Home monitoring with connected mobile devices for asthma attack prediction with machine learning.

Monitoring asthma is essential for self-management. However, traditional monitoring methods require high levels of active engagement, and some patients may find this tedious. Passive monitoring with mobile-health devices, especially when combined with machine-learning, provides an avenue to reduce management burden. Data for developing machine-learning algorithms are scarce, and gathering new data is expensive. A few datasets, such as the Asthma Mobile Health Study, are publicly available, but they only consist of self-reported diaries and lack any objective and passively collected data. To fill this gap, we carried out a 2-phase, 7-month AAMOS-00 observational study to monitor asthma using three smart-monitoring devices (smart-peak-flow-meter/smart-inhaler/smartwatch), and daily symptom questionnaires. Combined with localised weather, pollen, and air-quality reports, we collected a rich longitudinal dataset to explore the feasibility of passive monitoring and asthma attack prediction. This valuable anonymised dataset for phase-2 of the study (device monitoring) has been made publicly available. Between June-2021 and June-2022, in the midst of UK's COVID-19 lockdowns, 22 participants across the UK provided 2,054 unique patient-days of data.

Machine learning and artificial intelligence for the diagnosis of infectious diseases in immunocompromised patients.

PURPOSE OF REVIEW: Immunocompromised patients are at high risk for infection. During the coronavirus disease (COVID-19) pandemic, immunocompromised patients exhibited increased odds of intensive care unit admission and death. Early pathogen identification is essential to mitigating infection related risk in immunocompromised patients. Artificial intelligence (AI) and machine learning (ML) have tremendous appeal to address unmet diagnostic needs. These AI/ML tools often rely on the wealth of data found in healthcare to enhance our ability to identify clinically significant patterns of disease. To this end, our review provides an overview of the current AI/ML landscape as it applies to infectious disease testing with emphasis on immunocompromised patients. RECENT FINDINGS: Examples include AI/ML for predicting sepsis in high risk burn patients. Likewise, ML is utilized to analyze complex host-response proteomic data to predict respiratory infections including COVID-19. These same approaches have also been applied for pathogen identification of bacteria, viruses, and hard to detect fungal microbes. Future uses of AI/ML may include integration of predictive analytics in point-of-care (POC) testing and data fusion applications. SUMMARY: Immunocompromised patients are at high risk for infections. AI/ML is transforming infectious disease testing and has great potential to address challenges encountered in the immune compromised population.

Learning without forgetting by leveraging transfer learning for detecting COVID-19 infection from CT images.

COVID-19, a global pandemic, has killed thousands in the last three years. Pathogenic laboratory testing is the gold standard but has a high false-negative rate, making alternate diagnostic procedures necessary to fight against it. Computer Tomography (CT) scans help diagnose and monitor COVID-19, especially in severe cases. But, visual inspection of CT images takes time and effort. In this study, we employ Convolution Neural Network (CNN) to detect coronavirus infection from CT images. The proposed study utilized transfer learning on the three pre-trained deep CNN models, namely VGG-16, ResNet, and wide ResNet, to diagnose and detect COVID-19 infection from the CT images. However, when the pre-trained models are retrained, the model suffers the generalization capability to categorize the data in the original datasets. The novel aspect of this work is the integration of deep CNN architectures with Learning without Forgetting (LwF) to enhance the model's generalization capabilities on both trained and new data samples. The LwF makes the network use its learning capabilities in training on the new dataset while preserving the original competencies. The deep CNN models with the LwF model are evaluated on original images and CT scans of individuals infected with Delta-variant of the SARS-CoV-2 virus. The experimental results show that of the three fine-tuned CNN models with the LwF method, the wide ResNet model's performance is superior and effective in classifying original and delta-variant datasets with an accuracy of 93.08% and 92.32%, respectively.

Using Machine Learning Algorithms to Determine the Post-COVID State of a Person by Their Rhythmogram.

This study introduces a novel method for detecting the post-COVID state using ECG data. By leveraging a convolutional neural network, we identify "cardiospikes" present in the ECG data of individuals who have experienced a COVID-19 infection. With a test sample, we achieve an 87 percent accuracy in detecting these cardiospikes. Importantly, our research demonstrates that these observed cardiospikes are not artifacts of hardware-software signal distortions, but rather possess an inherent nature, indicating their potential as markers for COVID-specific modes of heart rhythm regulation. Additionally, we conduct blood parameter measurements on recovered COVID-19 patients and construct corresponding profiles. These findings contribute to the field of remote screening using mobile devices and heart rate telemetry for diagnosing and monitoring COVID-19.

Analysis and Prediction of COVID-19 Multivariate Data Using Deep Ensemble Learning Methods.

The global economy has suffered losses as a result of the COVID-19 epidemic. Accurate and effective predictive models are necessary for the governance and readiness of the healthcare system and its resources and, ultimately, for the prevention of the spread of illness. The primary objective of the project is to build a robust, universal method for predicting COVID-19-positive cases. Collaborators will benefit from this while developing and revising their pandemic response plans. For accurate prediction of the spread of COVID-19, the research recommends an adaptive gradient LSTM model (AGLSTM) using multivariate time series data. RNN, LSTM, LASSO regression, Ada-Boost, Light Gradient Boosting and KNN models are also used in the research, which accurately and reliably predict the course of this unpleasant disease. The proposed technique is evaluated under two different experimental conditions. The former uses case studies from India to validate the methodology, while the latter uses data fusion and transfer-learning techniques to reuse data and models to predict the onset of COVID-19. The model extracts important advanced features that influence the COVID-19 cases using a convolutional neural network and predicts the cases using adaptive LSTM after CNN processes the data. The experiment results show that the output of AGLSTM outperforms with an accuracy of 99.81% and requires only a short time for training and prediction.

Using Shapes of COVID-19 Positive Patient-Specific Trajectories for Mortality Prediction.

Machine learning can be used to identify relevant trajectory shape features for improved predictive risk modeling, which can help inform decisions for individualized patient management in intensive care during COVID-19 outbreaks. We present explainable random forests to dynamically predict next day mortality risk in COVID -19 positive and negative patients admitted to the Mount Sinai Health System between March 1st and June 8th, 2020 using patient time-series data of vitals, blood and other laboratory measurements from the previous 7 days. Three different models were assessed by using time series with: 1) most recent patient measurements, 2) summary statistics of trajectories (min/max/median/first/last/count), and 3) coefficients of fitted cubic splines to trajectories. AUROC and AUPRC with cross-validation were used to compare models. We found that the second and third models performed statistically significantly better than the first model. Model interpretations are provided at patient-specific level to inform resource allocation and patient care.

Machine Learning Model for Computer-Aided Depression Screening among Young Adults Using Wireless EEG Headset.

Depression is a disorder that if not treated can hamper the quality of life. EEG has shown great promise in detecting depressed individuals from depression control individuals. It overcomes the limitations of traditional questionnaire-based methods. In this study, a machine learning-based method for detecting depression among young adults using EEG data recorded by the wireless headset is proposed. For this reason, EEG data has been recorded using an Emotiv Epoc+ headset. A total of 32 young adults participated and the PHQ9 screening tool was used to identify depressed participants. Features such as skewness, kurtosis, variance, Hjorth parameters, Shannon entropy, and Log energy entropy from 1 to 5 sec data filtered at different band frequencies were applied to KNN and SVM classifiers with different kernels. At AB band (8-30 Hz) frequency, 98.43 ± 0.15% accuracy was achieved by extracting Hjorth parameters, Shannon entropy, and Log energy entropy from 5 sec samples with a 5-fold CV using a KNN classifier. And with the same features and classifier overall accuracy = 98.10 ± 0.11, NPV = 0.977, precision = 0.984, sensitivity = 0.984, specificity = 0.976, and F1 score = 0.984 was achieved after splitting the data to 70/30 ratio for training and testing with 5-fold CV. From the findings, it can be concluded that EEG data from an Emotiv headset can be used to detect depression with the proposed method.

Predicting missed health care visits during the COVID-19 pandemic using machine learning methods: evidence from 55,500 individuals from 28 European countries.

BACKGROUND: Pandemics such as the COVID-19 pandemic and other severe health care disruptions endanger individuals to miss essential care. Machine learning models that predict which patients are at greatest risk of missing care visits can help health administrators prioritize retentions efforts towards patients with the most need. Such approaches may be especially useful for efficiently targeting interventions for health systems overburdened during states of emergency. METHODS: We use data on missed health care visits from over 55,500 respondents of the Survey of Health, Ageing and Retirement in Europe (SHARE) COVID-19 surveys (June - August 2020 and June - August 2021) with longitudinal data from waves 1-8 (April 2004 - March 2020). We compare the performance of four machine learning algorithms (stepwise selection, lasso, random forest, and neural networks) to predict missed health care visits during the first COVID-19 survey based on common patient characteristics available to most health care providers. We test the prediction accuracy, sensitivity, and specificity of the selected models for the first COVID-19 survey by employing 5-fold cross-validation, and test the out-of-sample performance of the models by applying them to the data from the second COVID-19 survey. RESULTS: Within our sample, 15.5% of the respondents reported any missed essential health care visit due to the COVID-19 pandemic. All four machine learning methods perform similarly in their predictive power. All models have an area under the curve (AUC) of around 0.61, outperforming random prediction. This performance is sustained for data from the second COVID-19 wave one year later, with an AUC of 0.59 for men and 0.61 for women. When classifying all men (women) with a predicted risk of 0.135 (0.170) or higher as being at risk of missing care, the neural network model correctly identifies 59% (58%) of the individuals with missed care visits, and 57% (58%) of the individuals without missed care visits. As the sensitivity and specificity of the models are strongly related to the risk threshold used to classify individuals, the models can be calibrated depending on users' resource constraints and targeting approach. CONCLUSIONS: Pandemics such as COVID-19 require rapid and efficient responses to reduce disruptions in health care. Based on characteristics available to health administrators or insurance providers, simple machine learning algorithms can be used to efficiently target efforts to reduce missed essential care.

IoMT Meets Machine Learning: From Edge to Cloud Chronic Diseases Diagnosis System.

In conventional healthcare, real-time monitoring of patient records and information mining for timely diagnosis of chronic diseases under certain health conditions is a crucial process. Chronic diseases, if not diagnosed in time, may result in patients' death. In modern medical and healthcare systems, Internet of Things (IoT) driven ecosystems use autonomous sensors to sense and track patients' medical conditions and suggest appropriate actions. In this paper, a novel IoT and machine learning (ML)-based hybrid approach is proposed that considers multiple perspectives for early detection and monitoring of 6 different chronic diseases such as COVID-19, pneumonia, diabetes, heart disease, brain tumor, and Alzheimer's. The results from multiple ML models are compared for accuracy, precision, recall, F1 score, and area under the curve (AUC) as a performance measure. The proposed approach is validated in the cloud-based environment using benchmark and real-world datasets. The statistical analyses on the datasets using ANOVA tests show that the accuracy results of different classifiers are significantly different. This will help the healthcare sector and doctors in the early diagnosis of chronic diseases.

Predicting Mortality in Hospitalized COVID-19 Patients in Zambia: An Application of Machine Learning.

The coronavirus disease 2019 (COVID-19) has wreaked havoc globally, resulting in millions of cases and deaths. The objective of this study was to predict mortality in hospitalized COVID-19 patients in Zambia using machine learning (ML) methods based on factors that have been shown to be predictive of mortality and thereby improve pandemic preparedness. This research employed seven powerful ML models that included decision tree (DT), random forest (RF), support vector machines (SVM), logistic regression (LR), Naïve Bayes (NB), gradient boosting (GB), and XGBoost (XGB). These classifiers were trained on 1,433 hospitalized COVID-19 patients from various health facilities in Zambia. The performances achieved by these models were checked using accuracy, recall, F1-Score, area under the receiver operating characteristic curve (ROC_AUC), area under the precision-recall curve (PRC_AUC), and other metrics. The best-performing model was the XGB which had an accuracy of 92.3%, recall of 94.2%, F1-Score of 92.4%, and ROC_AUC of 97.5%. The pairwise Mann-Whitney U-test analysis showed that the second-best model (GB) and the third-best model (RF) did not perform significantly worse than the best model (XGB) and had the following: GB had an accuracy of 91.7%, recall of 94.2%, F1-Score of 91.9%, and ROC_AUC of 97.1%. RF had an accuracy of 90.8%, recall of 93.6%, F1-Score of 91.0%, and ROC_AUC of 96.8%. Other models showed similar results for the same metrics checked. The study successfully derived and validated the selected ML models and predicted mortality effectively with reasonably high performance in the stated metrics. The feature importance analysis found that knowledge of underlying health conditions about patients' hospital length of stay (LOS), white blood cell count, age, and other factors can help healthcare providers offer lifesaving services on time, improve pandemic preparedness, and decongest health facilities in Zambia and other countries with similar settings.

Machine learning analysis of humoral and cellular responses to SARS-CoV-2 infection in young adults.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) induces B and T cell responses, contributing to virus neutralization. In a cohort of 2,911 young adults, we identified 65 individuals who had an asymptomatic or mildly symptomatic SARS-CoV-2 infection and characterized their humoral and T cell responses to the Spike (S), Nucleocapsid (N) and Membrane (M) proteins. We found that previous infection induced CD4 T cells that vigorously responded to pools of peptides derived from the S and N proteins. By using statistical and machine learning models, we observed that the T cell response highly correlated with a compound titer of antibodies against the Receptor Binding Domain (RBD), S and N. However, while serum antibodies decayed over time, the cellular phenotype of these individuals remained stable over four months. Our computational analysis demonstrates that in young adults, asymptomatic and paucisymptomatic SARS-CoV-2 infections can induce robust and long-lasting CD4 T cell responses that exhibit slower decays than antibody titers. These observations imply that next-generation COVID-19 vaccines should be designed to induce stronger cellular responses to sustain the generation of potent neutralizing antibodies.

Use of machine learning to identify risk factors for insomnia.

IMPORTANCE: Sleep is critical to a person's physical and mental health, but there are few studies systematically assessing risk factors for sleep disorders. OBJECTIVE: The objective of this study was to identify risk factors for a sleep disorder through machine-learning and assess this methodology. DESIGN, SETTING, AND PARTICIPANTS: A retrospective, cross-sectional cohort study using the publicly available National Health and Nutrition Examination Survey (NHANES) was conducted in patients who completed the demographic, dietary, exercise, and mental health questionnaire and had laboratory and physical exam data. METHODS: A physician diagnosis of insomnia was the outcome of this study. Univariate logistic models, with insomnia as the outcome, were used to identify covariates that were associated with insomnia. Covariates that had a p<0.0001 on univariate analysis were included within the final machine-learning model. The machine learning model XGBoost was used due to its prevalence within the literature as well as its increased predictive accuracy in healthcare prediction. Model covariates were ranked according to the cover statistic to identify risk factors for insomnia. Shapely Additive Explanations (SHAP) were utilized to visualize the relationship between these potential risk factors and insomnia. RESULTS: Of the 7,929 patients that met the inclusion criteria in this study, 4,055 (51% were female, 3,874 (49%) were male. The mean age was 49.2 (SD = 18.4), with 2,885 (36%) White patients, 2,144 (27%) Black patients, 1,639 (21%) Hispanic patients, and 1,261 (16%) patients of another race. The machine learning model had 64 out of a total of 684 features that were found to be significant on univariate analysis (P<0.0001 used). These were fitted into the XGBoost model and an AUROC = 0.87, Sensitivity = 0.77, Specificity = 0.77 were observed. The top four highest ranked features by cover, a measure of the percentage contribution of the covariate to the overall model prediction, were the Patient Health Questionnaire depression survey (PHQ-9) (Cover = 31.1%), age (Cover = 7.54%), physician recommendation of exercise (Cover = 3.86%), weight (Cover = 2.99%), and waist circumference (Cover = 2.70%). CONCLUSION: Machine learning models can effectively predict risk for a sleep disorder using demographic, laboratory, physical exam, and lifestyle covariates and identify key risk factors.

A machine learning analysis to evaluate the outcome measures in inflammatory myopathies.

OBJECTIVE: To assess the long-term outcome in patients with Idiopathic Inflammatory Myopathies (IIM), focusing on damage and activity disease indexes using artificial intelligence (AI). BACKGROUND: IIM are a group of rare diseases characterized by involvement of different organs in addition to the musculoskeletal. Machine Learning analyses large amounts of information, using different algorithms, decision-making processes and self-learning neural networks. METHODS: We evaluate the long-term outcome of 103 patients with IIM, diagnosed on 2017 EULAR/ACR criteria. We considered different parameters, including clinical manifestations and organ involvement, number and type of treatments, serum creatine kinase levels, muscle strength (MMT8 score), disease activity (MITAX score), disability (HAQ-DI score), disease damage (MDI score), and physician and patient global assessment (PGA). The data collected were analysed, applying, with R, supervised ML algorithms such as lasso, ridge, elastic net, classification, and regression trees (CART), random forest and support vector machines (SVM) to find the factors that best predict disease outcome. RESULTS AND CONCLUSION: Using artificial intelligence algorithms we identified the parameters that best correlate with the disease outcome in IIM. The best result was on MMT8 at follow-up, predicted by a CART regression tree algorithm. MITAX was predicted based on clinical features such as the presence of RP-ILD and skin involvement. A good predictive capacity was also demonstrated on damage scores: MDI and HAQ-DI. In the future Machine Learning will allow us to identify the strengths or weaknesses of the composite disease activity and damage scores, to validate new criteria or to implement classification criteria.

Responses to a COVID-19 vaccination intervention: Qualitative analysis of 17K unsolicited SMS replies.

The development of effective interventions for COVID-19 vaccination has proven challenging given the unique and evolving determinants of that behavior. A tailored intervention to drive vaccination uptake through machine learning-enabled personalization of behavior change messages unexpectedly yielded a high volume of real-time short message service (SMS) feedback from recipients. A qualitative analysis of those replies contributes to a better understanding of the barriers to COVID-19 vaccination and demographic variations in determinants, supporting design improvements for vaccination interventions. OBJECTIVE: The purpose of this study was to examine unsolicited replies to a text message intervention for COVID-19 vaccination to understand the types of barriers experienced and any relationships between recipient demographics, intervention content, and reply type. METHOD: We categorized SMS replies into 22 overall themes. Interrater agreement was very good (all κpooled > 0.62). Chi-square analyses were used to understand demographic variations in reply types and which messaging types were most related to reply types. RESULTS: In total, 10,948 people receiving intervention text messages sent 17,090 replies. Most frequent reply types were "already vaccinated" (31.1%), attempts to unsubscribe (25.4%), and "will not get vaccinated" (12.7%). Within "already vaccinated" and "will not get vaccinated" replies, significant differences were observed in the demographics of those replying against expected base rates, all p > .001. Of those stating they would not vaccinate, 34% of the replies involved mis-/disinformation, suggesting that a determinant of vaccination involves nonvalidated COVID-19 beliefs. CONCLUSIONS: Insights from unsolicited replies can enhance our ability to identify appropriate intervention techniques to influence COVID-19 vaccination behaviors. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

A tree based eXtreme Gradient Boosting (XGBoost) machine learning model to forecast the annual rice production in Bangladesh.

In this study, we attempt to anticipate annual rice production in Bangladesh (1961-2020) using both the Autoregressive Integrated Moving Average (ARIMA) and the eXtreme Gradient Boosting (XGBoost) methods and compare their respective performances. On the basis of the lowest Corrected Akaike Information Criteria (AICc) values, a significant ARIMA (0, 1, 1) model with drift was chosen based on the findings. The drift parameter value shows that the production of rice positively trends upward. Thus, the ARIMA (0, 1, 1) model with drift was found to be significant. On the other hand, the XGBoost model for time series data was developed by changing the tunning parameters frequently with the greatest result. The four prominent error measures, such as mean absolute error (MAE), mean percentage error (MPE), root mean square error (RMSE), and mean absolute percentage error (MAPE), were used to assess the predictive performance of each model. We found that the error measures of the XGBoost model in the test set were comparatively lower than those of the ARIMA model. Comparatively, the MAPE value of the test set of the XGBoost model (5.38%) was lower than that of the ARIMA model (7.23%), indicating that XGBoost performs better than ARIMA at predicting the annual rice production in Bangladesh. Hence, the XGBoost model performs better than the ARIMA model in predicting the annual rice production in Bangladesh. Therefore, based on the better performance, the study forecasted the annual rice production for the next 10 years using the XGBoost model. According to our predictions, the annual rice production in Bangladesh will vary from 57,850,318 tons in 2021 to 82,256,944 tons in 2030. The forecast indicated that the amount of rice produced annually in Bangladesh will increase in the years to come.

Identification of major depression patients using machine learning models based on heart rate variability during sleep stages for pre-hospital screening.

With the COVID-19 pandemic causing challenges in hospital admissions globally, the role of home health monitoring in aiding the diagnosis of mental health disorders has become increasingly important. This paper proposes an interpretable machine learning solution to optimise initial screening for major depressive disorder (MDD) in both male and female patients. The data is from the Stanford Technical Analysis and Sleep Genome Study (STAGES). We analyzed 5-min short-term electrocardiogram (ECG) signals during nighttime sleep stages of 40 MDD patients and 40 healthy controls, with a 1:1 gender ratio. After preprocessing, we calculated the time-frequency parameters of heart rate variability (HRV) based on the ECG signals and used common machine learning algorithms for classification, along with feature importance analysis for global decision analysis. Ultimately, the Bayesian optimised extremely randomized trees classifier (BO-ERTC) showed the best performance on this dataset (accuracy 86.32%, specificity 86.49%, sensitivity 85.85%, F1-score 0.86). By using feature importance analysis on the cases confirmed by BO-ERTC, we found that gender is one of the most important factors affecting the prediction of the model, which should not be overlooked in our assisted diagnosis. This method can be embedded in portable ECG monitoring systems and is consistent with the literature results.

Prediction of COVID-19 Mortality in the Intensive Care Unit Using Machine Learning.

Since its emergence, the COVID-19 pandemic still poses a major global health threat. In this setting, a number of useful machine learning applications have been explored to assist clinical decision-making, predict the severity of disease and admission to the intensive care unit, and also to estimate future demand for hospital beds, equipment, and staff. The present study examined demographic data, hematological and biochemical markers routinely measured in Covid-19 patients admitted to the intensive care unit (ICU) of a public tertiary hospital, in relation to the ICU outcome, during the second and third Covid-19 waves, from October 2020 until February 2022. In this dataset, we applied eight well-known classifiers of the caret package for machine learning of the R programming language, to evaluate their performance in forecasting ICU mortality. The best performance regarding area under the receiver operating characteristic curve (AUC-ROC) was observed with Random Forest (0.82), while k-nearest neighbors (k-NN) were the lowest performing machine learning algorithm (AUC-ROC: 0.59). However, in terms of sensitivity, XGB outperformed the other classifiers (max Sens: 0.7). The six most important predictors of mortality in the Random Forest model were serum urea, age, hemoglobin, C-reactive protein, platelets, and lymphocyte count.

De-black-boxing health AI: demonstrating reproducible machine learning computable phenotypes using the N3C-RECOVER Long COVID model in the All of Us data repository.

Machine learning (ML)-driven computable phenotypes are among the most challenging to share and reproduce. Despite this difficulty, the urgent public health considerations around Long COVID make it especially important to ensure the rigor and reproducibility of Long COVID phenotyping algorithms such that they can be made available to a broad audience of researchers. As part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, researchers with the National COVID Cohort Collaborative (N3C) devised and trained an ML-based phenotype to identify patients highly probable to have Long COVID. Supported by RECOVER, N3C and NIH's All of Us study partnered to reproduce the output of N3C's trained model in the All of Us data enclave, demonstrating model extensibility in multiple environments. This case study in ML-based phenotype reuse illustrates how open-source software best practices and cross-site collaboration can de-black-box phenotyping algorithms, prevent unnecessary rework, and promote open science in informatics.

Proof of concept of the potential of a machine learning algorithm to extract new information from conventional SARS-CoV-2 rRT-PCR results.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been and remains one of the major challenges modern society has faced thus far. Over the past few months, large amounts of information have been collected that are only now beginning to be assimilated. In the present work, the existence of residual information in the massive numbers of rRT-PCRs that tested positive out of the almost half a million tests that were performed during the pandemic is investigated. This residual information is believed to be highly related to a pattern in the number of cycles that are necessary to detect positive samples as such. Thus, a database of more than 20,000 positive samples was collected, and two supervised classification algorithms (a support vector machine and a neural network) were trained to temporally locate each sample based solely and exclusively on the number of cycles determined in the rRT-PCR of each individual. Overall, this study suggests that there is valuable residual information in the rRT-PCR positive samples that can be used to identify patterns in the development of the SARS-CoV-2 pandemic. The successful application of supervised classification algorithms to detect these patterns demonstrates the potential of machine learning techniques to aid in understanding the spread of the virus and its variants.

Using Twitter-Based Data for Sexual Violence Research: Scoping Review.

BACKGROUND: Scholars have used data from in-person interviews, administrative systems, and surveys for sexual violence research. Using Twitter as a data source for examining the nature of sexual violence is a relatively new and underexplored area of study. OBJECTIVE: We aimed to perform a scoping review of the current literature on using Twitter data for researching sexual violence, elaborate on the validity of the methods, and discuss the implications and limitations of existing studies. METHODS: We performed a literature search in the following 6 databases: APA PsycInfo (Ovid), Scopus, PubMed, International Bibliography of Social Sciences (ProQuest), Criminal Justice Abstracts (EBSCO), and Communications Abstracts (EBSCO), in April 2022. The initial search identified 3759 articles that were imported into Covidence. Seven independent reviewers screened these articles following 2 steps: (1) title and abstract screening, and (2) full-text screening. The inclusion criteria were as follows: (1) empirical research, (2) focus on sexual violence, (3) analysis of Twitter data (ie, tweets or Twitter metadata), and (4) text in English. Finally, we selected 121 articles that met the inclusion criteria and coded these articles. RESULTS: We coded and presented the 121 articles using Twitter-based data for sexual violence research. About 70% (89/121, 73.6%) of the articles were published in peer-reviewed journals after 2018. The reviewed articles collectively analyzed about 79.6 million tweets. The primary approaches to using Twitter as a data source were content text analysis (112/121, 92.5%) and sentiment analysis (31/121, 25.6%). Hashtags (103/121, 85.1%) were the most prominent metadata feature, followed by tweet time and date, retweets, replies, URLs, and geotags. More than a third of the articles (51/121, 42.1%) used the application programming interface to collect Twitter data. Data analyses included qualitative thematic analysis, machine learning (eg, sentiment analysis, supervised machine learning, unsupervised machine learning, and social network analysis), and quantitative analysis. Only 10.7% (13/121) of the studies discussed ethical considerations. CONCLUSIONS: We described the current state of using Twitter data for sexual violence research, developed a new taxonomy describing Twitter as a data source, and evaluated the methodologies. Research recommendations include the following: development of methods for data collection and analysis, in-depth discussions about ethical norms, exploration of specific aspects of sexual violence on Twitter, examination of tweets in multiple languages, and decontextualization of Twitter data. This review demonstrates the potential of using Twitter data in sexual violence research.