ABSTRACT
Objectives: COVID 19 and increasing unmet needs of health technology had accelerated an adoption of digital health globally and the major categories are mobile-health, health information technology, telemedicine. Digital health interventions have various benefit on clinical efficacy, quality of care and reducing healthcare costs. The objective of the study is to identify new reimbursement policy trend of digital health medical devices in South Korea. Method(s): Official announcements published in national bodies and supplementary secondary research were used to capture policies, frameworks and currently approved products since 2019. Result(s): With policy development, several digital health devices and AI software have been introduced as non-reimbursement by utilizing new Health Technology Assessment (nHTA) pathway including grace period of nHTA and innovative medical devices integrated assessment pathway. AI based cardiac arrest risk management software (DeepCARS) and electroceutical device for major depressive disorders (MINDD STIM) have been approved as non-reimbursement use for about 3 years. Two digital therapeutics for insomnia and AI software for diagnosis of cerebral infarction were approved as the first innovative medical devices under new integrated assessment system, and they could be treated in the market. In addition, there is remote patient monitoring (RPM) reimbursement service fee. Continuous glucose monitoring devices have been reimbursed for type 1 diabetes patients by the National Health Insurance Service (NHIS) since January 2019. Homecare RPM service for peritoneal dialysis patients with cloud platform (Sharesource) has been reimbursed since December 2019, and long-term continuous ECG monitoring service fee for wearable ECG monitoring devices (ATpatch, MEMO) became reimbursement since January 2022. Conclusion(s): Although Korean government has been developed guidelines for digital health actively, only few products had been reimbursed. To introduce new technologies for improved patient centric treatment, novel value-based assessment and new pricing guideline of digital health medical devices are quite required.Copyright © 2023
ABSTRACT
Objectives: Reverse transcription and real-time polymerase chain reaction (RT-qPCR) based on the SARS-CoV-2 viral RNA demonstration is the gold standard in diagnosis. Data files obtained from PCR devices should be analysed by a specialist physician and results should be transferred to Laboratory Information Management System (LIMS). CAtenA Smart PCR (Ventura, Ankara, Turkiye) program is a local bioinformatics software that assess PCR data files with artificial intelligence, submits to expert approval and transfers the approved results to LIMS. The aim of this study is to investigate its accuracy and matching success rate with expert analysis. Method(s): A total of 9400 RT-qPCR test results studied in Ankara Provincial Health Directorate Public Health Molecular Diagnosis Laboratory were compared with respect to expert evaluation and CAtenA results. Result(s): It was determined that the preliminary evaluation results of the CAtenA matched 86% of the negative and 90% of the positive results provided by expert analysis. 987 tests which CAtenA determined as inconclusive and suggested repeating PCR were found either negative or positive by expert analysis. A significant difference between positive and negative matching success rates and artificial intelligence (AI) based software overall accuracy was found and associated with the missed tests of the AI. Conclusion(s): As a result, it was suggested there is a low risk of confirming false positive results without expert analysis and test repetitions would cause losing time along with extra test costs. It was agreed that the PCR analysis used in CAtenA should be improved particularly in terms of test repetitions.Copyright © 2023 by Prusa Medical Publishing.
ABSTRACT
Background: Describe the experience and results of the use of a digital platform navigated by the MAIA artificial intelligence engine for epidemiological surveillance in the department of Magdalena, Colombia, during the public health emergency generated by the Covid-19 disease pandemic in the period July 30 to December 8, 2020. Method(s): The MAIA digital platform was adapted to extract data from Covid-19 cases from the different health institutions distributed in the municipalities of the department of Magdalena. This information is then transformed through the platform into dynamic digital dashboards with 24/7 functionality, which allowed the visualization of descriptive information, trend curves and geolocation to facilitate decision-making in public health during the operating time. Satisfaction and utility surveys of the use of the platform called "MAIA DATA CRUE CENTRO REGULACION DE URGENCIAS Y EMERGENCIAS" (MAIA DATA CRUE) designed by MEDZAIO were carried out to know the perception of users. Result(s): Currently 58 health institutions from 27 municipalities of Magdalena are using the MAIA digital platform, in more than 4 months of operation a daily use of 100% has been achieved, with information extraction every 12 hours and continuous display of information throughout the period of use. More than 1200 records have been received, which have served to consolidate live information, with which daily health decisions have been made by the Magdalena COVID-19 pandemic regulatory center, optimizing the installed hospital and ICU capacity. 100% of those surveyed agree that this type of tool should continue to be used as epidemiological surveillance in COVID-19. Conclusion(s): The adaptation and use of digital platforms such as MAIA DATA CRUE CENTRO DE REGULACIONES DE URGENCIAS Y EMERGENCIAS, is an application of digital epidemiology for the intelligent management of diseases. This article demonstrates the importance of using digital tools supported by artificial intelligence to optimize the capacities of health systems regarding the different dimensions, in this case epidemiological surveillance and public health.Copyright © 2022 Asociacion Colombiana de Infectologia. All rights reserved.
ABSTRACT
Early detection of COVID-19 infection, followed by appropriate patient management, has the potential to reduce costs related to developing severe forms of the disease, as well as spreading of the disease, if left undetected. Our objective was to evaluate the impact of an AI-based chest CT analysis software (icolung, icometrix) for the detection and prognosis of COVID-19 cases in patients receiving a CT scan in a hospital setting in Belgium. We developed a decision analytic model comparing routine practice scenario where patients receiving a CT scan in the hospital are not screened for COVID-19 with a scenario where icolung is used to analyze CT scans for the detection and prognosis of COVID-19 cases. We evaluated the impact of the technology in preventing the further spreading of the infection in the community and in reducing the length of hospitalization of COVID-19 patients. In the base case using a relatively low COVID-19 prevalence of 0.36%, icolung is cost-effective in preventing COVID19 transmission in the community, costing 8.221 to prevent one infection. At low prevalence of the disease and low risk of hospitalization, the technology is not cost-effective in reducing the length of hospitalization. However, icolung may be cost-effective in situations with high disease prevalence (>30%) or high risk of hospitalization (>6%) such as patients suffering from chronic oncological diseases and benefiting from recurring thoracic imaging. This model provides initial evidence of cost-effectiveness of AI-based chest CT analysis software and may help to provide guidance regarding further health care research and policy.
ABSTRACT
Background: Poor prognosis of lung cancer is linked to its late diagnosis, typically in the advanced stage 4 in 50-70% of incidental cases. Lung Cancer Screening Programs provide low-dose lung CT screening to current and former smokers who are at high risk for developing this disease. Greece is an EU country, returning strong from a long period of economic recession, ranked 2nd place in overall age-standardized tobacco smoking prevalence in the EU. In December 2020, at the Metropolitan Hospital of Athens, we started the 1st Screening Program in the country. We present our initial results and pitfalls met. Method(s): A weekly outpatient clinic offers consultation to possible candidates. LDCT (<=3.0mGy), Siemens VIA, Artificial Intelligence multi-computer-aided diagnosis (multi-CAD) system and LungRADS (v.1.1) are used for the validation of any abnormal findings with semi-auto measurement of volume and volume doubling time. Patients get connected when necessary with the smoking cessation and Pulmonology clinic. USPSTF guidelines are used, (plus updated version). Abnormal CT findings are discussed by an MDT board with radiologists, pulmonologists/interventional pulmonologists, oncologists and thoracic surgeons. A collaboration with Fairlife Lung Cancer Care the first non-profit organization in Greece is done, in order to offer the program to population with low income too. An advertisement campaign was organized to inform family doctors and the people about screening programs, together with an anti-tobacco campaign. Result(s): 106 people were screened, 74 males & 32 females (mean age 62yo), 27/106 had an abnormal finding (25%). 2 were diagnosed with a resectable lung cancer tumor (primary adenocarcinoma) of early-stage (1.8%). 2 with extended SCLC (lung lesion & mediastinal adenopathy). 1 with multiple nodules (pancreatic cancer not known until then). 3 patients with mediastinal and hilar lymphadenopathy (2 diagnosed with lymphoma, 1 with sarcoidosis). 19 patients were diagnosed with pulmonary nodules (RADS 2-3, 17%) - CT follow up algorithm. Conclusion(s): We are presenting our initial results, from the first lung cancer screening program in Greece. Greece represents a country many smokers, who also started smoking at a young age, with a both public and private health sector, returning from a long period of economic recession. COVID-19 pandemia has cause practical difficulties along the way. LDCT with AI software, with an MDT board and availability of modern diagnostic and therapeutic alternatives should be considered as essential. A collaboration spirit with other hospitals around the country is being built, in order to share current experience and expertise. Copyright © 2022
ABSTRACT
Purpose : The COVID-19 pandemic exposed the need for increased mobilization of teleophthalmology resources. Artificial intelligence (AI) may serve as a tool to assist physicians in triaging highest need patients if the AI's assessment of disease is comparable to the physician's assessment. This study assesses the ability of AI software to diagnose diabetic retinopathy (DR) as compared to Tele-ophthalmology and in-person examination by a retina specialist. Methods : Records of forty patients (average age 55.1±10.9 years) presenting to an urban retina clinic were reviewed retrospectively for factors including demographics, retinal photos taken by Canon CR-2 Plus AF Retinal Imaging camera (Tokyo, Japan), and diagnosis of DR based on the International Clinical Diabetic Retinopathy (ICDR) classification scale during an in-person clinic visit in which a fundus exam was performed. Retinal photos were graded by AI software, EyeArt (EyeNuk, CA), as Normal, Mild DR, or More than Mild DR. Retinal images were also graded remotely by a retina specialist using the ICDR classification scale via TeamViewer software (Tele). Agreement between Tele, AI, and inperson DR diagnosis was assessed using Cohen's Kappa (κ) coefficient using IBM® SPSS® Statistics software. Results : Among 80 eyes, 33 were diagnosed in-person with no DR, 5 with mild nonproliferative DR (NPDR), 9 with moderate NPDR, 3 with severe NPDR, 7 with proliferative diabetic retinopathy (PDR), and 23 with regressed PDR. Eleven and 26 eyes could not be graded by Tele or AI, respectively. κ±SE for in-Person diagnosis vs Tele was 0.859±0.058 (p<.001), in-person vs AI was 0.751±0.082 (p<.001), and Tele vs AI was 0.883±0.063 (p<.001). Conclusions : AI is a reliable tool for screening patients for DR and referring them for physician evaluation since AI had a substantial rate of agreement with the in-person diagnosis and near perfect agreement with Tele. Tele grading was in near perfect agreement with the in-person diagnosis, showing that Tele is a reliable option for a physician to remotely screen patients that may be ungradable by AI. However, improvements are needed due to the high number of images that are ungradable via Tele and AI. Further studies should assess ways to reduce the number of ungradable images via Tele and AI and create a trend analysis for multiple visits for a given patient.
ABSTRACT
Purpose : Age-related macular degeneration (AMD) is projected to affect an average of 1.23 million individuals by the 2050. Whilst anti-VEGF treatment for neovascular AMD (nvAMD) is considered the current gold-standard care, this requires regular monitoring and treatment delivery which causes increased capacity challenges. This, along with the current COVID-19 pandemic, have highlighted the need for efficient and safe ways to diagnose and manage nvAMD. The use of artificial intelligence (AI) in medical care has the potential to alleviate some of this projected pressure facing eye clinics. Previous research has shown that AI has comparable sensitivity and specificity to clinicians in identifying ocular disorders from retinal images. The purpose of the current study was to develop and AI model to identify active from inactive nvAMD disease from retinal SD-OCT images. Methods : Using Google's Vision AutoML software, 1058 Heidelberg SD-OCT images were identified and labelled as either showing nvAMD activity or inactivity. All images were uploaded to Google's cloud storage and automatically assigned two bounding-box labels;1 label capturing the entire Heidelberg SD-OCT image, including the raster and b-scan, with the second capturing the b-scan only. All labels were automatically allocated to either a train, validate or test group based on an 80:10:10 ratio set by the software. Results : Of the 1058 images, a total of 2116 labels were assigned, 1012 showing active and 1104 showing inactive nvAMD. Performance of the AI model revealed an area under the precision recall curve (AUPRC) of 0.84 at a threshold of 0.5, specificity of 40.98% and sensitivity of 95.24%. For the active-only images, the specificity was 34.28% with a sensitivity of 97%. For the inactive-only images, the specificity was 51% with a sensitivity of 92.73%. Conclusions : Utilising Google's AutoML AI software, this model is able to correctly identify active nvAMD from Heidelberg SD-OCT images with a high level of sensitivity and good overall AUPRC.
ABSTRACT
Fatigue is a known contributor to open water accidents, decreased operational efficiency, and poor Warfighter health. Real-time feedback of the Warfighters cognitive state will allow for increased awareness of capabilities/limitations and adaptable decision making based on Warfighter readiness. The Fatigue Detection/Prediction using Machine Learning (ML) and Wearable Technology project aimed to develop a ML algorithm capable of detecting changes in the Parasympathetic Nervous System (PNS) that are indicative of cognitive fatigue using a Commercial Off-The-Shelf (COTS) wrist-worn device. A biometric dataset of 30 participants (including some active duty personnel) performing quantifiable vigilance tasking was collected and annotated with operator performance metrics and cognitive load. Variations of the Mackworth clock, a vigilance task widely used in psychometric studies to quantify cognitive engagement and fatigue, was used to generate quantitative operator performance metrics and discrete cognitive load states. ML models were trained and validated on the annotated biometric dataset to: 1) regress operator task performance accuracies, and 2) classify cognitive load/task difficulty. A trained Convolution Neural Network (CNN) regression model was able to predict Mackworth Clock task performance accuracy to within a mean absolute error of 2.5 percent. Additionally, a separate CNN classifier model achieved binary task-type classification accuracies of 86.5 percent, with different type tasks corresponding to a higher vs. lower cognitive load. The next phase of this Research and Development (R and D) effort will include additional testing events with Navy-relevant tasking (i.e., ship navigation, track management, and other watch standing tasks) with a participant pool of only active duty personnel.
ABSTRACT
OBJECTIVES: Fast diagnosis of Coronavirus Disease 2019 (COVID-19), and the detection of high-risk patients are crucial but challenging in the pandemic outbreak. The aim of this study was to evaluate if deep learning-based software correlates well with the generally accepted visual-based scoring for quantification of the lung injury to help radiologist in triage and monitoring of COVID-19 patients. MATERIALS AND METHODS: In this retrospective study, the lobar analysis of lung opacities (% opacities) by means of a prototype deep learning artificial intelligence (AI)-based software was compared to visual scoring. The visual scoring system used five categories (0: 0%, 1: 0-5%, 2: 5-25%, 3: 25-50%, 4: 50-75% and 5: >75% involvement). The total visual lung injury was obtained by the sum of the estimated grade of involvement of each lobe and divided by five. RESULTS: The dataset consisted of 182 consecutive confirmed COVID-19 positive patients with a median age of 65 ± 16 years, including 110 (60%) men and 72 (40%) women. There was a correlation coefficient of 0.89 (p < 0.001) between the visual and the AI-based estimates of the severity of lung injury. CONCLUSION: The study indicates a very good correlation between the visual scoring and AI-based estimates of lung injury in COVID-19.