Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 47
Filter
Add filters

Document Type
Year range
2.
Sensors (Basel) ; 21(21)2021 Oct 21.
Article in English | MEDLINE | ID: covidwho-1512556

ABSTRACT

This paper proposes a cloud-based software architecture for fully automated point-of-care molecular diagnostic devices. The target system operates a cartridge consisting of an extraction body for DNA extraction and a PCR chip for amplification and fluorescence detection. To facilitate control and monitoring via the cloud, a socket server was employed for fundamental molecular diagnostic functions such as DNA extraction, amplification, and fluorescence detection. The user interface for experimental control and monitoring was constructed with the RESTful application programming interface, allowing access from the terminal device, edge, and cloud. Furthermore, it can also be accessed through any web-based user interface on smart computing devices such as smart phones or tablets. An emulator with the proposed software architecture was fabricated to validate successful operation.


Subject(s)
Cloud Computing , Point-of-Care Systems , Computers , Pathology, Molecular , Software
3.
J Healthc Eng ; 2021: 8133076, 2021.
Article in English | MEDLINE | ID: covidwho-1501834

ABSTRACT

The mouse is one of the wonderful inventions of Human-Computer Interaction (HCI) technology. Currently, wireless mouse or a Bluetooth mouse still uses devices and is not free of devices completely since it uses a battery for power and a dongle to connect it to the PC. In the proposed AI virtual mouse system, this limitation can be overcome by employing webcam or a built-in camera for capturing of hand gestures and hand tip detection using computer vision. The algorithm used in the system makes use of the machine learning algorithm. Based on the hand gestures, the computer can be controlled virtually and can perform left click, right click, scrolling functions, and computer cursor function without the use of the physical mouse. The algorithm is based on deep learning for detecting the hands. Hence, the proposed system will avoid COVID-19 spread by eliminating the human intervention and dependency of devices to control the computer.


Subject(s)
COVID-19 , Deep Learning , Equipment Contamination , Algorithms , Computers , Gestures , Hand , Humans , SARS-CoV-2
4.
J Prof Nurs ; 37(5): 928-934, 2021.
Article in English | MEDLINE | ID: covidwho-1492501

ABSTRACT

The COVID-19 pandemic created an upheaval for nursing faculty teaching students in both didactic and clinical settings. From the intense disruption, opportunities for creative endeavors emerged. Program directors from a consortium of 12 nursing schools met remotely for problem-solving and support. Rich text from minutes of nine program director meetings were analyzed. Aims of our project included identifying challenges that nurse educators encountered during the pandemic, demonstrating benefits of a university and community college partnership model, and informing nurse educators of innovative outcomes that originated from our project. Thematic analysis of meeting minutes revealed four categories: timing and urgency; collaboration, preparation, and teaching; altruism; and what we learned. Further themes were identified from each of the categories. Innovative outcomes were identified from the text including creation of website teaching resources and development of a computer based clinical checklist. Implications for future nursing education included that computer- based simulation will continue to be embedded in nursing curricula. Also, the need for nursing faculty to remain technologically savvy to deliver trailblazing online pedagogies will prominently continue. We conclude that the synergistic collaboration of nursing program directors can have momentous outcomes for support and success of nursing programs.


Subject(s)
COVID-19 , Education, Nursing, Baccalaureate , Education, Nursing , Students, Nursing , Computers , Faculty, Nursing , Humans , New Mexico , Pandemics , SARS-CoV-2
5.
Sensors (Basel) ; 21(21)2021 Oct 31.
Article in English | MEDLINE | ID: covidwho-1488706

ABSTRACT

The speed and accuracy of phenotype detection from medical images are some of the most important qualities needed for any informed and timely response such as early detection of cancer or detection of desirable phenotypes for animal breeding. To improve both these qualities, the world is leveraging artificial intelligence and machine learning against this challenge. Most recently, deep learning has successfully been applied to the medical field to improve detection accuracies and speed for conditions including cancer and COVID-19. In this study, we applied deep neural networks, in the form of a generative adversarial network (GAN), to perform image-to-image processing steps needed for ovine phenotype analysis from CT scans of sheep. Key phenotypes such as gigot geometry and tissue distribution were determined using a computer vision (CV) pipeline. The results of the image processing using a trained GAN are strikingly similar (a similarity index of 98%) when used on unseen test images. The combined GAN-CV pipeline was able to process and determine the phenotypes at a speed of 0.11 s per medical image compared to approximately 30 min for manual processing. We hope this pipeline represents the first step towards automated phenotype extraction for ovine genetic breeding programmes.


Subject(s)
Artificial Intelligence , COVID-19 , Animals , Computers , Humans , Image Processing, Computer-Assisted , Phenotype , SARS-CoV-2 , Sheep
6.
Optom Vis Sci ; 98(11): 1255-1262, 2021 11 01.
Article in English | MEDLINE | ID: covidwho-1475929

ABSTRACT

SIGNIFICANCE: After 6 to 8 weeks of mandatory lockdown due to coronavirus disease 2019 (COVID-19) in Spain, the encouraged change in daily habits resulted in a significant increase in electronic device use. Computer vision syndrome-related symptoms were reported more often in participants who used electronic device for more time and spent less time outdoors. PURPOSE: The main purpose of this study was to evaluate computer vision syndrome-related eye symptoms due to the use of electronic devices during COVID-19 lockdown decreed in Spain in 2020. METHODS: After 6 to 8 weeks of strict lockdown, a total of 730 participants (18 to 73 years old) filled in a customized questionnaire divided into three sections: (1) general demographics, (2) usage habits of electronic devices during this period, and (3) computer vision syndrome-related ocular and visual symptoms associated with their use and with ergonomic practices. RESULTS: The daily duration of use of electronic devices increased an average of 3.1 ± 2.2 h/d during the lockdown, with computer use increasing the most. The main symptoms reported by the participants were headache (36.7%), dry eye (31.1%), irritation (24.1%), blurred vision (21.2%), and ocular pain (14.9%). There was a significant relationship between computer vision syndrome-related symptoms and age (greater in participants between 18 and 30 years old than in those older than 45 years, P < .001), primary activity (greater in studying from home and remote working, P < .001), and extended periods of electronic device use (greater when used more than 10 h/d, P = .05). Symptoms were also associated with time spent outdoors (greater in participants with <1 h/d, P = .02). CONCLUSIONS: The lockdown due to COVID-19 showed an increase in the electronic device use. Participants who spent more time with electronic devices and less time outdoors reported more computer vision syndrome-related eye symptoms.


Subject(s)
COVID-19 , Adolescent , Adult , Aged , Communicable Disease Control , Computers , Humans , Middle Aged , SARS-CoV-2 , Vision Disorders , Young Adult
7.
Int J Environ Res Public Health ; 18(19)2021 09 23.
Article in English | MEDLINE | ID: covidwho-1463630

ABSTRACT

The purpose of this paper is to describe the protocol for the design, implementation, and evaluation of an animation- versus text-based computer tailoring game intervention aimed at preventing alcohol consumption and binge drinking (BD) in adolescents. A cluster-randomized controlled trial (CRCT) is carried out in students aged 14-19 enrolled in 24 high schools from Andalusia (Spain), which are randomized either to experimental (EC-1, EC-2) or waiting-list control conditions (CC). EC-1 receives an online intervention (Alerta Alcohol) with personalized health advice, using textual feedback and several gamification techniques. EC-2 receives an improved version (Alerta Alcohol 2.0) using animated videos and new gamification strategies. Both programs consist of nine sessions (seven taking place at high school and two at home): session 1 or baseline, sessions 2 and 3 that provide tailored advice based on the I-Change Model; sessions 4, 5, 7, and 8 are booster sessions, and sessions 6 and 9 are follow-up questionnaires at six and twelve months. The CC completes the baseline and the evaluation questionnaires. The primary outcome is BD within 30 days before post-test evaluations, and as secondary outcomes we assess other patterns of alcohol use. The findings should help the development of future alcohol drinking prevention interventions in adolescents.


Subject(s)
Binge Drinking , Text Messaging , Adolescent , Alcohol Drinking/prevention & control , Binge Drinking/prevention & control , Computers , Ethanol , Humans , Randomized Controlled Trials as Topic
8.
Sensors (Basel) ; 20(21)2020 Oct 22.
Article in English | MEDLINE | ID: covidwho-1450862

ABSTRACT

Empowered by the ubiquitous sensing capabilities of Internet of Things (IoT) technologies, smart communities could benefit our daily life in many aspects. Various smart community studies and practices have been conducted, especially in China thanks to the government's support. However, most intelligent systems are designed and built individually by different manufacturers in diverging platforms with different functionalities. Therefore, multiple individual systems must be deployed in a smart community to have a set of functions, which could lead to hardware waste, high energy consumption and high deployment cost. More importantly, current smart community systems mainly focus on the technologies involved, while the effects of human activity are neglected. In this paper, a fourth-order tensor model representing object, time, location and human activity is proposed for human-centered smart communities, based on which a unified smart community system is designed. Thanks to the powerful data management abilities of a high-order tensor, multiple functions can be integrated into our system. In addition, since the tensor model embeds human activity information, complex functions could be implemented by exploring the effects of human activity. Two exemplary applications are presented to demonstrate the flexibility of the proposed unified fourth-order tensor-based smart community system.


Subject(s)
Computers , Technology , China , Environment Design , Human Activities , Humans , Internet of Things
9.
Front Cell Infect Microbiol ; 11: 594577, 2021.
Article in English | MEDLINE | ID: covidwho-1444038

ABSTRACT

Since the beginning of the COVID-19 pandemic, important health and regulatory decisions relied on SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR) results. Our diagnostic laboratory faced a rapid increase in the number of SARS-CoV-2 RT-PCR. To maintain a rapid turnaround time, we moved from a case-by-case validation of RT-PCR results to an automated validation and immediate results transmission to clinicians. A quality-monitoring tool based on a homemade algorithm coded in R was developed, to preserve high quality and to track aberrant results. We present the results of this quality-monitoring tool applied to 35,137 RT-PCR results. Patients tested several times led to 4,939 pairwise comparisons: 88% concordant and 12% discrepant. The algorithm automatically solved 428 out of 573 discrepancies. The most likely explanation for these 573 discrepancies was related for 44.9% of the situations to the clinical evolution of the disease, 27.9% to preanalytical factors, and 25.3% to stochasticity of the assay. Finally, 11 discrepant results could not be explained, including 8 for which clinical data was not available. For patients repeatedly tested on the same day, the second result confirmed a first negative or positive result in 99.2% or 88.9% of cases, respectively. The implemented quality-monitoring strategy allowed to: i) assist the investigation of discrepant results ii) focus the attention of medical microbiologists onto results requiring a specific expertise and iii) maintain an acceptable turnaround time. This work highlights the high RT-PCR consistency for the detection of SARS-CoV-2 and the necessity for automated processes to handle a huge number of microbiological results while preserving quality.


Subject(s)
COVID-19 , SARS-CoV-2 , Computers , Humans , Pandemics , Reverse Transcriptase Polymerase Chain Reaction , Sensitivity and Specificity
10.
Int J Environ Res Public Health ; 18(18)2021 09 21.
Article in English | MEDLINE | ID: covidwho-1430876

ABSTRACT

BACKGROUND: Adolescents and ethnic subgroups have been identified at high risks of overweight and its associated complications. Although some studies have investigated overweight, obesity, nutritional status, physical activity, and associated factors among Saudi students, no studies have examined these characteristics among non-Saudi students or compared non-Saudi to Saudi adolescent students. The objective of this study was to compare differences between Saudi and non-Saudi adolescent students regarding time spent watching television, using computers, engaging in physical activity, and their food preferences. The relationships between these lifestyle behaviors and body mass index by Saudi nativity and gender were tested. METHODS: Students aged 12 to 18 years (n = 214) from various schools in Riyadh, Saudi Arabia, completed a self-administered questionnaire that included questions about demographic and anthropometric characteristics, daily after-school routine, physical activity, watching television, using computers, and food preferences. Non-parametric (Mann-Whitney U) tests assessed the statistical differences between Saudi and non-Saudi respondents, and males and females were separately tested. RESULTS: Saudi boys who reported physical activity two to five times per week, the most television time, the most computer time, and the highest frequency of eating fast food and drinking soft drinks had a significantly higher mean body mass index than the non-Saudi boys in their categories. However, there were no significant differences found between the Saudi and non-Saudi girls. CONCLUSIONS: High levels of sedentary and low levels of physical activities as well as high consumption of high-fat fast foods and high-sugar drinks threaten the health of Saudi adolescents. Cultural differences in lifestyle between Saudi and non-Saudi families should be considered when developing programs to improve knowledge, attitudes, and behaviors regarding diet quality and physical activity. The objective of this study is more important in the current situation where increased time spent on computers and mobile phones due to online teaching in schools or working from home, decreased physical activity due to precautionary lockdowns, and unchecked eating patterns while spending more time in sedentary activities in homes has become our COVID-19 pandemic lifestyle in all the age groups. A similar study should be replicated on a large scale to study the effect of this lifestyle on our lives in all the age groups.


Subject(s)
COVID-19 , Food Preferences , Adolescent , Body Mass Index , Communicable Disease Control , Computers , Cross-Sectional Studies , Exercise , Feeding Behavior , Female , Humans , Male , Pandemics , SARS-CoV-2 , Saudi Arabia , Sedentary Behavior , Television
11.
PLoS One ; 16(9): e0257480, 2021.
Article in English | MEDLINE | ID: covidwho-1406757

ABSTRACT

PURPOSE: The outbreak of coronavirus disease 2019 (COVID-19) has caused many children to stay indoors. Increased near work and insufficient outdoor activities are considered important risk factors for myopic progression. This study aimed to compare the changes in myopic progression before and after COVID-19 in children treated with low-concentration atropine. METHODS: The records of 103 eyes of 103 children who were treated with low-concentration atropine eye drops were retrospectively reviewed. We classified children according to the concentration of atropine eye drops and children's age. The beginning of the pre-COVID-19 period was set from January 2019 to May 2019, and the endpoint was set in March 2020. The beginning of the post-COVID-19 period was set in March 2020, and the endpoint was set from January 2021 to March 2021. We evaluated the questionnaires administered to children's parents. RESULTS: A significant myopic progression was observed in the post-COVID-19 period compared to the pre-COVID-19 period in the 0.05% and 0.025% atropine groups (P < 0.001 and P = 0.020, respectively). For children aged 5 to 7 and 8 to 10 years, the axial elongations were significantly faster in the post-COVID-19 period than in the pre-COVID-19 period (P = 0.022 and P = 0.005, respectively). However, the rates of axial elongation and myopic progression were not significantly different between pre- and post-COVID-19 in children aged 11 to 15 years (P = 0.065 and P = 0.792, respectively). The average time spent using computers and smartphones and reading time were significantly increased, and the times of physical and outdoor activity were significantly decreased in the post-COVID-19 period compared to the pre-COVID-19 period. CONCLUSIONS: The rates of myopic progression have increased substantially after the spread of COVID-19 with an increase in the home confinement of children. Therefore, it is necessary to control the environmental risk factors for myopia, even in children undergoing treatment for the inhibition of myopic progression.


Subject(s)
Atropine/administration & dosage , COVID-19/prevention & control , Myopia/drug therapy , Adolescent , Atropine/therapeutic use , COVID-19/epidemiology , Child , Communicable Disease Control , Computers , Humans , Myopia/epidemiology , Ophthalmic Solutions , Pandemics , Republic of Korea/epidemiology , Retrospective Studies , Risk Factors , Smartphone
12.
Int J Environ Res Public Health ; 18(17)2021 08 30.
Article in English | MEDLINE | ID: covidwho-1390607

ABSTRACT

Quarantines imposed due to COVID-19 have forced the rapid implementation of e-learning, but also increased the rates of anxiety, depression, and fatigue, which relate to dramatically diminished e-learning motivation. Thus, it was deemed significant to identify e-learning motivating factors related to mental health. Furthermore, because computer programming skills are among the core competencies that professionals are expected to possess in the era of rapid technology development, it was also considered important to identify the factors relating to computer programming learning. Thus, this study applied the Learning Motivating Factors Questionnaire, the Patient Health Questionnaire-9 (PHQ-9), the Generalized Anxiety Disorder Scale-7 (GAD-7), and the Multidimensional Fatigue Inventory-20 (MFI-20) instruments. The sample consisted of 444 e-learners, including 189 computer programming e-learners. The results revealed that higher scores of individual attitude and expectation, challenging goals, clear direction, social pressure, and competition significantly varied across depression categories. The scores of challenging goals, and social pressure and competition, significantly varied across anxiety categories. The scores of individual attitude and expectation, challenging goals, and social pressure and competition significantly varied across general fatigue categories. In the group of computer programming e-learners: challenging goals predicted decreased anxiety; clear direction and challenging goals predicted decreased depression; individual attitude and expectation predicted diminished general fatigue; and challenging goals and punishment predicted diminished mental fatigue. Challenging goals statistically significantly predicted lower mental fatigue, and mental fatigue statistically significantly predicted depression and anxiety in both sample groups.


Subject(s)
COVID-19 , Computer-Assisted Instruction , Anxiety , Computers , Depression/epidemiology , Humans , SARS-CoV-2
13.
Nucleic Acids Res ; 49(W1): W425-W430, 2021 07 02.
Article in English | MEDLINE | ID: covidwho-1387966

ABSTRACT

Methods for estimating the quality of 3D models of proteins are vital tools for driving the acceptance and utility of predicted tertiary structures by the wider bioscience community. Here we describe the significant major updates to ModFOLD, which has maintained its position as a leading server for the prediction of global and local quality of 3D protein models, over the past decade (>20 000 unique external users). ModFOLD8 is the latest version of the server, which combines the strengths of multiple pure-single and quasi-single model methods. Improvements have been made to the web server interface and there has been successive increases in prediction accuracy, which were achieved through integration of newly developed scoring methods and advanced deep learning-based residue contact predictions. Each version of the ModFOLD server has been independently blind tested in the biennial CASP experiments, as well as being continuously evaluated via the CAMEO project. In CASP13 and CASP14, the ModFOLD7 and ModFOLD8 variants ranked among the top 10 quality estimation methods according to almost every official analysis. Prior to CASP14, ModFOLD8 was also applied for the evaluation of SARS-CoV-2 protein models as part of CASP Commons 2020 initiative. The ModFOLD8 server is freely available at: https://www.reading.ac.uk/bioinf/ModFOLD/.


Subject(s)
Computers , Models, Molecular , Neural Networks, Computer , Protein Conformation , Protein Folding , Proteins/chemistry , Software , Reproducibility of Results , Research Design , SARS-CoV-2/chemistry , Viral Proteins/chemistry
14.
Invest Ophthalmol Vis Sci ; 62(10): 37, 2021 08 02.
Article in English | MEDLINE | ID: covidwho-1379697

ABSTRACT

Purpose: To investigate the effect of home quarantine during the COVID-19 pandemic on myopia progression in children and its associated factors. Methods: Myopic children aged 7 to 12 years with regular follow-up visits every half a year from April 2019 to May 2020 were included. Cycloplegic refraction was measured at baseline and at two follow-up visits. The first follow-up visit (visit 1) was conducted before the COVID-19 home quarantine, whereas the second (visit 2) was four months after the home quarantine. Myopia progression at visits 1 and 2 were compared. Factors associated with changes in myopia progression were tested with a multiple regression analysis. Results: In total, 201 myopic children were enrolled. There was a significantly greater change in spherical equivalent at visit 2 (-0.98 ± 0.52 D) than at visit 1 (-0.39 ± 0.58 D; P < 0.001). Students were reported to have spent more time on digital devices for online learning (P < 0.001) and less time on outdoor activities (P < 0.001) at visit 2 than at visit 1. Children using television and projectors had significantly less myopic shift than those using tablets and mobile phones (P < 0.001). More time spent on digital screens (ß = 0.211, P < 0.001), but not less time on outdoor activities (ß = -0.106, P = 0.110), was associated with greater myopia progression at visit 2. Conclusions: Changes in behavior and myopic progression were found during the COVID-19 home quarantine. Myopic progression was associated with digital screen use for online learning, but not time spent on outdoor activities. The projector and television could be better choices for online learning.


Subject(s)
COVID-19/epidemiology , Computers/statistics & numerical data , Education, Distance/statistics & numerical data , Myopia/diagnosis , Myopia/epidemiology , Quarantine/statistics & numerical data , SARS-CoV-2 , Child , China/epidemiology , Computer Terminals , Disease Progression , Female , Humans , Male , Refraction, Ocular/physiology , Risk Factors , Screen Time , Surveys and Questionnaires
16.
Front Public Health ; 9: 696036, 2021.
Article in English | MEDLINE | ID: covidwho-1325589

ABSTRACT

Purpose: To compare the prevalence of computer vision syndrome in university students of different teaching modes during the SARS-CoV-2 outbreak period. Methods: A cross-sectional survey study using the validated Computer Vision Syndrome Questionnaire in Chinese medical students of Sichuan University who took classroom lectures and the same-grade foreign students from a Bachelor of Medicine and Bachelor of Surgery (MBBS) program who took online lectures with similar schedules. Results: A total of 137 responses from 63 Chinese students and 74 MBBS students were obtained. The highest frequency of digital screen time was 7-9 h (43.24%, 32/74) for MBBS students and 2-4 h (46.03%, 29/63) for Chinese students. The prevalence of computer vision syndrome among Chinese students and MBBS students were 50.79% and 74.32%, respectively (P = 0.004). The average numbers of reported symptoms were 5.00 ± 2.17 in Chinese students and 5.91 ± 1.90 in MBBS students (P = 0.01). The three most highly reported symptoms were "heavy eyelids" (53.97%), "dryness" (50.79%), and "feeling of a foreign body" (46.03%) in Chinese students and "dryness" (72.97%), "feeling of a foreign body" (62.16%), and "heavy eyelids" (58.11%) in MBBS students. The sum grades of computer vision syndrome had a moderate positive correlation with screen time (Spearman's correlation coefficient = 0.386, P < 0.001). The grades of symptoms of "feeling of a foreign body," "heavy eyelids," and "dryness" showed a weak positive correlation with screen time (Spearman's correlation coefficients were 0.220, 0.205, and 0.230, respectively). Conclusion: Online study may contribute to the prevalence of computer vision syndrome among university students.


Subject(s)
COVID-19 , Students, Medical , Computers , Cross-Sectional Studies , Disease Outbreaks , Humans , SARS-CoV-2 , Universities
17.
Int J Environ Res Public Health ; 18(14)2021 07 10.
Article in English | MEDLINE | ID: covidwho-1323230

ABSTRACT

An aging population and a digital society are realities. There is a need to equip older people with knowledge and computer skills so that they can participate in society, without feeling excluded or being marginalized. Third age universities are organizations around the world that specialize in teaching and learning for senior students in a more informal and more integrated way than other educational institutions. The objective of this study was to identify the existing quality publications that deal with the subject of computer education at senior universities. The SCOPUS and Web of Science databases were used, and 18 records were found according to the adopted criteria. It was found that these articles, depending on their focus, can be divided into four groups: educators, organizations/directors, students, and conceptual/review papers. Through these articles, it was possible to draw a picture of what older people's computer learning is like, what barriers exist for students to not be able to attend these classes, as well as tips on how courses should be organized and the pedagogical methodologies that must be adopted. It is intended that this article is used as a good tool for people who work in teaching information technology to the elderly, and especially for course directors who intend to create or reformulate courses of this type for this specific age group.


Subject(s)
Learning , Universities , Aged , Computers , Educational Status , Humans , Students
18.
Ann Palliat Med ; 10(7): 7329-7339, 2021 Jul.
Article in English | MEDLINE | ID: covidwho-1311480

ABSTRACT

BACKGROUND: This study aimed to build a radiomics model with deep learning (DL) and human auditing and examine its diagnostic value in differentiating between coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP). METHODS: Forty-three COVID-19 patients, whose diagnoses had been confirmed with reverse-transcriptase polymerase-chain-reaction (RT-PCR) tests, and 60 CAP patients, whose diagnoses had been confirmed with sputum cultures, were enrolled in this retrospective study. The candidate regions of interest (ROIs) on the computed tomography (CT) images of the 103 patients were determined using a DL-based segmentation model powered by transfer learning. These ROIs were manually audited and corrected by 3 radiologists (with an average of 12 years of experience; range 6-17 years) to check the segmentation acceptance for the radiomics analysis. ROI-derived radiomics features were subsequently extracted to build the classification model and processed using 4 different algorithms (L1 regularization, Lasso, Ridge, and Z test) and 4 classifiers, including the logistic regression (LR), multi-layer perceptron (MLP), support vector machine (SVM), and extreme Gradient Boosting (XGboost). A receiver operating characteristic curve (ROC) analysis was conducted to evaluate the performance of the model. RESULTS: Quantitative CT measurements derived from human-audited segmentation results showed that COVID-19 patients had significantly decreased numbers of infected lobes compared to patients in the CAP group {median [interquartile range (IQR)]: 4 [3, 4] and 4 [4, 5]; P=0.031}. The infected percentage (%) of the whole lung was significantly more elevated in the CAP group [6.40 (2.77, 11.11)] than the COVID-19 group [1.83 (0.65, 4.42); P<0.001], and the same trend applied to each lobe, except for the superior lobe of the right lung [1.81 (0.09, 5.28) for COVID-19 vs. 1.32 (0.14, 7.02) for CAP; P=0.649]. Additionally, the highest proportion of infected lesions were observed in the CT value range of (-470, -370) Hounsfield units (HU) in the COVID-19 group. Conversely, the CAP group had a value range of (30, 60) HU. Radiomic model using corrected ROIs exhibited the highest area under ROC (AUC) of 0.990 [95% confidence interval (CI): 0.962-1.000] using Lasso for feature selection and MLP for classification. CONCLUSIONS: The proposed radiomics model based on human-audited segmentation made accurate differential diagnoses of COVID-19 and CAP. The quantification of CT measurements derived from DL could potentially be used as effective biomarkers in current clinical practice.


Subject(s)
COVID-19 , Deep Learning , Computers , Humans , Retrospective Studies , SARS-CoV-2
19.
Anat Sci Educ ; 14(5): 536-551, 2021 Sep.
Article in English | MEDLINE | ID: covidwho-1300365

ABSTRACT

In early 2020, the Covid-19 crisis forced medical institutions worldwide to convert quickly to online platforms for content delivery. Although many components of medical education were adaptable to that format, anatomical dissection laboratory lost substantial content in that conversion, including features of active student participation, three-dimensional spatial relationships of structures, and the perception of texture, variation, and scale. The present study aimed to develop and assess online anatomy laboratory sessions that sought to preserve benefits of the dissection experience for first-year medical students. The online teaching package was based on a novel form of active videography that emulates eye movement patterns that occur during processes of visual identification, scene analysis, and learning. Using this video-image library of dissected materials, content was presented through asynchronous narrated laboratory demonstrations and synchronous/active video conference sessions and included a novel, video-based assessment tool. Data were obtained using summative assessments and a final course evaluation. Test scores for the online practical examination were significantly improved over those for previous in-person dissection-based examinations, as evidenced by several measures of performance (Mean: 2015-2019: 82.5%; 2020: 94.9%; P = 0.003). Concurrently, didactic test scores were slightly, but not significantly, improved (Mean: 2015-2019: 88.0%; 2020: 89.9%). Student evaluations of online sessions and overall course were highly positive. Results indicated that this innovative online teaching package can provide an effective alternative when in-person dissection laboratory is unavailable. Although this approach consumed considerable faculty time for video editing, further development will include video conference breakout rooms to emulate dissection small-group teamwork.


Subject(s)
Anatomy , COVID-19 , Education, Medical, Undergraduate , Students, Medical , Anatomy/education , Cadaver , Computers , Curriculum , Educational Measurement , Humans , SARS-CoV-2 , Teaching
20.
J Med Internet Res ; 23(2): e21037, 2021 02 22.
Article in English | MEDLINE | ID: covidwho-1256225

ABSTRACT

BACKGROUND: Facial expressions require the complex coordination of 43 different facial muscles. Parkinson disease (PD) affects facial musculature leading to "hypomimia" or "masked facies." OBJECTIVE: We aimed to determine whether modern computer vision techniques can be applied to detect masked facies and quantify drug states in PD. METHODS: We trained a convolutional neural network on images extracted from videos of 107 self-identified people with PD, along with 1595 videos of controls, in order to detect PD hypomimia cues. This trained model was applied to clinical interviews of 35 PD patients in their on and off drug motor states, and seven journalist interviews of the actor Alan Alda obtained before and after he was diagnosed with PD. RESULTS: The algorithm achieved a test set area under the receiver operating characteristic curve of 0.71 on 54 subjects to detect PD hypomimia, compared to a value of 0.75 for trained neurologists using the United Parkinson Disease Rating Scale-III Facial Expression score. Additionally, the model accuracy to classify the on and off drug states in the clinical samples was 63% (22/35), in contrast to an accuracy of 46% (16/35) when using clinical rater scores. Finally, each of Alan Alda's seven interviews were successfully classified as occurring before (versus after) his diagnosis, with 100% accuracy (7/7). CONCLUSIONS: This proof-of-principle pilot study demonstrated that computer vision holds promise as a valuable tool for PD hypomimia and for monitoring a patient's motor state in an objective and noninvasive way, particularly given the increasing importance of telemedicine.


Subject(s)
Parkinson Disease/complications , Vision, Ocular/physiology , Adult , Aged , Aged, 80 and over , Algorithms , Computers , Female , Humans , Male , Middle Aged , Neurologic Examination , Parkinson Disease/physiopathology , Pilot Projects
SELECTION OF CITATIONS
SEARCH DETAIL
...