Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 9 de 9
Filter
1.
J Am Med Inform Assoc ; 2022 Apr 15.
Article in English | MEDLINE | ID: covidwho-1795239

ABSTRACT

OBJECTIVE: To combine machine efficiency and human intelligence for converting complex clinical trial eligibility criteria text into cohort queries. MATERIALS AND METHODS: Criteria2Query (C2Q) 2.0 was developed to enable real-time user intervention for criteria selection and simplification, parsing error correction, and concept mapping. The accuracy, precision, recall, and F1 score of enhanced modules for negation scope detection, temporal and value normalization were evaluated using a previously curated gold standard, the annotated eligibility criteria of 1010 COVID-19 clinical trials. The usability and usefulness were evaluated by 10 research coordinators in a task-oriented usability evaluation using 5 Alzheimer's disease trials. Data were collected by user interaction logging, a demographic questionnaire, the Health Information Technology Usability Evaluation Scale (Health-ITUES), and a feature-specific questionnaire. RESULTS: The accuracies of negation scope detection, temporal and value normalization were 0.924, 0.916, and 0.966, respectively. C2Q 2.0 achieved a moderate usability score (3.84 out of 5) and a high learnability score (4.54 out of 5). On average, 9.9 modifications were made for a clinical study. Experienced researchers made more modifications than novice researchers. The most frequent modification was deletion (5.35 per study). Furthermore, the evaluators favored cohort queries resulting from modifications (score 4.1 out of 5) and the user engagement features (score 4.3 out of 5). DISCUSSION AND CONCLUSION: Features to engage domain experts and to overcome the limitations in automated machine output are shown to be useful and user-friendly. We concluded that human-computer collaboration is key to improving the adoption and user-friendliness of natural language processing.

2.
Diagnostics (Basel) ; 12(4)2022 Apr 07.
Article in English | MEDLINE | ID: covidwho-1785560

ABSTRACT

Problem-Since the outbreak of the COVID-19 pandemic, mass testing has become essential to reduce the spread of the virus. Several recent studies suggest that a significant number of COVID-19 patients display no physical symptoms whatsoever. Therefore, it is unlikely that these patients will undergo COVID-19 testing, which increases their chances of unintentionally spreading the virus. Currently, the primary diagnostic tool to detect COVID-19 is a reverse-transcription polymerase chain reaction (RT-PCR) test from the respiratory specimens of the suspected patient, which is invasive and a resource-dependent technique. It is evident from recent researches that asymptomatic COVID-19 patients cough and breathe in a different way than healthy people. Aim-This paper aims to use a novel machine learning approach to detect COVID-19 (symptomatic and asymptomatic) patients from the convenience of their homes so that they do not overburden the healthcare system and also do not spread the virus unknowingly by continuously monitoring themselves. Method-A Cambridge University research group shared such a dataset of cough and breath sound samples from 582 healthy and 141 COVID-19 patients. Among the COVID-19 patients, 87 were asymptomatic while 54 were symptomatic (had a dry or wet cough). In addition to the available dataset, the proposed work deployed a real-time deep learning-based backend server with a web application to crowdsource cough and breath datasets and also screen for COVID-19 infection from the comfort of the user's home. The collected dataset includes data from 245 healthy individuals and 78 asymptomatic and 18 symptomatic COVID-19 patients. Users can simply use the application from any web browser without installation and enter their symptoms, record audio clips of their cough and breath sounds, and upload the data anonymously. Two different pipelines for screening were developed based on the symptoms reported by the users: asymptomatic and symptomatic. An innovative and novel stacking CNN model was developed using three base learners from of eight state-of-the-art deep learning CNN algorithms. The stacking CNN model is based on a logistic regression classifier meta-learner that uses the spectrograms generated from the breath and cough sounds of symptomatic and asymptomatic patients as input using the combined (Cambridge and collected) dataset. Results-The stacking model outperformed the other eight CNN networks with the best classification performance for binary classification using cough sound spectrogram images. The accuracy, sensitivity, and specificity for symptomatic and asymptomatic patients were 96.5%, 96.42%, and 95.47% and 98.85%, 97.01%, and 99.6%, respectively. For breath sound spectrogram images, the metrics for binary classification of symptomatic and asymptomatic patients were 91.03%, 88.9%, and 91.5% and 80.01%, 72.04%, and 82.67%, respectively. Conclusion-The web-application QUCoughScope records coughing and breathing sounds, converts them to a spectrogram, and applies the best-performing machine learning model to classify the COVID-19 patients and healthy subjects. The result is then reported back to the test user in the application interface. Therefore, this novel system can be used by patients in their premises as a pre-screening method to aid COVID-19 diagnosis by prioritizing the patients for RT-PCR testing and thereby reducing the risk of spreading of the disease.

3.
2021 IEEE International Conference on Engineering, Technology and Education, TALE 2021 ; : 755-761, 2021.
Article in English | Scopus | ID: covidwho-1741282

ABSTRACT

The COVID-19 pandemic has brought a tremendous challenge to global society. During the pandemic, education is affected significantly due to school closures. In Hong Kong, the queue for the screening of dyslexia given by the government is longer than a year. Together with the outbreak of COVID-19, manual pre-screening of dyslexia became less accessible. Although there are various digital learning games for dyslexic students to learn Chinese, there is a lack of digital pre-screening tools for dyslexia in the Chinese context. Therefore, we have developed a digital tool to pre-screen dyslexia in Hong Kong. This study aims to examine which handwriting problems reveal symptoms of dyslexia and which characteristics of students are indicative of dyslexia. © 2021 IEEE.

4.
Pattern Recognit ; 127: 108656, 2022 Jul.
Article in English | MEDLINE | ID: covidwho-1740084

ABSTRACT

This study presents the Auditory Cortex ResNet (AUCO ResNet), it is a biologically inspired deep neural network especially designed for sound classification and more specifically for Covid-19 recognition from audio tracks of coughs and breaths. Differently from other approaches, it can be trained end-to-end thus optimizing (with gradient descent) all the modules of the learning algorithm: mel-like filter design, feature extraction, feature selection, dimensionality reduction and prediction. This neural network includes three attention mechanisms namely the squeeze and excitation mechanism, the convolutional block attention module, and the novel sinusoidal learnable attention. The attention mechanism is able to merge relevant information from activation maps at various levels of the network. The net takes as input raw audio files and it is able to fine tune also the features extraction phase. In fact, a Mel-like filter is designed during the training, thus adapting filter banks on important frequencies. AUCO ResNet has proved to provide state of art results on many datasets. Firstly, it has been tested on many datasets containing Covid-19 cough and breath. This choice is related to the fact that that cough and breath are language independent, allowing for cross dataset tests with generalization aims. These tests demonstrate that the approach can be adopted as a low cost, fast and remote Covid-19 pre-screening tool. The net has also been tested on the famous UrbanSound 8K dataset, achieving state of the art accuracy without any data preprocessing or data augmentation technique.

5.
Global Spine J ; : 21925682211057489, 2021 Dec 06.
Article in English | MEDLINE | ID: covidwho-1555250

ABSTRACT

STUDY DESIGN: Retrospective cohort study. OBJECTIVES: The coronavirus disease (COVID-19), caused by the severe respiratory syndrome coronavirus 2 (SARS-CoV-2), has created an unprecedented global public health emergency. The aim of the current study was to report on COVID-19 rates in an asymptomatic population prior to undergoing spine procedures or surgeries at two large Los Angeles healthcare systems. METHODS: Elective spine procedures and surgeries from May 1, 2020 to January 31, 2021 were included. Results from SARS-CoV-2 virus RT-PCR nasopharyngeal testing within 72 hours prior to elective spine procedures were recorded. Los Angeles County COVID-19 rates were calculated using data sets from Los Angeles County Department of Public Health. Chi-squared test and Stata/IC were used for statistical analysis. RESULTS: A total of 4,062 spine procedures and surgeries were scheduled during this time period. Of these, 4,043 procedures and surgeries were performed, with a total of 19 patients testing positive. Nine positive patients were from UCLA, and 10 from USC. The overall rate of positive tests was low at .47% and reflected similarities with Los Angeles County COVID-19 rates over time. CONCLUSIONS: The current study shows that pre-procedure COVID-19 testing rates remains very low, and follows similar patterns of community rates. While pre-procedure testing increases the safety of elective procedures, universal COVID-19 pre-screening adds an additional barrier to receiving care for patients and increases cost of delivering care. A combination of pre-screening, pre-procedure self-quarantine, and consideration of overall community COVID-19 positivity rates should be further studied.

6.
J Korean Med Sci ; 36(42): e295, 2021 Nov 01.
Article in English | MEDLINE | ID: covidwho-1497009

ABSTRACT

BACKGROUND: To minimize nosocomial infection against coronavirus disease 2019 (COVID-19), most hospitals conduct a prescreening process to evaluate the patient or guardian of any symptoms suggestive of COVID-19 or exposure to a COVID-19 patient at entrances of hospital buildings. In our hospital, we have implemented a two-level prescreening process in the outpatient clinic: an initial prescreening process at the entrance of the outpatient clinic (PPEO) and a second prescreening process is repeated in each department. If any symptoms or epidemiological history are identified at the second level, an emergency code is announced through the hospital's address system. The patient is then guided outside through a designated aisle. In this study, we analyze the cases missed in the PPEO that caused the emergency code to be applied. METHODS: All cases reported from March 2020 to April 2021 were analyzed retrospectively. We calculated the incidence of cases missed by the PPEO per 1,000 outpatients and compared the incidence between first-time hospital visitors and those visiting for the second time or more; morning and afternoon office hours; and days of the week. RESULTS: During the study period, the emergency code was applied to 449 cases missed by the PPEO. Among those cases, 20.7% were reported in otorhinolaryngology, followed by 11.6% in gastroenterology, 5.8% in urology, and 5.8% in dermatology. Fever was the most common symptom (59.9%), followed by cough (19.8%). The incidence of cases per 1,000 outpatients was significantly higher among first-time visitors than among those visiting for the second time or more (1.77 [confidence interval (CI), 1.44-2.10] vs. 0.59 [CI, 0.52-0.65], respectively) (P < 0.001). CONCLUSION: Fever was the most common symptom missed by the PPEO, and otorhinolaryngology and gastroenterology most frequently reported missed cases. Cases missed by the PPEO were more likely to occur among first-time visitors than returning visitors. The results obtained from this study can provide insights or recommendations to other healthcare facilities in operating prescreening processes during the COVID-19 pandemic.


Subject(s)
Ambulatory Care Facilities/statistics & numerical data , COVID-19/diagnosis , COVID-19/prevention & control , Cough/etiology , Fever/etiology , Mass Screening/statistics & numerical data , Adolescent , Adult , Aged , Aged, 80 and over , Ambulatory Care , COVID-19/epidemiology , Child , Female , Humans , Incidence , Infection Control , Male , Mass Screening/organization & administration , Middle Aged , Pandemics , Young Adult
7.
World J Clin Cases ; 9(12): 2731-2738, 2021 Apr 26.
Article in English | MEDLINE | ID: covidwho-1215740

ABSTRACT

BACKGROUND: Emerging infectious diseases are a constant threat to the public's health and health care systems around the world. Coronavirus disease 2019 (COVID-2019), which was defined by the World Health Organization as pandemic, has rapidly emerged as a global health threat. Outbreak evolution and prevention of international implications require substantial flexibility of frontline health care facilities in their response. AIM: To explore the effect of the implementation and management strategy of pre-screening triage in children during COVID-19. METHODS: The standardized triage screening procedures included a standardized triage screening questionnaire, setup of pre-screening triage station, multi-point temperature monitoring, extensive screenings, and two-way protection. In order to ensure the implementation of the pre-screening triage, the prevention and control management strategies included training, emergency exercise, and staff protection. Statistical analysis was performed on the data from all the children hospitalized from January 20, 2020 to March 20, 2020 at solstice during the pandemic period. Data were obtained from questionnaires and electronic medical record systems. RESULTS: A total of 17561 children, including 2652 who met the criteria for screening, 192 suspected cases, and two confirmed cases without omission, were screened from January 20, 2020 to March 20, 2020 at solstice during the pandemic period. There was zero transmission of the infection to any medical staff. CONCLUSION: The effective strategies for pre-screening triage have an essential role in the prevention and control of hospital infection.

8.
Inform Med Unlocked ; 20: 100378, 2020.
Article in English | MEDLINE | ID: covidwho-621705

ABSTRACT

BACKGROUND: The inability to test at scale has become humanity's Achille's heel in the ongoing war against the COVID-19 pandemic. A scalable screening tool would be a game changer. Building on the prior work on cough-based diagnosis of respiratory diseases, we propose, develop and test an Artificial Intelligence (AI)-powered screening solution for COVID-19 infection that is deployable via a smartphone app. The app, named AI4COVID-19 records and sends three 3-s cough sounds to an AI engine running in the cloud, and returns a result within 2 min. METHODS: Cough is a symptom of over thirty non-COVID-19 related medical conditions. This makes the diagnosis of a COVID-19 infection by cough alone an extremely challenging multidisciplinary problem. We address this problem by investigating the distinctness of pathomorphological alterations in the respiratory system induced by COVID-19 infection when compared to other respiratory infections. To overcome the COVID-19 cough training data shortage we exploit transfer learning. To reduce the misdiagnosis risk stemming from the complex dimensionality of the problem, we leverage a multi-pronged mediator centered risk-averse AI architecture. RESULTS: Results show AI4COVID-19 can distinguish among COVID-19 coughs and several types of non-COVID-19 coughs. The accuracy is promising enough to encourage a large-scale collection of labeled cough data to gauge the generalization capability of AI4COVID-19. AI4COVID-19 is not a clinical grade testing tool. Instead, it offers a screening tool deployable anytime, anywhere, by anyone. It can also be a clinical decision assistance tool used to channel clinical-testing and treatment to those who need it the most, thereby saving more lives.

SELECTION OF CITATIONS
SEARCH DETAIL