2021 IEEE International Conference on Big Data (Big Data) 978-1-6654-3902-2/21/$31.00 ©2021 IEEE 4753 Modeling Influenza with a Forest Deep Neural Network Utilizing a Virtualized Clinical Semantic Network Fuad Rahman ∗ , Abrar Rahman † , AKM Shahariar Azad Rabby ‡§ , Md Jamiur Rahman Rifat ‡ , Mridul Banik ††‡ , Md. Majedul Islam ‡ , Aminul Islam ‡ , Nor Azriah Aziz ¶ , Rick Meyer ∥ , John Kriak ∗∗ , Sidney Goldblatt ∥ ∗ Apurba Technologies, CA, USA, § Apurba Technologies, Dhaka, Bangladesh, ¶ Apurba Technologies, Malaysia, † The University of California, Berkeley, CA, USA, ‡ The University of Alabama at Birmingham, AL, USA, †† Colorado State University, CO, USA, ∥ Goldblatt Systems, AZ, USA, ∗∗ MolecularDx LLC, PA, USA ∗§¶ {fuad, rabby, rifat, mridul, majed, azriah.aziz}@apurbatech.com, † abrarfrahman@berkeley.edu, ‡ arabby@uab.edu †† mbanik@colostate.edu, ∥ rick.meyer@visioneimpatto.com, sagoldblatt@aol.com, ∗∗ jkriak@molecdx.com Abstract—CoViD-19 pandemic has shown that we have deep gaps in understanding this extremely infectious virus—not only both from a clinical diagnosis and treatment perspective—but also from a forecasting point of view, so that we are better prepared for the next onset of a similar pandemic, which, at this point, seems almost inevitable. In this paper, we present a novel approach towards modeling influenza, a closely related disease to CoViD-19, marrying clinical understanding with artificial intelligence, exploiting the Forest Deep Neural Network (fDNN) with accuracy rates in the 90% range. Index Terms—FDNN, Disease modeling, vCSN, Influenza, NLP. I. I NTRODUCTION CoViD-19 has demonstrated how unprepared we were in terms of handling a global pandemic. Like the rest of the world, the US reaction to this pandemic has uncovered a deep chasm of divide not only in the sociopolitical area, but also on the core issue of clinical assessment—how and when to diagnose, how to formulate a treatment plan, who should be a hospitalized, when is someone ready to go home and how to effectively follow up—and more importantly, how to prepare for the next round of a similar pandemic that many say is an inevitability. It has become clear to us that in order to address any of the issues mentioned before, our starting point should be a better understanding of the disease itself. In this paper, we have presented a clinical assessment of the disease which we then exploited to model a disease using advanced Artificial Intelligence (AI), using Natural Language Processing (NLP) and Machine Learning (ML) techniques. A. Modeling a Disease How do we model a disease? Disease modeling consists of two distinct but interrelated components: scientific or math- ematical disease modeling and clinical disease modeling. A scientific disease model is a mathematical construct that is built based on ‘seen’ samples and calculating the relation- ships between measurable characteristics of a phenomenon or ‘variables’ in the form of mathematical equations [1]. One of the primary benefits of a mathematical disease model is that it can establish associations between a given disease and other factors (epidemiology, symptomatology, risk factors, etc.). However, it does not necessarily consider the severity and/or importance of the aforementioned factors. For example, a CDC report indicated that, in the United States, persons with select underlying health conditions (diabetes mellitus, chronic lung disease, and cardiovascular disease) or other recognized risk factors for severe outcomes from respiratory infections appear to be at a higher risk for severe disease from CoViD-19 than are persons without these conditions [2]. This report was likely based on a mathematical model that made associations between these conditions and CoViD-19 outcomes. However, the CDC report did not rank the importance of these conditions (or combination of these conditions) or identify factors related to these conditions that are more likely to result in severe outcomes. Fortunately, this deficiency can be corrected when clinical disease modeling is combined with scientific disease modeling. Clinical disease modeling can help determine the underlying disease factors and degree and severity of each associated factor. For example, once the mathematical model establishes an association, clinicians will analyze the data and help determine exactly what additional data / information is needed from a clinical perspective to help properly characterize a disease. Thus, clinical disease modeling involves mathematical disease modeling with input from clinicians. B. Disease Characterization Clinicians and scientists characterize a “disease” as any objectively addressable deviation from the abstract normal. That abstract normal would be assigned a “neutrum” of customarily and/ or scholarly defined state of equilibrium and perfection [3]. Furthermore, the definition of anatomically and physiologically normal has been determined by centuries of 2021 IEEE International Conference on Big Data (Big Data) | 978-1-6654-3902-2/21/$31.00 ©2021 IEEE | DOI: 10.1109/BigData52589.2021.9671507 Authorized licensed use limited to: Univ of Calif Berkeley. Downloaded on May 03,2022 at 22:38:46 UTC from IEEE Xplore. Restrictions apply.