The diagnostic accuracy of Artificial Intelligence-Assisted CT imaging in COVID-19 disease: A systematic review and meta-analysis

Moezzi, Meisam; Shirbandi, Kiarash; Shahvandi, Hassan Kiani; Arjmand, Babak; Rahim, Fakher

doi:10.1016/j.imu.2021.100591

Cited by 18 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…El metaanálisis de Moezzi et al 19 demostró un rendimiento satisfactorio utilizando el algoritmo de IA para la identificación de COVID-19 por medio de TC asistida por IA frente a muestras sanas. Demostraron que la IA fue precisa en la afectación pulmonar durante el CO-VID-19, con una sensibilidad combinada de 0.90 (IC 95%: 0.90-0.91), una especificidad de 0.90 (IC 95%: 0.90-0.91) y un AUC de 0.96 (IC 95%: 0.91-0.98), lo que contrasta con nuestro estudio, pues este demostró una sensibilidad y especificidad de 0.65 y 0.84, respectivamente.…”

Section: Discussionunclassified

Precisión diagnóstica del <i>software</i> de cuantificación automática en pacientes con sospecha de COVID-19 del Instituto Nacional de Cardiología Ignacio Chávez

Gallego-Díaz

Cristancho-Rojas²,

Críales-Vera

2024

ACM

View full text Add to dashboard Cite

Objetivos: Establecer la precisión diagnóstica por tomografía computarizada (TC) de la probabilidad de neumopatía por enfermedad por coronavirus 2019 , dada por el sistema de inteligencia artificial (IA) diseñado por Siemens, y el resultado de la evaluación cualitativa Reporting and Data System) con el estándar de referencia reacción en cadena de la polimerasa transcriptasa inversa (RT-PCR), entregando así la experiencia de nuestra institución. Métodos: Se realizó un estudio observacional, comparativo y retrolectivo en 192 pacientes adultos con sospecha de infección por coronavirus 2 del síndrome respiratorio agudo grave (SARS-CoV-2) que contaban con prueba PCR. Se obtuvo la información de precisión diagnóstica luego de comparar el estándar de referencia (RT-PCR) con el CO-RADS realizado por los observadores y la probabilidad de COVID-19 que arrojaron las imágenes de TC mediante la IA. Resultados: La comparación de la probabilidad de COVID-19 obtenida por la IA vs. la RT-PCR para SARS-CoV-2 generó un AUC ROC de 0.774 (IC: 0.69-0.81) con p = 0.0001. La probabilidad de COVID-19 tuvo una precisión aceptable, con un buen valor predictivo positivo del 87.80%, pero con un pobre valor predictivo negativo del 58.80%. La variable CO-RADS vs. PCR obtuvo una mayor precisión con valores de sensibilidad y especificidad del 91.80 y 88.7% respectivamente. Conclusión: La comparación entre los resultados obtenidos por la IA y por la variable CO-RADS mostró mayor efectividad en esta última, sin embargo se logró documentar el alto impacto que tiene el sistema de cuantificación automática en la evaluación de estos pacientes, ya que permite agilizar la valoración del radiólogo y funciona como complemento en casos de dudas diagnósticas.

show abstract

Section: Discussionunclassified

Precisión diagnóstica del <i>software</i> de cuantificación automática en pacientes con sospecha de COVID-19 del Instituto Nacional de Cardiología Ignacio Chávez

Gallego-Díaz

Cristancho-Rojas²,

Críales-Vera

2024

ACM

View full text Add to dashboard Cite

show abstract

“…Their incorporation might improve the CTSS. Other suggestions are increasing the number of categories of the CTSS, or using use of artificial intelligence (AI) to aid pulmonary involvement quantification [ 30 ].…”

Section: Discussionmentioning

confidence: 99%

Monitoring of pulmonary involvement in critically ill COVID-19 patients - should lung ultrasound be preferred over CT?

et al. 2023

View full text Add to dashboard Cite

Background It is unclear if relevant changes in pulmonary involvement in critically ill COVID-19 patients can be reliably detected by the CT severity score (CTSS) and lung ultrasound score (LUSS), or if these changes have prognostic implications. In addition, it has been argued that adding pleural abnormalities to the LUSS could improve its prognostic value. The objective of this study was to compare LUSS and CTSS for the monitoring of COVID-19 pulmonary involvement through: first, establishing the correlation of LUSS (± pleural abnormalities) and CTSS throughout admission; second, assessing agreement and measurement error between raters for LUSS, pleural abnormalities, and CTSS; third, evaluating the association of the LUSS (± pleural abnormalities) and CTSS with mortality at different timepoints. Methods This is a prospective, observational study, conducted during the second COVID-19 wave at the AmsterdamUMC, location VUmc. Adult COVID-19 ICU patients were prospectively included when a CT or a 12-zone LUS was performed at admission or at weekly intervals according to local protocol. Patients were followed 90 days or until death. We calculated the: (1) Correlation of the LUSS (± pleural abnormalities) and CTSS throughout admission with mixed models; (2) Intra-class correlation coefficients (ICCs) and smallest detectable changes (SDCs) between raters; (3) Association between the LUSS (± pleural abnormalities) and CTSS with mixed models. Results 82 consecutive patients were included. Correlation between LUSS and CTSS was 0.45 (95% CI 0.31–0.59). ICCs for LUSS, pleural abnormalities, and CTSS were 0.88 (95% CI 0.73–0.95), 0.94 (95% CI 0.90–0.96), and 0.84 (95% CI 0.65–0.93), with SDCs of 4.8, 1.4, and 3.9. The LUSS was associated with mortality in week 2, with a score difference between patients who survived or died greater than its SDC. Addition of pleural abnormalities was not beneficial. The CTSS was associated with mortality only in week 1, but with a score difference less than its SDC. Conclusions LUSS correlated with CTSS throughout ICU admission but performed similar or better at agreement between raters and mortality prognostication. Given the benefits of LUS over CT, it should be preferred as initial monitoring tool.

show abstract

“…Accordingly, while some cases are asymptomatic and some patients develop a viral upper respiratory infection, other individuals face life-threatening symptoms such pneumonia, respiratory failure, shock, and multi-organ dysfunction (Arjmand et al 2020a ; Azodi et al 2020 ; Batu and Özen 2020 ; Aghili et al 2021 ; Azodi et al 2021 ). Additionally, cytokine storm or cytokine release syndrome (CRS), overproduction of cytokines, and bacterial co-infection or secondary bacterial infection are examples of lethal complications of COVID-19 (Feng et al 2020 ; Rana 2020 , Moezzi et al 2021 ). Herein, while COVID-19 is mostly transmitted through the lungs, it has been demonstrated to also have gastrointestinal effects, with diarrhea being reported in roughly one-third of patients.…”

Section: Introductionmentioning

confidence: 99%

Critical roles of cytokine storm and bacterial infection in patients with COVID-19: therapeutic potential of mesenchymal stem cells

et al. 2023

Self Cite

View full text Add to dashboard Cite

The severe acute respiratory syndrome coronavirus 2 has been a shocking disaster for healthcare systems worldwide since December 2019. This virus can affect all systems of the body and its symptoms vary from a simple upper respiratory infection to fatal complications including end-organ damage. On the other hand, the normal immune system plays a pivotal role in the recovery of infectious diseases such as COVID-19. However, occasionally, exaggerated immune system inflammation and an excessive synthesis of cytokines, known as a "cytokine storm," can deteriorate the patient's clinical condition. Secondary bacterial co-infection is another problem in COVID-19 which affects the prognosis of patients. Although there are a few studies about this complication, they suggest not using antibiotics commonly, especially broad-spectrum ones. During this pandemic, various approaches and therapeutics were introduced for treating COVID-19 patients. However, available treatments are not helpful enough, especially for complicated cases. Hence, in this era, cell therapy and regenerative medicine will create new opportunities. Therefore, the therapeutic benefits of mesenchymal stem cells, especially their antimicrobial activity, will help us understand how to treat COVID-19. Herein, mesenchymal stem cells may stop the immune system from becoming overactive in COVID-19 patients. On the other side, the stem cells' capacity for repair could encourage natural healing processes.

show abstract

The diagnostic accuracy of Artificial Intelligence-Assisted CT imaging in COVID-19 disease: A systematic review and meta-analysis

Cited by 18 publications

References 57 publications

Precisión diagnóstica del <i>software</i> de cuantificación automática en pacientes con sospecha de COVID-19 del Instituto Nacional de Cardiología Ignacio Chávez

Precisión diagnóstica del <i>software</i> de cuantificación automática en pacientes con sospecha de COVID-19 del Instituto Nacional de Cardiología Ignacio Chávez

Monitoring of pulmonary involvement in critically ill COVID-19 patients - should lung ultrasound be preferred over CT?

Critical roles of cytokine storm and bacterial infection in patients with COVID-19: therapeutic potential of mesenchymal stem cells

Contact Info

Product

Resources

About