Hemogram-based decision tree models for discriminating COVID-19 from RSV in infants.

OBJECTIVE: Decision trees are efficient and reliable decision-making algorithms, and medicine has reached its peak of interest in these methods during the current pandemic. Herein, we reported several decision tree algorithms for a rapid discrimination between coronavirus disease (COVID-19) and respiratory syncytial virus (RSV) infection in infants. METHODS: A cross-sectional study was conducted on 77 infants: 33 infants with novel betacoronavirus (SARS-CoV-2) infection and 44 infants with RSV infection. In total, 23 hemogram-based instances were used to construct the decision tree models via 10-fold cross-validation method. RESULTS: The Random forest model showed the highest accuracy (81.8%), while in terms of sensitivity (72.7%), specificity (88.6%), positive predictive value (82.8%), and negative predictive value (81.3%), the optimized forest model was the most superior one. CONCLUSION: Random forest and optimized forest models might have significant clinical applications, helping to speed up decision-making when SARS-CoV-2 and RSV are suspected, prior to molecular genome sequencing and/or antigen testing.

Use of a Cytosponge biomarker panel to prioritise endoscopic Barrett's oesophagus surveillance: a cross-sectional study followed by a real-world prospective pilot.

BACKGROUND: Endoscopic surveillance is recommended for patients with Barrett's oesophagus because, although the progression risk is low, endoscopic intervention is highly effective for high-grade dysplasia and cancer. However, repeated endoscopy has associated harms and access has been limited during the COVID-19 pandemic. We aimed to evaluate the role of a non-endoscopic device (Cytosponge) coupled with laboratory biomarkers and clinical factors to prioritise endoscopy for Barrett's oesophagus. METHODS: We first conducted a retrospective, multicentre, cross-sectional study in patients older than 18 years who were having endoscopic surveillance for Barrett's oesophagus (with intestinal metaplasia confirmed by TFF3 and a minimum Barrett's segment length of 1 cm [circumferential or tongues by the Prague C and M criteria]). All patients had received the Cytosponge and confirmatory endoscopy during the BEST2 (ISRCTN12730505) and BEST3 (ISRCTN68382401) clinical trials, from July 7, 2011, to April 1, 2019 (UK Clinical Research Network Study Portfolio 9461). Participants were divided into training (n=557) and validation (n=334) cohorts to identify optimal risk groups. The biomarkers evaluated were overexpression of p53, cellular atypia, and 17 clinical demographic variables. Endoscopic biopsy diagnosis of high-grade dysplasia or cancer was the primary endpoint. Clinical feasibility of a decision tree for Cytosponge triage was evaluated in a real-world prospective cohort from Aug 27, 2020 (DELTA; ISRCTN91655550; n=223), in response to COVID-19 and the need to provide an alternative to endoscopic surveillance. FINDINGS: The prevalence of high-grade dysplasia or cancer determined by the current gold standard of endoscopic biopsy was 17% (92 of 557 patients) in the training cohort and 10% (35 of 344) in the validation cohort. From the new biomarker analysis, three risk groups were identified: high risk, defined as atypia or p53 overexpression or both on Cytosponge; moderate risk, defined by the presence of a clinical risk factor (age, sex, and segment length); and low risk, defined as Cytosponge-negative and no clinical risk factors. The risk of high-grade dysplasia or intramucosal cancer in the high-risk group was 52% (68 of 132 patients) in the training cohort and 41% (31 of 75) in the validation cohort, compared with 2% (five of 210) and 1% (two of 185) in the low-risk group, respectively. In the real-world setting, Cytosponge results prospectively identified 39 (17%) of 223 patients as high risk (atypia or p53 overexpression, or both) requiring endoscopy, among whom the positive predictive value was 31% (12 of 39 patients) for high-grade dysplasia or intramucosal cancer and 44% (17 of 39) for any grade of dysplasia. INTERPRETATION: Cytosponge atypia, p53 overexpression, and clinical risk factors (age, sex, and segment length) could be used to prioritise patients for endoscopy. Further investigation could validate their use in clinical practice and lead to a substantial reduction in endoscopy procedures compared with current surveillance pathways. FUNDING: Medical Research Council, Cancer Research UK, Innovate UK.

Application of a Decision Tree Model to Predict the Outcome of Non-Intensive Inpatients Hospitalized for COVID-19.

Many studies have identified predictors of outcomes for inpatients with coronavirus disease 2019 (COVID-19), especially in intensive care units. However, most retrospective studies applied regression methods to evaluate the risk of death or worsening health. Recently, new studies have based their conclusions on retrospective studies by applying machine learning methods. This study applied a machine learning method based on decision tree methods to define predictors of outcomes in an internal medicine unit with a prospective study design. The main result was that the first variable to evaluate prediction was the international normalized ratio, a measure related to prothrombin time, followed by immunoglobulin M response. The model allowed the threshold determination for each continuous blood or haematological parameter and drew a path toward the outcome. The model's performance (accuracy, 75.93%; sensitivity, 99.61%; and specificity, 23.43%) was validated with a k-fold repeated cross-validation. The results suggest that a machine learning approach could help clinicians to obtain information that could be useful as an alert for disease progression in patients with COVID-19. Further research should explore the acceptability of these results to physicians in current practice and analyze the impact of machine learning-guided decisions on patient outcomes.

Predictive Analysis of the Pro-Environmental Behaviour of College Students Using a Decision-Tree Model.

The emergence of the COVID-19 pandemic has hindered the achievement of the global Sustainable Development Goals (SDGs). Pro-environmental behaviour contributes to the achievement of the SDGs, and UNESCO considers college students as major contributors. There is a scarcity of research on college student pro-environmental behaviour and even less on the use of decision trees to predict pro-environmental behaviour. Therefore, this study aims to investigate the validity of applying a modified C5.0 decision-tree model to predict college student pro-environmental behaviour and to determine which variables can be used as predictors of such behaviour. To address these questions, 334 university students in Guangdong Province, China, completed a questionnaire that consisted of seven parts: the Perceived Behavioural Control Scale, the Social Identity Scale, the Innovative Behaviour Scale, the Sense of Place Scale, the Subjective Norms Scale, the Environmental Activism Scale, and the willingness to behave in an environmentally responsible manner scale. A modified C5.0 decision-tree model was also used to make predictions. The results showed that the main predictor variables for pro-environmental behaviour were willingness to behave in an environmentally responsible manner, innovative behaviour, and perceived behavioural control. The importance of willingness to behave in an environmentally responsible manner was 0.1562, the importance of innovative behaviour was 0.1404, and the perceived behavioural control was 0.1322. Secondly, there are 63.88% of those with high pro-environmental behaviour. Therefore, we conclude that the decision tree model is valid in predicting the pro-environmental behaviour of college student. The predictor variables for pro-environmental behaviour were, in order of importance: Willingness to behave in an environmentally responsible manner, Environmental Activism, Subjective Norms, Sense of Place, Innovative Behaviour, Social Identity, and Perceived Behavioural Control. This study establishes a link between machine learning and pro-environmental behaviour and broadens understanding of pro-environmental behaviour. It provides a research support with improving people's sustainable development philosophy and behaviour.

Application of machine learning models based on decision trees in classifying the factors affecting mortality of COVID-19 patients in Hamadan, Iran.

BACKGROUND: Due to the high mortality of COVID-19 patients, the use of a high-precision classification model of patient's mortality that is also interpretable, could help reduce mortality and take appropriate action urgently. In this study, the random forest method was used to select the effective features in COVID-19 mortality and the classification was performed using logistic model tree (LMT), classification and regression tree (CART), C4.5, and C5.0 tree based on important features. METHODS: In this retrospective study, the data of 2470 COVID-19 patients admitted to hospitals in Hamadan, west Iran, were used, of which 75.02% recovered and 24.98% died. To classify, at first among the 25 demographic, clinical, and laboratory findings, features with a relative importance more than 6% were selected by random forest. Then LMT, C4.5, C5.0, and CART trees were developed and the accuracy of classification performance was evaluated with recall, accuracy, and F1-score criteria for training, test, and total datasets. At last, the best tree was developed and the receiver operating characteristic curve and area under the curve (AUC) value were reported. RESULTS: The results of this study showed that among demographic and clinical features gender and age, and among laboratory findings blood urea nitrogen, partial thromboplastin time, serum glutamic-oxaloacetic transaminase, and erythrocyte sedimentation rate had more than 6% relative importance. Developing the trees using the above features revealed that the CART with the values of F1-score, Accuracy, and Recall, 0.8681, 0.7824, and 0.955, respectively, for the test dataset and 0.8667, 0.7834, and 0.9385, respectively, for the total dataset had the best performance. The AUC value obtained for the CART was 79.5%. CONCLUSIONS: Finding a highly accurate and qualified model for interpreting the classification of a response that is considered clinically consequential is critical at all stages, including treatment and immediate decision making. In this study, the CART with its high accuracy for diagnosing and classifying mortality of COVID-19 patients as well as prioritizing important demographic, clinical, and laboratory findings in an interpretable format, risk factors for prognosis of COVID-19 patients mortality identify and enable immediate and appropriate decisions for health professionals and physicians.

An open-access database of infectious disease transmission trees to explore superspreader epidemiology.

Historically, emerging and reemerging infectious diseases have caused large, deadly, and expensive multinational outbreaks. Often outbreak investigations aim to identify who infected whom by reconstructing the outbreak transmission tree, which visualizes transmission between individuals as a network with nodes representing individuals and branches representing transmission from person to person. We compiled a database, called OutbreakTrees, of 382 published, standardized transmission trees consisting of 16 directly transmitted diseases ranging in size from 2 to 286 cases. For each tree and disease, we calculated several key statistics, such as tree size, average number of secondary infections, the dispersion parameter, and the proportion of cases considered superspreaders, and examined how these statistics varied over the course of each outbreak and under different assumptions about the completeness of outbreak investigations. We demonstrated the potential utility of the database through 2 short analyses addressing questions about superspreader epidemiology for a variety of diseases, including Coronavirus Disease 2019 (COVID-19). First, we found that our transmission trees were consistent with theory predicting that intermediate dispersion parameters give rise to the highest proportion of cases causing superspreading events. Additionally, we investigated patterns in how superspreaders are infected. Across trees with more than 1 superspreader, we found preliminary support for the theory that superspreaders generate other superspreaders. In sum, our findings put the role of superspreading in COVID-19 transmission in perspective with that of other diseases and suggest an approach to further research regarding the generation of superspreaders. These data have been made openly available to encourage reuse and further scientific inquiry.

Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU.

BACKGROUND: Coronavirus disease-19 (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and is currently a major cause of intensive care unit (ICU) admissions globally. The role of machine learning in the ICU is evolving but currently limited to diagnostic and prognostic values. A decision tree (DT) algorithm is a simple and intuitive machine learning method that provides sequential nonlinear analysis of variables. It is simple and might be a valuable tool for bedside physicians during COVID-19 to predict ICU outcomes and help in critical decision-making like end-of-life decisions and bed allocation in the event of limited ICU bed capacities. Herein, we utilized a machine learning DT algorithm to describe the association of a predefined set of variables and 28-day ICU outcome in adult COVID-19 patients admitted to the ICU. We highlight the value of utilizing a machine learning DT algorithm in the ICU at the time of a COVID-19 pandemic. METHODS: This was a prospective and multicenter cohort study involving 14 hospitals in Saudi Arabia. We included critically ill COVID-19 patients admitted to the ICU between March 1, 2020, and October 31, 2020. The predictors of 28-day ICU mortality were identified using two predictive models: conventional logistic regression and DT analyses. RESULTS: There were 1468 critically ill COVID-19 patients included in the study. The 28-day ICU mortality was 540 (36.8 %), and the 90-day mortality was 600 (40.9 %). The DT algorithm identified five variables that were integrated into the algorithm to predict 28-day ICU outcomes: need for intubation, need for vasopressors, age, gender, and PaO2/FiO2 ratio. CONCLUSION: DT is a simple tool that might be utilized in the ICU to identify critically ill COVID-19 patients who are at high risk of 28-day ICU mortality. However, further studies and external validation are still required.

Predicting the Risk Factors Associated With Severe Outcomes Among COVID-19 Patients-Decision Tree Modeling Approach.

Background: The COVID-19 pandemic has seen a large surge in case numbers over several waves, and has critically strained the health care system, with a significant number of cases requiring hospitalization and ICU admission. This study used a decision tree modeling approach to identify the most important predictors of severe outcomes among COVID-19 patients. Methods: We identified a retrospective population-based cohort (n = 140,182) of adults who tested positive for COVID-19 between 5th March 2020 and 31st May 2021. Demographic information, symptoms and co-morbidities were extracted from a communicable disease and outbreak management information system and electronic medical records. Decision tree modeling involving conditional inference tree and random forest models were used to analyze and identify the key factors(s) associated with severe outcomes (hospitalization, ICU admission and death) following COVID-19 infection. Results: In the study cohort, nearly 6.37% were hospitalized, 1.39% were admitted to ICU and 1.57% died due to COVID-19. Older age (>71Y) and breathing difficulties were the top two factors associated with a poor prognosis, predicting about 50% of severe outcomes in both models. Neurological conditions, diabetes, cardiovascular disease, hypertension, and renal disease were the top five pre-existing conditions that altogether predicted 29% of outcomes. 79% of the cases with poor prognosis were predicted based on the combination of variables. Age stratified models revealed that among younger adults (18-40 Y), obesity was among the top risk factors associated with adverse outcomes. Conclusion: Decision tree modeling has identified key factors associated with a significant proportion of severe outcomes in COVID-19. Knowledge about these variables will aid in identifying high-risk groups and allocating health care resources.

Healthcare costs and mortality associated with serious fluoroquinolone-related adverse reactions.

The aim of this study was to estimate healthcare costs and mortality associated with serious fluoroquinolone-related adverse reactions in Finland from 2008 to 2019. Serious adverse reaction types were identified from the Finnish Pharmaceutical Insurance Pool's pharmaceutical injury claims and the Finnish Medicines Agency's Adverse Reaction Register. A decision tree model was built to predict costs and mortality associated with serious adverse drug reactions (ADR). Severe clostridioides difficile infections, severe cutaneous adverse reactions, tendon ruptures, aortic ruptures, and liver injuries were included as serious adverse drug reactions in the model. Direct healthcare costs of a serious ADR were based on the number of reimbursed fluoroquinolone prescriptions from the Social Insurance Institution of Finland's database. Sensitivity analyses were conducted to address parameter uncertainty. A total of 1 831 537 fluoroquinolone prescriptions were filled between 2008 and 2019 in Finland, with prescription numbers declining 40% in recent years. Serious ADRs associated with fluoroquinolones lead to estimated direct healthcare costs of 501 938 402 €, including 11 405 ADRs and 3,884 deaths between 2008 and 2019. The average mortality risk associated with the use of fluoroquinolones was 0.21%. Severe clostridioides difficile infections were the most frequent, fatal, and costly serious ADRs associated with the use of fluoroquinolones. Although fluoroquinolones continue to be generally well-tolerated antimicrobials, serious adverse reactions cause long-term impairment to patients and high healthcare costs. Therefore, the risks and benefits should be weighed carefully in antibiotic prescription policies, as well as with individual patients.

Risk stratification for COVID-19 hospitalization: a multivariable model based on gradient-boosting decision trees.

BACKGROUND: The COVID-19 pandemic has led to an increased demand for health care resources and, in some cases, shortage of medical equipment and staff. Our objective was to develop and validate a multivariable model to predict risk of hospitalization for patients infected with SARS-CoV-2. METHODS: We used routinely collected health records in a patient cohort to develop and validate our prediction model. This cohort included adult patients (age ≥ 18 yr) from Ontario, Canada, who tested positive for SARS-CoV-2 ribonucleic acid by polymerase chain reaction between Feb. 2 and Oct. 5, 2020, and were followed up through Nov. 5, 2020. Patients living in long-term care facilities were excluded, as they were all assumed to be at high risk of hospitalization for COVID-19. Risk of hospitalization within 30 days of diagnosis of SARS-CoV-2 infection was estimated via gradient-boosting decision trees, and variable importance examined via Shapley values. We built a gradient-boosting model using the Extreme Gradient Boosting (XGBoost) algorithm and compared its performance against 4 empirical rules commonly used for risk stratifications based on age and number of comorbidities. RESULTS: The cohort included 36 323 patients with 2583 hospitalizations (7.1%). Hospitalized patients had a higher median age (64 yr v. 43 yr), were more likely to be male (56.3% v. 47.3%) and had a higher median number of comorbidities (3, interquartile range [IQR] 2-6 v. 1, IQR 0-3) than nonhospitalized patients. Patients were split into development (n = 29 058, 80.0%) and held-out validation (n = 7265, 20.0%) cohorts. The gradient-boosting model achieved high discrimination (development cohort: area under the receiver operating characteristic curve across the 5 folds of 0.852; validation cohort: 0.8475) and strong calibration (slope = 1.01, intercept = -0.01). The patients who scored at the top 10% captured 47.4% of hospitalizations, and those who scored at the top 30% captured 80.6%. INTERPRETATION: We developed and validated an accurate risk stratification model using routinely collected health administrative data. We envision that modelling such risk stratification based on routinely collected health data could support management of COVID-19 on a population health level.

Clinical prediction rule for SARS-CoV-2 infection from 116 U.S. emergency departments 2-22-2021.

OBJECTIVES: Accurate and reliable criteria to rapidly estimate the probability of infection with the novel coronavirus-2 that causes the severe acute respiratory syndrome (SARS-CoV-2) and associated disease (COVID-19) remain an urgent unmet need, especially in emergency care. The objective was to derive and validate a clinical prediction score for SARS-CoV-2 infection that uses simple criteria widely available at the point of care. METHODS: Data came from the registry data from the national REgistry of suspected COVID-19 in EmeRgency care (RECOVER network) comprising 116 hospitals from 25 states in the US. Clinical variables and 30-day outcomes were abstracted from medical records of 19,850 emergency department (ED) patients tested for SARS-CoV-2. The criterion standard for diagnosis of SARS-CoV-2 required a positive molecular test from a swabbed sample or positive antibody testing within 30 days. The prediction score was derived from a 50% random sample (n = 9,925) using unadjusted analysis of 107 candidate variables as a screening step, followed by stepwise forward logistic regression on 72 variables. RESULTS: Multivariable regression yielded a 13-variable score, which was simplified to a 13-point score: +1 point each for age>50 years, measured temperature>37.5°C, oxygen saturation<95%, Black race, Hispanic or Latino ethnicity, household contact with known or suspected COVID-19, patient reported history of dry cough, anosmia/dysgeusia, myalgias or fever; and -1 point each for White race, no direct contact with infected person, or smoking. In the validation sample (n = 9,975), the probability from logistic regression score produced an area under the receiver operating characteristic curve of 0.80 (95% CI: 0.79-0.81), and this level of accuracy was retained across patients enrolled from the early spring to summer of 2020. In the simplified score, a score of zero produced a sensitivity of 95.6% (94.8-96.3%), specificity of 20.0% (19.0-21.0%), negative likelihood ratio of 0.22 (0.19-0.26). Increasing points on the simplified score predicted higher probability of infection (e.g., >75% probability with +5 or more points). CONCLUSION: Criteria that are available at the point of care can accurately predict the probability of SARS-CoV-2 infection. These criteria could assist with decisions about isolation and testing at high throughput checkpoints.

Detection of Fake News Text Classification on COVID-19 Using Deep Learning Approaches.

A vast amount of data is generated every second for microblogs, content sharing via social media sites, and social networking. Twitter is an essential popular microblog where people voice their opinions about daily issues. Recently, analyzing these opinions is the primary concern of Sentiment analysis or opinion mining. Efficiently capturing, gathering, and analyzing sentiments have been challenging for researchers. To deal with these challenges, in this research work, we propose a highly accurate approach for SA of fake news on COVID-19. The fake news dataset contains fake news on COVID-19; we started by data preprocessing (replace the missing value, noise removal, tokenization, and stemming). We applied a semantic model with term frequency and inverse document frequency weighting for data representation. In the measuring and evaluation step, we applied eight machine-learning algorithms such as Naive Bayesian, Adaboost, K-nearest neighbors, random forest, logistic regression, decision tree, neural networks, and support vector machine and four deep learning CNN, LSTM, RNN, and GRU. Afterward, based on the results, we boiled a highly efficient prediction model with python, and we trained and evaluated the classification model according to the performance measures (confusion matrix, classification rate, true positives rate...), then tested the model on a set of unclassified fake news on COVID-19, to predict the sentiment class of each fake news on COVID-19. Obtained results demonstrate a high accuracy compared to the other models. Finally, a set of recommendations is provided with future directions for this research to help researchers select an efficient sentiment analysis model on Twitter data.

Mobilization of Resources and Emergency Response on the National Scale.

Mass casualty incidents are increasingly common. They are defined by large numbers of patients arriving nearly simultaneously, overwhelming available resources needed for optimal care. They require rapid mobilization of resources to provide optimal outcomes and limit disability and death. Because the mechanism of injury in a mass casualty incident is often traumatic in nature, surgeons should be aware of the critical role they play in planning and response. The coronavirus disease 2019 pandemic is a notable, resulting in a sustained surge of critically ill patients. Initial response requires local mobilization of resources; large-scale events potentially require a national response.

Using machine learning to create a decision tree model to predict outcomes of COVID-19 cases in the Philippines.

OBJECTIVE: The aim of this study was to create a decision tree model with machine learning to predict the outcomes of COVID-19 cases from data publicly available in the Philippine Department of Health (DOH) COVID Data Drop. METHODS: The study design was a cross-sectional records review of the DOH COVID Data Drop for 25 August 2020. Resolved cases that had either recovered or died were used as the final data set. Machine learning processes were used to generate, train and validate a decision tree model. RESULTS: A list of 132 939 resolved COVID-19 cases was used. The notification rates and case fatality rates were higher among males (145.67 per 100 000 and 2.46%, respectively). Most COVID-19 cases were clustered among people of working age, and older cases had higher case fatality rates. The majority of cases were from the National Capital Region (590.20 per 100 000), and the highest case fatality rate (5.83%) was observed in Region VII. The decision tree model prioritized age and history of hospital admission as predictors of mortality. The model had high accuracy (81.42%), sensitivity (81.65%), specificity (81.41%) and area under the curve (0.876) but a poor F-score (16.74%). DISCUSSION: The model predicted higher case fatality rates among older people. For cases aged > 51 years, a history of hospital admission increased the probability of COVID-19-related death. We recommend that more comprehensive primary COVID-19 data sets be used to create more robust prognostic models.

Prediction of diagnosis and prognosis of COVID-19 disease by blood gas parameters using decision trees machine learning model: a retrospective observational study.

The coronavirus disease 2019 (COVID-19) epidemic went down in history as a pandemic caused by corona-viruses that emerged in 2019 and spread rapidly around the world. The different symptoms of COVID-19 made it difficult to understand which variables were more influential on the diagnosis, course and mortality of the disease. Machine learning models can accurately assess hidden patterns among risk factors by analyzing large-datasets to quickly predict diagnosis, prognosis and mortality of diseases. Because of this advantage, the use of machine learning models as decision support systems in health services is increasing. The aim of this study is to determine the diagnosis and prognosis of COVID-19 disease with blood-gas data using the Chi-squared Automatic Interaction Detector (CHAID) decision-tree-model, one of the machine learning methods, which is a subfield of artificial intelligence. This study was carried out on a total of 686 patients with COVID-19 (n = 343) and non-COVID-19 (n = 343) treated at Erzincan-Mengücek-Gazi-Training and Research-Hospital between April 1, 2020 and March 1, 2021. Arterial blood gas values of all patients were obtained from the hospital registry system. While the total-accuracyratio of the decision-tree-model was 65.0% in predicting the prognosis of the disease, it was 68.2% in the diagnosis of the disease. According to the results obtained, the low ionized-calcium value (< 1.10 mM) significantly predicted the need for intensive care of COVID-19 patients. At admission, low-carboxyhemoglobin (< 1.00%), high-pH (> 7.43), low-sodium (< 135.0 mM), hematocrit (< 40.0%), and methemoglobin (< 1.30%) values are important biomarkers in the diagnosis of COVID-19 and the results were promising. The findings in the study may aid in the early-diagnosis of the disease and the intensive-care treatment of patients who are severe. The study was approved by the Ministry of Health and Erzincan University Faculty of Medicine Clinical Research Ethics Committee.

Fast Outcome Categorization of the Upper Limb After Stroke.

BACKGROUND AND PURPOSE: The ARAT (Action Research Arm Test) has been used to classify upper limb motor outcome after stroke in 1 of 3, 4, or 5 categories. The COVID-19 pandemic has encouraged the development of assessments that can be performed quickly and remotely. The aim of this study was to derive and internally validate decision trees for categorizing upper limb motor outcomes at the late subacute and chronic stages of stroke using a subset of ARAT tasks. METHODS: This study retrospectively analyzed ARAT scores obtained in-person at 3 months poststroke from 333 patients. In-person ARAT scores were used to categorize patients' 3-month upper limb outcome using classification systems with 3, 4, and 5 outcome categories. Individual task scores from in-person assessments were then used in classification and regression tree analyses to determine subsets of tasks that could accurately categorize upper limb outcome for each of the 3 classification systems. The decision trees developed using 3-month ARAT data were also applied to in-person ARAT data obtained from 157 patients at 6 months poststroke. RESULTS: The classification and regression tree analyses produced decision trees requiring 2 to 4 ARAT tasks. The overall accuracy of the cross-validated decision trees ranged from 87.7% (SE, 1.0%) to 96.7% (SE, 2.0%). Accuracy was highest when classifying patients into one of 3 outcome categories and lowest for 5 categories. The decision trees are referred to as FOCUS (Fast Outcome Categorization of the Upper Limb After Stroke) assessments and they remained accurate for 6-month poststroke ARAT scores (overall accuracy range 83.4%-91.7%). CONCLUSIONS: A subset of ARAT tasks can accurately categorize upper limb motor outcomes after stroke. Future studies could investigate the feasibility and accuracy of categorizing outcomes using the FOCUS assessments remotely via video call.

Clinical characteristics and a decision tree model to predict death outcome in severe COVID-19 patients.

BACKGROUND: The novel coronavirus disease 2019 (COVID-19) spreads rapidly among people and causes a pandemic. It is of great clinical significance to identify COVID-19 patients with high risk of death. METHODS: A total of 2169 adult COVID-19 patients were enrolled from Wuhan, China, from February 10th to April 15th, 2020. Difference analyses of medical records were performed between severe and non-severe groups, as well as between survivors and non-survivors. In addition, we developed a decision tree model to predict death outcome in severe patients. RESULTS: Of the 2169 COVID-19 patients, the median age was 61 years and male patients accounted for 48%. A total of 646 patients were diagnosed as severe illness, and 75 patients died. An older median age and a higher proportion of male patients were found in severe group or non-survivors compared to their counterparts. Significant differences in clinical characteristics and laboratory examinations were found between severe and non-severe groups, as well as between survivors and non-survivors. A decision tree, including three biomarkers, neutrophil-to-lymphocyte ratio, C-reactive protein and lactic dehydrogenase, was developed to predict death outcome in severe patients. This model performed well both in training and test datasets. The accuracy of this model were 0.98 in both datasets. CONCLUSION: We performed a comprehensive analysis of COVID-19 patients from the outbreak in Wuhan, China, and proposed a simple and clinically operable decision tree to help clinicians rapidly identify COVID-19 patients at high risk of death, to whom priority treatment and intensive care should be given.

Application of Data Mining Algorithms for Dementia in People with HIV/AIDS.

Dementia interferes with the individual's motor, behavioural, and intellectual functions, causing him to be unable to perform instrumental activities of daily living. This study is aimed at identifying the best performing algorithm and the most relevant characteristics to categorise individuals with HIV/AIDS at high risk of dementia from the application of data mining. Principal component analysis (PCA) algorithm was used and tested comparatively between the following machine learning algorithms: logistic regression, decision tree, neural network, KNN, and random forest. The database used for this study was built from the data collection of 270 individuals infected with HIV/AIDS and followed up at the outpatient clinic of a reference hospital for infectious and parasitic diseases in the State of Ceará, Brazil, from January to April 2019. Also, the performance of the algorithms was analysed for the 104 characteristics available in the database; then, with the reduction of dimensionality, there was an improvement in the quality of the machine learning algorithms and identified that during the tests, even losing about 30% of the variation. Besides, when considering only 23 characteristics, the precision of the algorithms was 86% in random forest, 56% logistic regression, 68% decision tree, 60% KNN, and 59% neural network. The random forest algorithm proved to be more effective than the others, obtaining 84% precision and 86% accuracy.

Risk of missing colorectal cancer with a COVID-adapted diagnostic pathway using quantitative faecal immunochemical testing.

BACKGROUND: COVID-19 has brought an unprecedented challenge to healthcare services. The authors' COVID-adapted pathway for suspected bowel cancer combines two quantitative faecal immunochemical tests (qFITs) with a standard CT scan with oral preparation (CT mini-prep). The aim of this study was to estimate the degree of risk mitigation and residual risk of undiagnosed colorectal cancer. METHOD: Decision-tree models were developed using a combination of data from the COVID-adapted pathway (April-May 2020), a local audit of qFIT for symptomatic patients performed since 2018, relevant data (prevalence of colorectal cancer and sensitivity and specificity of diagnostic tools) obtained from literature and a local cancer data set, and expert opinion for any missing data. The considered diagnostic scenarios included: single qFIT; two qFITs; single qFIT and CT mini-prep; two qFITs and CT mini-prep (enriched pathway). These were compared to the standard diagnostic pathway (colonoscopy or CT virtual colonoscopy (CTVC)). RESULTS: The COVID-adapted pathway included 422 patients, whereas the audit of qFIT included more than 5000 patients. The risk of missing a colorectal cancer, if present, was estimated as high as 20.2 per cent with use of a single qFIT as a triage test. Using both a second qFIT and a CT mini-prep as add-on tests reduced the risk of missed cancer to 6.49 per cent. The trade-off was an increased rate of colonoscopy or CTVC, from 287 for a single qFIT to 418 for the double qFIT and CT mini-prep combination, per 1000 patients. CONCLUSION: Triage using qFIT alone could lead to a high rate of missed cancers. This may be reduced using CT mini-prep as an add-on test for triage to colonoscopy or CTVC.

Laboratory Predictors of COVID-19 Pneumonia in Patients with Mild to Moderate Symptoms.

OBJECTIVE: This research aims to develop a laboratory model that can accurately distinguish pneumonia from nonpneumonia in patients with COVID-19 and to identify potential protective factors against lung infection. METHODS: We recruited 50 patients diagnosed with COVID-19 infection with or without pneumonia. We selected candidate predictors through group comparison and punitive least absolute shrinkage and selection operator (LASSO) analysis. A stepwise logistic regression model was used to distinguish patients with and without pneumonia. Finally, we used a decision-tree method and randomly selected 50% of the patients 1000 times from the same specimen to verify the effectiveness of the model. RESULTS: We found that the percentage of eosinophils, a high-fluorescence-reticulocyte ratio, and creatinine had better discriminatory power than other factors. Age and underlying diseases were not significant for discrimination. The model correctly discriminated 77.1% of patients. In the final validation step, we observed that the model had an overall predictive rate of 81.3%. CONCLUSION: We developed a laboratory model for COVID-19 pneumonia in patients with mild to moderate symptoms. In the clinical setting, the model will be able to predict and differentiate pneumonia vs nonpneumonia before any lung computed tomography findings. In addition, the percentage of eosinophils, a high-fluorescence-reticulocyte ratio, and creatinine were considered protective factors against lung infection in patients without pneumonia.