Simple hemogram to support the decision-making of COVID-19 diagnosis using clusters analysis with self-organizing maps neural network

Abstract

The pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) which is related to new coronavirus disease (COVID-19) has mobilized several scientifics to explore clinical data using soft-computing approaches. In the context of machine learning, previous studies have explored supervised algorithms to predict and support diagnosis based on several clinical parameters from patients diagnosed with and without COVID-19. However, in most of them the decision is based on a "black-box" method, making it impossible to discover the variable relevance in decision making. Hence, in this study, we introduce a non-supervised clustering analysis with neural network self-organizing maps (SOM) as a strategy of decision-making. We propose to identify potential variables in routine blood tests that can support clinician decision-making during COVID-19 diagnosis at hospital admission, facilitating rapid medical intervention. Based on SOM features (visual relationships between clusters and identification of patterns and behaviors), and using linear discriminant analysis , it was possible to detect a group of units of the map with a discrimination power around 83% to SARS-CoV-2-positive patients. In addition, we identified some variables in admission blood tests (Leukocytes, Basophils, Eosinophils, and Red cell Distribution Width) that, in combination had strong influence in the clustering performance, which could assist a possible clinical decision. Thus, although with limitations, we believe that SOM can be used as a soft-computing approach to support clinician decision-making in the context of COVID-19. Keywords Covid-19 diagnostic • SARS-CoV-2 • Self-organizing maps Communicated by Victor Hugo C. de Albuquerque.

Emerging technologies for the management of COVID19: A review

“…Robots are the finest option for this risky profession since they are innately resistant to virus infection. Autonomous robots, such as the floor-cleaning bots that are already accessible as consumer products, can do more than just clean in hospitals [19] . Similar to “drone technology,” other autonomous technologies such as “robots and autonomous vehicles (AVs)” have made important advancements in thebattle against the pandemic [20] .In some countries robots are used for taking care of patients as well as for cleaning and sanitising purpose, in case of severly infected patient [21] …”

“…These datasets enables a very significant computational methods in finding the needle in the haystack which will aid in medical decision-making for ‘COVID-19’ identification and prediction. Hence, data mining approaches can be carried out using a “supervised machine learning algorithm” to predict future values through classification and/or regression, or by unsupervised learning to cluster data [19] . With the help of AI assisted healthcare devices, only contactless treatment is possible.…”

“…The samples are then classified using a machine learning algorithm. This method is used to avoid making contact with the patient [19] . However, this procedure does not yield accurate results.…”

“…The “feature maps” are collectively referred to as “kernels,” and the designer determines their size at random. The selected output has become concise after a feature map has been 'convoluted and sub-sampled' [19] . Each neural network design learns specific patterns from other neural networks since deep CNNs are stochastic.…”

“…Based on responses from the mobile app, AI is utilised to substitute human expert judgement in calculating risk level. The software scans the user's information for suspected coronavirus infection, like some indications are (feeling feverish, headache, dry cough, breathing problem, and exhaustion), length and extremity of symptoms, travelling data, employment and home details, and population stats [19] . The “Covid19 mobile defender” is an example of a sensing device which keeps watch on virusdefensive measures and violation of rules done by people during lockdown to help authorities in managing the coronavirus' propagation and allocating scarce resources [45] .…”