Artificial Intelligence: supporting clinical decisions to stop COVID-19

The clinical decision making systems based on Artificial Intelligence (AI) are a greater utility tools considering the ongoing sanitary emergency situation. One of the main problems of the crisis generated by the arrival of the COVID-19 is the saturation of the healthcare systems personnel for the big pressure at which are subjected. AI is a  tool extremely useful to carry out routine tasks that requires a high rank of specialisation (1).

The AI algorithms are previously tested with professionals’ knowledge and expertise and are developed to learn and reproduce the results expected in a fast and reliable form. Therefore, the app of this type of solutions (2) would permit to liberate professionals from these mechanical tasks to use itefficently to develop other priority tasks duties.

Primary care

According to Eric J. Topol, cardiologist, in the present situation the use of the AI is promoting athree levels impact: for doctors, by means of a fast and accurate performance of the image; for healthcare systems, improving the processes and decreasing the range of medical errors; and for patients, facilitating their data management process to improve healthcare (3).

In Catalonia, the great and varied amoount of medical data (for example the clinical records of the Catalan people), the dyagnosis and treatments protocol enabling , the advances at computing and the agility by using and performing huge amounts of information. In addition to the ongoing trends on customised and preventive medicine, the artificial intelligence has for healthcare a big opppotunity of value contribution. On the other hand, the pharmaceutical sector is one of the sectors that, by means of the supercomputing is already taking advantage of this technicial progress to create new drugs (4) (5).

AI proposals avaluation

The TIC Salut Social Foundations explores to answer the needs of analysis the differenet solutions that are arising in such the presentcircumstances. The area of Artificial Intelligence of the Foundation is analysing the varied initiatives -platforms of follow-up and monitoring support to brestfeeding mothers, transport and distribution, predictive tools and other products- arisen at the area of the struggle against the COVID-19, realising a process of appraisal of the distinct solutions detected.

Medical Imagins and other solutions

One of the main AI advances in healthcare is the massive medical imaging analysis (6). Regarding the the use of highly structured, standardized and skilled informations in these digital environments, healthcare appears to be one og the pioneers activity areas where this kind of tech solution can be developed and spread to other activities. Different proposals are being analysed, already are based at X-ray (RX) or Tomography Computerised (TC)(7), both at his modality of thoracic localization, for such to analyse the pulmonary affectation caused by the virus. It treats of algorithms that seek to give a diagnostic of COVID-19 rapid and reliable by means of RXexplorations or making predictions of the patient’sevolution once the illness it’s been detected (8).

Another line of inquest is centred at the analysis of the clinical constants of the patients with COVID-19 for such to foresee his evolution and possible complications (9). Also they are valuing other more solutions incipients at the field of the recognition of the voice, and the cough more precisely, for such to detect masters that can be ascribed of unambiguous form at the infection for coronavirus.
To face the COVID-19, the Healthcare Ministry of the Catalan Governmenthas enhanced a technological tool, the App STOP Covid19 Cat, that contributes to detect the symptoms of the sickness and make a follow-up of  patients, and tracks the pandemic evolution in Catalonia facilitating in real time the decision making (10).

References

1. McCall B. COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread. Lancet Digit Heal [Internet]. 2020;2(4):e166–7. Available from: http://dx.doi.org/10.1016/S2589-7500(20)30054-6

2. Alimadadi A, Aryal S, Manandhar I, Munroe PB, Joe B, Cheng X. Artificial Intelligence and Machine Learning to Fight COVID-19. Physiol Genomics. 2020;52:200–2.

3. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med [Internet]. 2019;25(1):44–56. Available from: http://dx.doi.org/10.1038/s41591-018-0300-7

4. Departament de Polítiques Digitals i Administració_Pública. CATALONIA.AI, l’Estratègia d’Intel·ligència Artificial de Catalunya [Internet]. 2020 [cited 2020 Apr 7]. Available from: http://politiquesdigitals.gencat.cat/ca/tic/catalonia-ai

5. Autoritat Catalana de Protecció de Dades. Intel·ligència Artificial. Decisions Automatitzades a Catalunya [Internet]. Barcelona; 2020. Available from: https://apdcat.gencat.cat/web/.content/04-actualitat/noticies/documents/INFORME-INTELLIGENCIA-ARTIFICIAL-FINAL-WEB-OK.pdf

6. Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nat Med [Internet]. 2019;25(1):24–9. Available from: http://dx.doi.org/10.1038/s41591-018-0316-z

7. Li L, Qin L, Xu Z, Yin Y, Wang X, Kong B, et al. Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT. Radiology [Internet]. 2020 Mar19; Available from: http://pubs.rsna.org/doi/10.1148/radiol.2020200905

8. Huang Y, Cheng W, Zhao N, Qu H, Tian J. CT screening for early diagnosis of SARS-CoV-2 infection. Lancet Infect Dis [Internet]. 2020;51(20):30241. Available from: http://dx.doi.org/10.1016/S1473-3099(20)30241-3

9. McCullough PA, Eidt J, Rangaswami J, Lerma E, Tumlin J, Wheelan K, et al. Urgent need for individual mobile phone and institutional reporting of at home, hospitalized, and intensive care unit cases of SARS-CoV-2 (COVID-19) infection. Rev Cardiovasc Med [Internet]. 2020;21(1):1–7. Available from: http://www.ncbi.nlm.nih.gov/pubmed/32259899

10. Rao ASRS, Vazquez JA. Identification of COVID-19 Can be Quicker through Artificial Intelligence framework using a Mobile Phone-Based Survey in the Populations when Cities/Towns Are under Quarantine. Infect Control Hosp Epidemiol. 2020;1–18.