Voice-based control system for smart hospital wards: a pilot study of patient acceptance.

BACKGROUND: The smart hospital's concept of using the Internet of Things (IoT) to reduce human resources demand has become more popular in the aging society. OBJECTIVE: To implement the voice smart care (VSC) system in hospital wards and explore patient acceptance via the Technology Acceptance Model (TAM). METHODS: A structured questionnaire based on TAM was developed and validated as a research tool. Only the patients hospitalized in the VSC wards and who used it for more than two days were invited to fill the questionnaire. Statistical variables were analyzed using SPSS version 24.0. A total of 30 valid questionnaires were finally obtained after excluding two incomplete questionnaires. Cronbach's α values for all study constructs were above 0.84. RESULT: We observed that perceived ease of use on perceived usefulness, perceived usefulness on user satisfaction and attitude toward using, and attitude toward using on behavioral intention to use had statistical significance (p < .01), respectively. CONCLUSION: We have successfully developed the VSC system in a Taiwanese academic medical center. Our study indicated that perceived usefulness was a crucial factor, which means the system function should precisely meet the patients' demands. Additionally, a clever system design is important since perceived ease of use positively affects perceived usefulness. The insight generated from this study could be beneficial to hospitals when implementing similar systems to their wards.

Hybrid robot-assisted gait training for motor function in subacute stroke: a single-blind randomized controlled trial.

BACKGROUND: Robot-assisted gait training (RAGT) is a practical treatment that can complement conventional rehabilitation by providing high-intensity repetitive training for patients with stroke. RAGT systems are usually either of the end-effector or exoskeleton types. We developed a novel hybrid RAGT system that leverages the advantages of both types. OBJECTIVE: This single-blind randomized controlled trial evaluated the beneficial effects of the novel RAGT system both immediately after the intervention and at the 3-month follow-up in nonambulatory patients with subacute stroke. METHODS: We recruited 40 patients with subacute stroke who were equally randomized to receive conventional rehabilitation either alone or with the addition of 15 RAGT sessions. We assessed lower-extremity motor function, balance, and gait performance by using the following tools: active range of motion (AROM), manual muscle test (MMT), the Fugl-Meyer Assessment (FMA) lower-extremity subscale (FMA-LE) and total (FMA-total), Postural Assessment Scale for Stroke (PASS), Berg Balance Scale (BBS), Tinetti Performance-Oriented Mobility Assessment (POMA) balance and gait subscores, and the 3-m and 6-m walking speed and Timed Up and Go (TUG) tests. These measurements were performed before and after the intervention and at the 3-month follow-up. RESULTS: Both groups demonstrated significant within-group changes in the AROM, MMT, FMA-LE, FMA-total, PASS, BBS, POMA, TUG, and 3-m and 6-m walking speed tests before and after intervention and at the 3-month follow-up (p < 0.05). The RAGT group significantly outperformed the control group only in the FMA-LE (p = 0.014) and total (p = 0.002) assessments. CONCLUSION: Although the novel hybrid RAGT is effective, strong evidence supporting its clinical effectiveness relative to controls in those with substantial leg dysfunction after stroke remains elusive. Trial registration The study was registered with an International Standard Randomized Controlled Trial Number, ISRCTN, ISRCTN15088682. Registered retrospectively on September 16, 2016, at https://www.isrctn.com/ISRCTN15088682.

Assessment of knowledge, attitudes, and practices towards Zika virus among healthcare workers in St. Kitts.

BACKGROUND: Healthcare workers are usually the first responders during outbreaks and are instrumental in educating the populace about the prevention of different diseases and illnesses. The aim of this study was to assess the association between healthcare workers' characteristics and knowledge, attitudes and practices toward Zika virus. METHODS: This was a cross-sectional study that collected data from healthcare workers at 3 medical facilities using a validated self-administered questionnaire between July 2017 - September 2017. Logistic regression models were used to examine the association between sociodemographic and knowledge, attitudes, and practices. RESULTS: A total of 190 healthcare workers were analyzed. Of these, 60, 72.6 and 64.7% had good knowledge, positive attitudes, and good practices toward Zika virus, respectively. Healthcare workers without a formal degree were less likely to have good knowledge of Zika virus (adjusted odds ratio (AOR) = 0:49; 95% confidence interval (CI) = 0.24-0.99) compared to those with a formal degree. Reduced odds for positive attitude towards Zika virus were observed in healthcare workers with low income as compared to those with high income (AOR = 0.31; 95% CI =0.13-0.75). Being younger than 40 years old was associated with poor Zika virus practices (AOR = 0:34; 95% CI = 0.15-0.79). CONCLUSIONS: Significant association between healthcare workers' sociodemographic characteristics and Zika virus knowledge, attitudes and practices were observed. Public health interventions that seek to increase Zika virus awareness should aim to train healthcare workers who are younger, without formal degree and those earning low income.

Levothyroxine use and the risk of breast cancer: a nation-wide population-based case-control study.

PURPOSE: To investigate whether the use of levothyroxine was associated with breast cancer risk. METHODS: We conducted a population-based case-control study in Taiwan. Cases consisted of all patients who were aged 20 years and older, and had a first-time diagnosis of breast cancer for the period between 2001 and 2011. The controls were matched to the cases by age, sex, year, and month of diagnosis. Adjusted odd ratios (ORs) and 95% confidence intervals (CIs) were estimated by a conditional logistic regression. RESULTS: We examined 65,491 breast cancer cases and 261,964 controls. We found that use of levothyroxine was associated with a significant increase in breast cancer risk (OR 1.24, 95% CI 1.15-1.33; P < 0.001). Compared with no use levothyroxine, the adjusted odd ratio was 1.22 (95% CI 1.11-1.35; P = 0.01) for the group having been prescribed levothyroxine 2 months to 1 year, and 1.26 (95% CI 1.12-1.41; P < 0.01) for the group with more than 1 year. When stratified by age, the adjusted odd ratio was 1.45 (95% CI 1.23-1.71; P < 0.01) for the patients aged 65 years or more and 1.19 (95% CI 1.09-1.29, P < 0.01) for the patients aged less than 65 years. CONCLUSION: The results of the present study are the first to suggest that levothyroxine use increased the risk of breast cancer. However, a larger long-term prospective randomized-controlled trial specifically designed to assess the effect of levothyroxine use on the risk of developing breast cancer is needed.

Benzodiazepines use and breast cancer risk: A population-based study and gene expression profiling evidence.

The aim of this study was to investigate whether long-term use of Benzodiazepines (BZDs) is associated with breast cancer risk through the combination of population-based observational and gene expression profiling evidence. We conducted a population-based case-control study by using 1998 to 2009year Taiwan National Health Insurance Research Database and investigated the association between BZDs use and breast cancer risk. We selected subjects age of >20years old and six eligible controls matched for age, sex and the index date (i.e., free of any cancer at the case diagnosis date) by using propensity scores. A bioinformatics analysis approach was also performed for the identification of oncogenesis effects of BZDs on breast cancer. We used breast cancer gene expression data from the Cancer Genome Atlas and perturbagen signatures of BZDs from the Library of Integrated Cellular Signatures database in order to identify the oncogenesis effects of BZDs on breast cancer. We found evidence of increased breast cancer risk for diazepam (OR, 1.16; 95%CI, 0.95-1.42; connectivity score [CS], 0.3016), zolpidem (OR, 1.11; 95%CI, 0.95-1.30; CS, 0.2738), but not for lorazepam (OR, 1.04; 95%CI, 0.89-1.23; CS, -0.2952) consistently in both methods. The finding for alparazolam was contradictory from the two methods. Diazepam and zolpidem trends showed association, although not statistically significant, with breast cancer risk in both epidemiological and bioinformatics analyses outcomes. The methodological value of our study is in introducing the way of combining epidemiological and bioinformatics approaches in order to answer a common scientific question. Combining the two approaches would be a substantial step towards uncovering, validation and further application of previously unknown scientific knowledge to the emerging field of precision medicine informatics.

Psychotropic medications prescribing trends in adolescents: A nationwide population-based study in Taiwan.

OBJECTIVE: To describe psychotropic medications prescription patterns among adolescents in Taiwan; focusing on age, gender, duration of treatments and various classes of psychotropic medications. DESIGN: A retrospective description analysis. SETTING: Taiwan National Health Insurance Database. PARTICIPANTS: Twelve to seventeen years' patients treated with psychotropic medications. INTERVENTION: None. MAIN OUTCOME MEASURE(S): Percentage and duration of treatment with psychotropic medications during the study periods by medication classes and age groups were calculated. In addition, top three prescribed psychotropic medications were also determined. RESULTS: A total of 3,120 patients were prescribed psychotropic drugs. The percentage of adolescent patients that received anxiolytics and antidepressants in 2002-2012 were 2.89% and 2.15%, respectively. Also, 851 patients (1.21%) were prescribed hypnotics and 638 (0.91%) were given sedatives. The prevalence rate of the prescription of psychotropic drugs increased steadily with age and females were more treated than males except antipsychotic. Among psychotropic drugs, antidepressants (mean: 8.6 times) were refilled more but antipsychotics (mean 188 days) were the long-term treatment drugs. Additionally, the trend of hospital visits fluctuated over the year while May and December showed a higher rate of visits. CONCLUSIONS: These findings show that the prevalence of psychotropic drug prescriptions in Taiwanese adolescents is even low but increasing trends in the prescription of these medications raises some concern. As the evidence of psychotropic drug safety and effectiveness in adolescents is still inadequate; we recommend that healthcare providers should consider psychotropic drugs therapy, continuously monitor for outcomes and empower their patients to improve their knowledge, therapeutic outcomes and quality of life.

An automated technique to identify potential inappropriate traditional Chinese medicine (TCM) prescriptions.

PURPOSE: Medication errors such as potential inappropriate prescriptions would induce serious adverse drug events to patients. Information technology has the ability to prevent medication errors; however, the pharmacology of traditional Chinese medicine (TCM) is not as clear as in western medicine. The aim of this study was to apply the appropriateness of prescription (AOP) model to identify potential inappropriate TCM prescriptions. METHODS: We used the association rule of mining techniques to analyze 14.5 million prescriptions from the Taiwan National Health Insurance Research Database. The disease and TCM (DTCM) and traditional Chinese medicine-traditional Chinese medicine (TCMM) associations are computed by their co-occurrence, and the associations' strength was measured as Q-values, which often referred to as interestingness or life values. By considering the number of Q-values, the AOP model was applied to identify the inappropriate prescriptions. Afterwards, three traditional Chinese physicians evaluated 1920 prescriptions and validated the detected outcomes from the AOP model. RESULT: Out of 1920 prescriptions, 97.1% of positive predictive value and 19.5% of negative predictive value were shown by the system as compared with those by experts. The sensitivity analysis indicated that the negative predictive value could improve up to 27.5% when the model's threshold changed to 0.4. CONCLUSION: We successfully applied the AOP model to automatically identify potential inappropriate TCM prescriptions. This model could be a potential TCM clinical decision support system in order to improve drug safety and quality of care.

A richly interactive exploratory data analysis and visualization tool using electronic medical records.

BACKGROUND: Electronic medical records (EMRs) contain vast amounts of data that is of great interest to physicians, clinical researchers, and medial policy makers. As the size, complexity, and accessibility of EMRs grow, the ability to extract meaningful information from them has become an increasingly important problem to solve. METHODS: We develop a standardized data analysis process to support cohort study with a focus on a particular disease. We use an interactive divide-and-conquer approach to classify patients into relatively uniform within each group. It is a repetitive process enabling the user to divide the data into homogeneous subsets that can be visually examined, compared, and refined. The final visualization was driven by the transformed data, and user feedback direct to the corresponding operators which completed the repetitive process. The output results are shown in a Sankey diagram-style timeline, which is a particular kind of flow diagram for showing factors' states and transitions over time. RESULTS: This paper presented a visually rich, interactive web-based application, which could enable researchers to study any cohorts over time by using EMR data. The resulting visualizations help uncover hidden information in the data, compare differences between patient groups, determine critical factors that influence a particular disease, and help direct further analyses. We introduced and demonstrated this tool by using EMRs of 14,567 Chronic Kidney Disease (CKD) patients. CONCLUSIONS: We developed a visual mining system to support exploratory data analysis of multi-dimensional categorical EMR data. By using CKD as a model of disease, it was assembled by automated correlational analysis and human-curated visual evaluation. The visualization methods such as Sankey diagram can reveal useful knowledge about the particular disease cohort and the trajectories of the disease over time.

Utilizing Health Information Technology to Support Universal Healthcare Delivery: Experience of a National Healthcare System.

Recent discussions have focused on using health information technology (HIT) to support goals related to universal healthcare delivery. These discussions have generally not reflected on the experience of countries with a large amount of experience using HIT to support universal healthcare on a national level. HIT was compared globally by using data from the Ministry of the Interior, Republic of China (Taiwan). Taiwan has been providing universal healthcare since 1995 and began to strategically implement HIT on a national level at that time. Today the national-level HIT system is more extensive in Taiwan than in many other countries and is used to aid administration, clinical care, and public health. The experience of Taiwan thus can provide an illustration of how HIT can be used to support universal healthcare delivery. In this article we present an overview of some key historical developments and successes in the adoption of HIT in Taiwan over a 17-year period, as well as some more recent developments. We use this experience to offer some strategic perspectives on how it can aid in the adoption of large-scale HIT systems and on how HIT can be used to support universal healthcare delivery.

Adjustable Cuffless Smartphone Attachment (ACSA+) for Estimation of Blood Pressure Trends: A Pilot Study.

Among the elderly, hypertension remains one of the prevalent health conditions, which requires monitoring and intervention strategies. Nevertheless, regular reporting of blood pressure (BP) from these individuals still poses multiple challenges. However, most people own cell phone and are engaged in phone conversations daily. Here, we propose an adjustable cuffless smartphone attachment (ACSA+) equipped with a PPG sensor for the estimation of BP during phone conversations. ACSA+ can be easily attached to the back of any modern cell phone. ACSA+ will help to continuously collect BP data and store it as a trend line.

Corrigendum to "Investigating nurses' acceptance of patients' bring your own device implementation in a clinical setting: A pilot study" [Asia-Pacific J Oncol Nurs 10 (2023) 100195].

[This corrects the article DOI: 10.1016/j.apjon.2023.100195.].

A novel Multi-Level Refined (MLR) knowledge graph design and chatbot system for healthcare applications.

Imagine having a knowledge graph that can extract medical health knowledge related to patient diagnosis solutions and treatments from thousands of research papers, distilled using machine learning techniques in healthcare applications. Medical doctors can quickly determine treatments and medications for urgent patients, while researchers can discover innovative treatments for existing and unknown diseases. This would be incredible! Our approach serves as an all-in-one solution, enabling users to employ a unified design methodology for creating their own knowledge graphs. Our rigorous validation process involves multiple stages of refinement, ensuring that the resulting answers are of the utmost professionalism and solidity, surpassing the capabilities of other solutions. However, building a high-quality knowledge graph from scratch, with complete triplets consisting of subject entities, relations, and object entities, is a complex and important task that requires a systematic approach. To address this, we have developed a comprehensive design flow for knowledge graph development and a high-quality entities database. We also developed knowledge distillation schemes that allow you to input a keyword (entity) and display all related entities and relations. Our proprietary methodology, multiple levels refinement (MLR), is a novel approach to constructing knowledge graphs and refining entities level-by-level. This ensures the generation of high-quality triplets and a readable knowledge graph through keyword searching. We have generated multiple knowledge graphs and developed a scheme to find the corresponding inputs and outputs of entity linking. Entities with multiple inputs and outputs are referred to as joints, and we have created a joint-version knowledge graph based on this. Additionally, we developed an interactive knowledge graph, providing a user-friendly environment for medical professionals to explore entities related to existing or unknown treatments/diseases. Finally, we have advanced knowledge distillation techniques.

Correction: A novel Multi-Level Refined (MLR) knowledge graph design and chatbot system for healthcare applications.

[This corrects the article DOI: 10.1371/journal.pone.0296939.].

Misleading health-related information promoted through video-based social media: anorexia on YouTube.

INTRODUCTION: The amount of information being uploaded onto social video platforms, such as YouTube, Vimeo, and Veoh, continues to spiral, making it increasingly difficult to discern reliable health information from misleading content. There are thousands of YouTube videos promoting misleading information about anorexia (eg, anorexia as a healthy lifestyle). OBJECTIVE: The aim of this study was to investigate anorexia-related misinformation disseminated through YouTube videos. METHODS: We retrieved YouTube videos related to anorexia using the keywords anorexia, anorexia nervosa, proana, and thinspo on October 10, 2011.Three doctors reviewed 140 videos with approximately 11 hours of video content, classifying them as informative, pro-anorexia, or others. By informative we mean content describing the health consequences of anorexia and advice on how to recover from it; by pro-anorexia we mean videos promoting anorexia as a fashion, a source of beauty, and that share tips and methods for becoming and remaining anorexic. The 40 most-viewed videos (20 informative and 20 pro-anorexia videos) were assessed to gauge viewer behavior. RESULTS: The interrater agreement of classification was moderate (Fleiss' kappa=0.5), with 29.3% (n=41) being rated as pro-anorexia, 55.7% (n=78) as informative, and 15.0% (n=21) as others. Pro-anorexia videos were favored 3 times more than informative videos (odds ratio [OR] 3.3, 95% CI 3.3-3.4, P<.001). CONCLUSIONS: Pro-anorexia information was identified in 29.3% of anorexia-related videos. Pro-anorexia videos are less common than informative videos; however, in proportional terms, pro-anorexia content is more highly favored and rated by its viewers. Efforts should focus on raising awareness, particularly among teenagers, about the trustworthiness of online information about beauty and healthy lifestyles. Health authorities producing videos to combat anorexia should consider involving celebrities and models to reach a wider audience. More research is needed to study the characteristics of pro-anorexia videos in order to develop algorithms that will automatically detect and filter those videos before they become popular.

Incidence and Mortality of Malignant Brain Tumors after 20 Years of Mobile Use.

(1) Objective: This population-based study was performed to examine the trends of incidence and deaths due to malignant neoplasm of the brain (MNB) in association with mobile phone usage for a period of 20 years (January 2000-December 2019) in Taiwan. (2) Methods: Pearson correlation, regression analysis, and joinpoint regression analysis were used to examine the trends of incidence of MNB and deaths due to MNB in association with mobile phone usage. (3) Results: The findings indicate a trend of increase in the number of mobile phone users over the study period, accompanied by a slight rise in the incidence and death rates of MNB. The compound annual growth rates further support these observations, highlighting consistent growth in mobile phone users and a corresponding increase in MNB incidences and deaths. (4) Conclusions: The results suggest a weaker association between the growing number of mobile phone users and the rising rates of MNB, and no significant correlation was observed between MNB incidences and deaths and mobile phone usage. Ultimately, it is important to acknowledge that conclusive results cannot be drawn at this stage and further investigation is required by considering various other confounding factors and potential risks to obtain more definitive findings and a clearer picture.

Investigating nurses' acceptance of patients' bring your own device implementation in a clinical setting: A pilot study.

Objective: The popularity of the â€‹"bring your own device (BYOD)" â€‹concept has grown in recent years, and its application has extended to the healthcare field. This study was aimed at examining nurses' acceptance of a BYOD-supported system after a 9-month implementation period. Methods: We used the technology acceptance model to develop and validate a structured questionnaire as a research tool. All nurses (n â€‹= â€‹18) responsible for the BYOD-supported wards during the study period were included in our study. A 5-point Likert scale was used to assess the degree of disagreement and agreement. Statistical analysis was performed in SPSS version 24.0. Results: The questionnaire was determined to be reliable and well constructed, on the basis of the item-level content validity index and Cronbach α values above 0.95 and 0.87, respectively. The mean constant values for all items were above 3.95, thus suggesting that nurses had a positive attitude toward the BYOD-supported system, driven by the characteristics of the tasks involved. Conclusions: We successfully developed a BYOD-supported system. Our study results suggested that nursing staff satisfaction with BYOD-supported systems could be effectively increased by providing practical functionalities and reducing clinical burden. Hospitals could benefit from the insights generated by this study when implementing similar systems.

Assessment of effects of moon phases on hospital outpatient visits: An observational national study.

Objectives: A vast amount of literature has been conducted for investigating the association of different lunar phases with human health; and it has mixed reviews for association and non-association of diseases with lunar phases. This study investigates the existence of any impact of moon phases on humans by exploring the difference in the rate of outpatient visits and type of diseases that prevail in either non-moon or moon phases. Methods: We retrieved dates of non-moon and moon phases for eight years (1st January 2001-31st December 2008) from the timeanddate.com website for Taiwan. The study cohort consisted of 1 million people from Taiwan's National Health Insurance Research Database (NHIRD) followed over eight years (1st January 2001-31st December 2008). We used the two-tailed, paired-t-test to compare the significance of difference among outpatient visits for 1229 moon phase days and 1074 non-moon phase days by using International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes from NHIRD records. Results: We found 58 diseases that showed statistical differences in number of outpatient visits in the non-moon and moon phases. Conclusions: The results of our study identified diseases that have significant variations during different lunar phases (non-moon and moon phases) for outpatient visits in the hospital. In order to fully understand the reality of the pervasive myth of lunar effects on human health, behaviors and diseases, more in-depth research investigations are required for providing comprehensive evidence covering all the factors, such as biological, psychological and environmental aspects.

Factors influencing consumer adoption of USB-based Personal Health Records in Taiwan.

BACKGROUND: Usually patients receive healthcare services from multiple hospitals, and consequently their healthcare data are dispersed over many facilities' paper and electronic-based record systems. Therefore, many countries have encouraged the research on data interoperability, access, and patient authorization. This study is an important part of a national project to build an information exchange environment for cross-hospital digital medical records carried out by the Department of Health (DOH) of Taiwan in May 2008. The key objective of the core project is to set up a portable data exchange environment in order to enable people to maintain and own their essential health information.This study is aimed at exploring the factors influencing behavior and adoption of USB-based Personal Health Records (PHR) in Taiwan. METHODS: Quota sampling was used, and structured questionnaires were distributed to the outpatient department at ten medical centers which participated in the DOH project to establish the information exchange environment across hospitals. A total of 3000 questionnaires were distributed and 1549 responses were collected, out of those 1465 were valid, accumulating the response rate to 48.83%. RESULTS: 1025 out of 1465 respondents had expressed their willingness to apply for the USB-PHR. Detailed analysis of the data reflected that there was a remarkable difference in the "usage intention" between the PHR adopters and non-adopters (χ2 =182.4, p < 0.001). From the result of multivariate logistic regression analyses, we found the key factors affecting patients' adoption pattern were Usage Intention (OR, 9.43, 95%C.I., 5.87-15.16), Perceived Usefulness (OR, 1.60; 95%C.I., 1.11-2.29) and Subjective Norm (OR, 1.47; 95%C.I., 1.21-1.78). CONCLUSIONS: Higher Usage Intentions, Perceived Usefulness and Subjective Norm of patients were found to be the key factors influencing PHR adoption. Thus, we suggest that government and hospitals should promote the potential usefulness of PHR, and physicians should encourage patients' to adopt the PHR.

The Taiwanese method for providing patients data from multiple hospital EHR systems.

Personal Health Record (PHR) systems are growing in popularity and are receiving increased attention from the Biomedical Informatics research community. Information Collection is one PHR research topic and includes system functionality that helps patients retrieve their data from external sources. One of the most potentially useful external sources of information is the data stored in patients' EHRs at medical institutions. PHR systems that support Information Collection from EHR systems are thus interesting to investigate. In this paper we present PHR system that allows patients to receive data from 10 participating hospitals in Taiwan via a USB flash memory device. The overall design goals and architecture for the system are presented. Based on our experiences in designing and implementing the system we propose a three step method for accomplishing Information Collection from EHR systems at medical institutions for similar PHR systems in the future.

Application of Artificial Intelligence for Screening COVID-19 Patients Using Digital Images: Meta-analysis.

BACKGROUND: The COVID-19 outbreak has spread rapidly and hospitals are overwhelmed with COVID-19 patients. While analysis of nasal and throat swabs from patients is the main way to detect COVID-19, analyzing chest images could offer an alternative method to hospitals, where health care personnel and testing kits are scarce. Deep learning (DL), in particular, has shown impressive levels of performance when analyzing medical images, including those related to COVID-19 pneumonia. OBJECTIVE: The goal of this study was to perform a systematic review with a meta-analysis of relevant studies to quantify the performance of DL algorithms in the automatic stratification of COVID-19 patients using chest images. METHODS: A search strategy for use in PubMed, Scopus, Google Scholar, and Web of Science was developed, where we searched for articles published between January 1 and April 25, 2020. We used the key terms "COVID-19," or "coronavirus," or "SARS-CoV-2," or "novel corona," or "2019-ncov," and "deep learning," or "artificial intelligence," or "automatic detection." Two authors independently extracted data on study characteristics, methods, risk of bias, and outcomes. Any disagreement between them was resolved by consensus. RESULTS: A total of 16 studies were included in the meta-analysis, which included 5896 chest images from COVID-19 patients. The pooled sensitivity and specificity of the DL models in detecting COVID-19 were 0.95 (95% CI 0.94-0.95) and 0.96 (95% CI 0.96-0.97), respectively, with an area under the receiver operating characteristic curve of 0.98. The positive likelihood, negative likelihood, and diagnostic odds ratio were 19.02 (95% CI 12.83-28.19), 0.06 (95% CI 0.04-0.10), and 368.07 (95% CI 162.30-834.75), respectively. The pooled sensitivity and specificity for distinguishing other types of pneumonia from COVID-19 were 0.93 (95% CI 0.92-0.94) and 0.95 (95% CI 0.94-0.95), respectively. The performance of radiologists in detecting COVID-19 was lower than that of the DL models; however, the performance of junior radiologists was improved when they used DL-based prediction tools. CONCLUSIONS: Our study findings show that DL models have immense potential in accurately stratifying COVID-19 patients and in correctly differentiating them from patients with other types of pneumonia and normal patients. Implementation of DL-based tools can assist radiologists in correctly and quickly detecting COVID-19 and, consequently, in combating the COVID-19 pandemic.