Dataset Information

AI-Based Chest CT Analysis for Rapid COVID-19 Diagnosis and Prognosis: A Practical Tool to Flag High-Risk Patients and Lower Healthcare Costs.

ABSTRACT: Early diagnosis of COVID-19 is required to provide the best treatment to our patients, to prevent the epidemic from spreading in the community, and to reduce costs associated with the aggravation of the disease. We developed a decision tree model to evaluate the impact of using an artificial intelligence-based chest computed tomography (CT) analysis software (icolung, icometrix) to analyze CT scans for the detection and prognosis of COVID-19 cases. The model compared routine practice where patients receiving a chest CT scan were not screened for COVID-19, with a scenario where icolung was introduced to enable COVID-19 diagnosis. The primary outcome was to evaluate the impact of icolung on the transmission of COVID-19 infection, and the secondary outcome was the in-hospital length of stay. Using EUR 20000 as a willingness-to-pay threshold, icolung is cost-effective in reducing the risk of transmission, with a low prevalence of COVID-19 infections. Concerning the hospitalization cost, icolung is cost-effective at a higher value of COVID-19 prevalence and risk of hospitalization. This model provides a framework for the evaluation of AI-based tools for the early detection of COVID-19 cases. It allows for making decisions regarding their implementation in routine practice, considering both costs and effects.

SUBMITTER: Esposito G

PROVIDER: S-EPMC9324628 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

AI-Based Chest CT Analysis for Rapid COVID-19 Diagnosis and Prognosis: A Practical Tool to Flag High-Risk Patients and Lower Healthcare Costs.

Esposito Giovanni G Ernst Benoit B Henket Monique M Winandy Marie M Chatterjee Avishek A Van Eyndhoven Simon S Praet Jelle J Smeets Dirk D Meunier Paul P Louis Renaud R Kolh Philippe P Guiot Julien J

Diagnostics (Basel, Switzerland) 20220701 7

Early diagnosis of COVID-19 is required to provide the best treatment to our patients, to prevent the epidemic from spreading in the community, and to reduce costs associated with the aggravation of the disease. We developed a decision tree model to evaluate the impact of using an artificial intelligence-based chest computed tomography (CT) analysis software (icolung, icometrix) to analyze CT scans for the detection and prognosis of COVID-19 cases. The model compared routine practice where patie ...[more]

PMID: 35885513

Similar Datasets

Project description:Our aim was to develop practical models built with simple clinical and radiological features to help diagnosing Coronavirus disease 2019 [COVID-19] in a real-life emergency cohort. To do so, 513 consecutive adult patients suspected of having COVID-19 from 15 emergency departments from 2020-03-13 to 2020-04-14 were included as long as chest CT-scans and real-time polymerase chain reaction (RT-PCR) results were available (244 [47.6%] with a positive RT-PCR). Immediately after their acquisition, the chest CTs were prospectively interpreted by on-call teleradiologists (OCTRs) and systematically reviewed within one week by another senior teleradiologist. Each OCTR reading was concluded using a 5-point scale: normal, non-infectious, infectious non-COVID-19, indeterminate and highly suspicious of COVID-19. The senior reading reported the lesions' semiology, distribution, extent and differential diagnoses. After pre-filtering clinical and radiological features through univariate Chi-2, Fisher or Student t-tests (as appropriate), multivariate stepwise logistic regression (Step-LR) and classification tree (CART) models to predict a positive RT-PCR were trained on 412 patients, validated on an independent cohort of 101 patients and compared with the OCTR performances (295 and 71 with available clinical data, respectively) through area under the receiver operating characteristics curves (AUC). Regarding models elaborated on radiological variables alone, best performances were reached with the CART model (i.e., AUC = 0.92 [versus 0.88 for OCTR], sensitivity = 0.77, specificity = 0.94) while step-LR provided the highest AUC with clinical-radiological variables (AUC = 0.93 [versus 0.86 for OCTR], sensitivity = 0.82, specificity = 0.91). Hence, these two simple models, depending on the availability of clinical data, provided high performances to diagnose positive RT-PCR and could be used by any radiologist to support, modulate and communicate their conclusion in case of COVID-19 suspicion. Practically, using clinical and radiological variables (GGO, fever, presence of fibrotic bands, presence of diffuse lesions, predominant peripheral distribution) can accurately predict RT-PCR status.

Project description:INTRODUCTION:A study based on the Danish Randomised Controlled Lung Cancer Screening Trial (DLCST) calculated the healthcare costs of lung cancer screening by comparing costs in an intervention group with a control group. Participants in both groups, however, experienced significantly increased negative psychosocial consequences after randomisation. Substantial participation bias has also been documented: The DLCST participants reported fewer negative psychosocial aspects and experienced better living conditions compared with the random sample. OBJECTIVE:To comprehensively analyse the costs of lung cancer CT screening and to determine whether invitations to mass screening alter the utilisation of the healthcare system resulting in indirect costs. Healthcare utilisation and costs are analysed in the primary care sector (general practitioner psychologists, physiotherapists, other specialists, drugs) and the secondary care sector (emergency room contacts, outpatient visits, hospitalisation days, surgical procedures and non-surgical procedures). DESIGN:To account for bias in the original trial, the costs and utilisation of healthcare by participants in DLCST were compared with a new reference group, selected in the period from randomisation (2004-2006) until 2014. SETTING:Four Danish national registers. PARTICIPANTS:DLCST included 4104 current or former heavy smokers, randomly assigned to the CT group or the control group. The new reference group comprised a random sample of 535 current or former heavy smokers in the general Danish population who were never invited to participate in a cancer screening test. MAIN OUTCOME MEASURES:Total healthcare costs including costs and utilisation of healthcare in both the primary and the secondary care sector. RESULTS:Compared with the reference group, the participants in both the CT group (offered annual CT screening, lung function test and smoking counselling) and the control group (offered annual lung function test and smoking counselling) had significantly increased total healthcare costs, calculated at 60% and 48% respectively. The increase in costs was caused by increased use of healthcare in both the primary and the secondary sectors. CONCLUSION:CT screening leads to 60% increased total healthcare costs. Such increase would raise the expected annual healthcare cost per participant from EUR 2348 to EUR 3756. Cost analysis that only includes costs directly related to the CT scan and follow-up procedures most likely underestimates total costs. Our data show that the increased costs are not limited to the secondary sector. TRIAL REGISTRATION NUMBER:NCT00496977.

Dataset Information

AI-Based Chest CT Analysis for Rapid COVID-19 Diagnosis and Prognosis: A Practical Tool to Flag High-Risk Patients and Lower Healthcare Costs.

Publications

AI-Based Chest CT Analysis for Rapid COVID-19 Diagnosis and Prognosis: A Practical Tool to Flag High-Risk Patients and Lower Healthcare Costs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets