosomes 19 and 22. CML includes 15-20% of all cases of leukemia. Although bone marrow transplant and, more recently, tyrosine kinase inhibitors (TKIs) as a first-line treatment have significantly prolonged survival in CML patients, accurate prediction using available patient-level factors can be challenging. We intended to predict 5-year survival among CML patients via eight machine learning (ML) algorithms and compare their performance. METHODS: The data of 837 CML patients were retrospectively extracted and randomly split into training and test segments (70:30 ratio). The outcome variable was 5-year survival with potential values of alive or deceased. The dataset for the full features and important features selected by minimal redundancy maximal relevance (mRMR) feature selection were fed into eight ML techniques, including eXtreme gradient boosting (XGBoost), multilayer perceptron (MLP), pattern recognition network, k-nearest neighborhood (KNN), probabilistic neural network, support vector machine (SVM) (kernel = linear), SVM (kernel = RBF), and J-48. The scikit-learn library in Python was used to implement the models. Finally, the performance of the developed models was measured using some evaluation criteria with 95% confidence intervals (CI). RESULTS: Spleen palpable, age, and unexplained hemorrhage were identified as the top three effective features affecting CML 5-year survival. The performance of ML models using the selected-features was superior to that of the full-features dataset. Among the eight ML algorithms, SVM (kernel = RBF) had the best performance in tenfold cross-validation with an accuracy of 85.7%, specificity of 85%, sensitivity of 86%, F-measure of 87%, kappa statistic of 86.1%, and area under the curve (AUC) of 85% for the selected-features. Using the full-features dataset yielded an accuracy of 69.7%, specificity of 69.1%, sensitivity of 71.3%, F-measure of 72%, kappa statistic of 75.2%, and AUC of 70.1%. CONCLUSIONS: Accurate prediction of the survival likelihood of CML patients can inform caregivers to promote patient prognostication and choose the best possible treatment path. While external validation is required, our developed models will offer customized treatment and may guide the prescription of personalized medicine for CML patients.

Design, development, and evaluation of a surveillance system for suicidal behaviors in Iran.

BACKGROUND: Suicide is a serious cause of morbidity and mortality in Iran and worldwide. Although several organizations gather information on suicide and suicide attempts, there is substantial misperception regarding the description of the phenomenon. This study proposes the minimum data set (MDS) for suicidal behaviors surveillance. METHODS: A literature review was first conducted to achieve a thorough overview of suicide-related items and map the existing evidence supporting the development of the MDS. The data items included in the literature review were then analyzed using a two-round Delphi technique with content validation by an expert panel. The suicidal behaviors surveillance system was then established based on the confirmed MDS, and ultimately, its performance was assessed by involving the end-users. RESULTS: The panel of experts consisted of 50 experts who participated in the Delphi phase and validity content review. Of these, 46% were men, and their mean age and average work experience were (36.4, SD ± 6.4) and (12.32, SD ± 5.2) years, respectively. The final MDS platform of our study contained 108 items classified into eight main categories. A web-based system with a modular and layered architecture was developed based on the derived MDS. CONCLUSION: The developed system provides a framework for recording suicidal behaviors' data. The integration of multiple suicide-related information systems at the regional and national levels makes it possible to assess the long-term outcomes and evolutions of suicide prevention interventions.

Survey of the patients' perspectives and preferences in adopting telepharmacy versus in-person visits to the pharmacy: a feasibility study during the COVID-19 pandemic.

BACKGROUND: Following the coronavirus disease 2019 (COVID-19) pandemic, the health authorities recommended the implementation of strict social distancing and complete lockdown regulations to reduce disease spread. The pharmacists quickly adopted telemedicine (telepharmacy) as a solution against this crisis, but awareness about this technology is lacking. Therefore, the purpose of this research was to explore the patients' perspectives and preferences regarding telepharmacy instead of traditional in-person visits. METHODS: An electronic questionnaire was designed and sent to 313 patients who were eligible for the study (from March to April 2021). The questionnaire used five-point Likert scales to inquire about motivations for adopting telepharmacy and in-person visits, their perceived advantages and disadvantages, and the declining factors of telepharmacy. Finally, the results were descriptively analyzed using SPSS 22. RESULTS: Of all 313 respondents, a total of 241 (77%) preferred appointments via telepharmacy while 72 (23%) preferred in-person services. There was a significant difference between the selection percentage of telepharmacy and in-person services (chi-square 91.42; p < 0.0001). Preference bout the telepharmacy system versus in-person visits to the pharmacy was associated with factors such as "reducing the incidence of contagious disease" (4.41; ± 0.78), "spending less time receiving pharmaceutical services" (4.24; ± 0.86)), and "traveling a shorter distance for receiving pharmaceutical services" (4.25; ± 0.86). "Reducing costs" (90.87%), "saving time" (89.21%), and "reducing the incidence of contagious disease" (87.13%) were the most important reasons for choosing telepharmacy services. Also, "face-to-face communication with the pharmacist" (25%), "low internet bandwidth" (25%), and "reduction of patients' anxiety and the increase of their peace of mind" (23.61%) were the most important reasons for choosing in-person visits. CONCLUSION: Survey data indicate that most participants are likely to prefer the use of telepharmacy, especially during crises such as the current COVID-19 pandemic. Telepharmacy can be applied as an important means and a crucial service to lessen the load on healthcare organizations and expand drug supply shelters in pharmacies. However, there are still substantial hurdles to overcome in order to successfully implement the telemedicine platform as part of mainstream practice.

Development and evaluation of an electronic nursing documentation system.

BACKGROUND: Nursing documentation is a critical aspect of the nursing care workflow. There is a varying degree in how detailed nursing reports are described in scientific literature and care practice, and no uniform structured documentation is provided. This study aimed to describe the process of designing and evaluating the content of an electronic clinical nursing documentation system (ECNDS) to provide consistent and unified reporting in this context. METHODS: A four-step sequential methodological approach was utilized. The Minimum Data Set (MDS) development process consisted of two phases, as follows: First, a literature review was performed to attain an exhaustive overview of the relevant elements of nursing and map the available evidence underpinning the development of the MDS. Then, the data included from the literature review were analyzed using a two-round Delphi study with content validation by an expert panel. Afterward, the ECNDS was developed according to the finalized MDS, and eventually, its performance was evaluated by involving the end-users. RESULTS: The proposed MDS was divided into administrative and clinical sections; including nursing assessment and the nursing diagnosis process. Then, a web-based system with modular and layered architecture was developed based on the derived MDS. Finally, to evaluate the developed system, a survey of 150 registered nurses (RNs) was conducted to identify the positive and negative impacts of the system. CONCLUSIONS: The developed system is suitable for the documentation of patient care in nursing care plans within a legal, ethical, and professional framework. However, nurses need further training in documenting patient care according to the nursing process, and in using the standard reporting templates to increase patient safety and improve documentation.

Predicting the Need for Intubation among COVID-19 Patients Using Machine Learning Algorithms: A Single-Center Study.

Background: Owing to the shortage of ventilators, there is a crucial demand for an objective and accurate prognosis for 2019 coronavirus disease (COVID-19) critical patients, which may necessitate a mechanical ventilator (MV). This study aimed to construct a predictive model using machine learning (ML) algorithms for frontline clinicians to better triage endangered patients and priorities who would need MV. Methods: In this retrospective single-center study, the data of 482 COVID-19 patients from February 9, 2020, to December 20, 2020, were analyzed by several ML algorithms including, multi-layer perception (MLP), logistic regression (LR), J-48 decision tree, and Naïve Bayes (NB). First, the most important clinical variables were identified using the Chi-square test at P < 0.01. Then, by comparing the ML algorithms' performance using some evaluation criteria, including TP-Rate, FP-Rate, precision, recall, F-Score, MCC, and Kappa, the best performing one was identified. Results: Predictive models were trained using 15 validated features, including cough, contusion, oxygen therapy, dyspnea, loss of taste, rhinorrhea, blood pressure, absolute lymphocyte count, pleural fluid, activated partial thromboplastin time, blood glucose, white cell count, cardiac diseases, length of hospitalization, and other underline diseases. The results indicated the J-48 with F-score = 0.868 and AUC = 0.892 yielded the best performance for predicting intubation requirement. Conclusion: ML algorithms are potentials to improve traditional clinical criteria to forecast the necessity for intubation in COVID-19 in-hospital patients. Such ML-based prediction models may help physicians with optimizing the timing of intubation, better sharing of MV resources and personnel, and increase patient clinical status.

Performance evaluation of selected decision tree algorithms for COVID-19 diagnosis using routine clinical data.

Background: The novel 2019 Coronavirus disease (COVID-19) poses a great threat to global public health and the economy. The earlier detection of COVID-19 is the key to its treatment and mitigating the transmission of the virus. Given that Machine Learning (ML) could be potentially useful in COVID-19 identification, we compared 7 decision tree (DT) algorithms to select the best clinical diagnostic model. Methods: A hospital-based retrospective dataset was used to train the selected DT algorithms. The performance of DT models was measured using performance criteria, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC), and precision-recall curves (PRC). Finally, the best decision model was obtained based on comparing the mentioned performance criteria. Results: Based on the Gini Index (GI) scoring model, 13 diagnostic criteria, including the lung lesion existence (GI= 0217), fever (GI= 0.205), history of contact with suspected people (GI= 0.188), O2 saturation rate in the blood (GI= 0.181), rhinorrhea (GI= 0.177), dyspnea (GI = 0.177), cough (GI = 0.159), history of taking the immunosuppressive drug (GI= 0.145), history of respiratory failure (ARDS) (GI= 0.141), lung lesion situation (GI= 0.133) and appearance (GI= 0.126), diarrhea (GI= 0.112), and nausea and vomiting (GI = 0.092) have been obtained as the most important criteria in diagnosing COVID-19. The results indicated that the J-48, with the accuracy= 0.85, F-Score= 0.85, ROC= 0.926, and PRC= 0.93, had the best performance for diagnosing COVID-19. Conclusion: According to the empirical results, it is promising to implement J-48 in health care settings to increase the accuracy and speed of COVID-19 diagnosis.

Developing a clinical decision support system based on the fuzzy logic and decision tree to predict colorectal cancer.

Background: Colorectal Cancer (CRC) is the most prevalent digestive system- related cancer and has become one of the deadliest diseases worldwide. Given the poor prognosis of CRC, it is of great importance to make a more accurate prediction of this disease. Early CRC detection using computational technologies can significantly improve the overall survival possibility of patients. Hence this study was aimed to develop a fuzzy logic-based clinical decision support system (FL-based CDSS) for the detection of CRC patients. Methods: This study was conducted in 2020 using the data related to CRC and non-CRC patients, which included the 1162 cases in the Masoud internal clinic, Tehran, Iran. The chi-square method was used to determine the most important risk factors in predicting CRC. Furthermore, the C4.5 decision tree was used to extract the rules. Finally, the FL-based CDSS was designed in a MATLAB environment and its performance was evaluated by a confusion matrix. Results: Eleven features were selected as the most important factors. After fuzzification of the qualitative variables and evaluation of the decision support system (DSS) using the confusion matrix, the accuracy, specificity, and sensitivity of the system was yielded 0.96, 0.97, and 0.96, respectively. Conclusion: We concluded that developing the CDSS in this field can provide an earlier diagnosis of CRC, leading to a timely treatment, which could decrease the CRC mortality rate in the community.

Development of minimal basic data set to report COVID-19.

Background: Effective surveillance of COVID-19 highlights the importance of rapid, valid, and standardized information to crisis monitoring and prompts clinical interventions. Minimal basic data set (MBDS) is a set of metrics to be collated in a standard approach to allow aggregated use of data for clinical purposes and research. Data standardization enables accurate comparability of collected data, and accordingly, enhanced generalization of findings. The aim of this study is to establish a core set of data to characterize COVID-19 to consolidate clinical practice. Methods: A 3-step sequential approach was used in this study: (1) an elementary list of data were collected from the existing information systems and data sets; (2) a systematic literature review was conducted to extract evidence supporting the development of MBDS; and (3) a 2-round Delphi survey was done for reaching consensus on data elements to include in COVID-19 MBDS and for its robust validation. Results: In total, 643 studies were identified, of which 38 met the inclusion criteria, where a total of 149 items were identified in the data sources. The data elements were classified by 3 experts and validated via a 2-round Delphi procedure. Finally, 125 data elements were confirmed as the MBDS. Conclusion: The development of COVID-19 MBDS could provide a basis for meaningful evaluations, reporting, and benchmarking COVID-19 disease across regions and countries. It could also provide scientific collaboration for care providers in the field, which may lead to improved quality of documentation, clinical care, and research outcomes.

Design and development of a web-based registry for Coronavirus (COVID-19) disease.

Background: The 2019 coronavirus (COVID-19) is a highly contagious disease associated with a high morbidity and mortality worldwide. The accumulation of data through a prospective clinical registry enables public health authorities to make informed decisions based on real evidence obtained from surveillance of COVID-19. This registry is also fundamental to providing robust infrastructure for future research surveys. The purpose of this study was to design a registry and its minimum data set (MDS), as a valid and reliable data source for reporting and benchmarking COVID-19. Methods: This cross sectional and descriptive study provides a template for the required MDS to be included in COVID-19 registry. This was done by an extensive literature review and 2 round Delphi survey to validate the content, which resulted in a web-based registry created by Visual Studio 2019 and a database designed by Structured Query Language (SQL). Results: The MDS of COVID-19 registry was categorized into the administrative part with 3 sections, including 30 data elements, and the clinical part with 4 sections, including 26 data elements. Furthermore, a web-based registry with modular and layered architecture was designed based on final data classes and elements. Conclusion: To the best of our knowledge, COVID-19 registry is the first designed instrument from information management perspectives in Iran and can become a homogenous and reliable infrastructure for collecting data on COVID-19. We hope this approach will facilitate epidemiological surveys and support policymakers to better plan for monitoring patients with COVID-19.