Causal knowledge engineering: A case study from COVID-19 (preprint)

COVID-19 appeared abruptly in early 2020, requiring a rapid response amid a context of great uncertainty. Good quality data and knowledge was initially lacking, and many early models had to be developed with causal assumptions and estimations built in to supplement limited data, often with no reliable approach for identifying, validating and documenting these causal assumptions. Our team embarked on a knowledge engineering process to develop a causal knowledge base consisting of several causal BNs for diverse aspects of COVID-19. The unique challenges of the setting lead to experiments with the elicitation approach, and what emerged was a knowledge engineering method we call Causal Knowledge Engineering (CKE). The CKE provides a structured approach for building a causal knowledge base that can support the development of a variety of application-specific models. Here we describe the CKE method, and use our COVID-19 work as a case study to provide a detailed discussion and analysis of the method.

Modelling long COVID using Bayesian networks (preprint)

Motivated by the ambiguity of operational case definitions for long COVID and the impact of the lack of a common causal language on long COVID research, in early 2023 we began developing a research framework on this post-acute infection syndrome. We used directed acyclic graphs (DAGs) and Bayesian networks (BNs) to depict the hypothesised mechanisms of long COVID in an agnostic fashion. The DAGs were informed by the evolving literature and subsequently refined following elicitation workshops with domain experts. The workshops were structured online sessions guided by an experienced facilitator. The causal DAG aims to summarise the hypothesised pathobiological pathways from mild or severe COVID-19 disease to the development of pulmonary symptoms and fatigue over four different time points. The DAG was converted into a BN using qualitative parametrisation. These causal models aim to assist the identification of disease endotypes, as well as the design of randomised controlled trials and observational studies. The framework can also be extended to a range of other post-acute infection syndromes.

Statistical Considerations for the Platform Trial in COVID-19 Vaccine Priming and Boosting (preprint)

The Platform trial In COVID-19 priming and BOOsting (PICOBOO) is a multi-site, adaptive platform trial designed to generate evidence of the immunogenicity, reactogenicity, and cross-protection of different booster vaccination strategies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and its variants, specific for the Australian context. The PICOBOO trial randomises participants to receive one of three COVID-19 booster vaccine brands (Pfizer, Moderna, Novavax) available for use in Australia, where the vaccine brand subtypes vary over time according to the national vaccine roll out strategy, and employs a Bayesian hierarchical modelling approach to efficiently borrow information across consecutive booster doses, age groups and vaccine brand subtypes. Here, we briefly describe the PICOBOO trial structure, and report the statistical considerations for the estimands, statistical models and decision making for trial adaptations. This paper should be read in conjunction with the PICOBOO Core Protocol and PICOBOO Sub-Study Protocol 1: Booster Vaccination. PICOBOO was registered on 10 February 2022 with the Australian and New Zealand Clinical Trials Registry ACTRN12622000238774.

Modeling COVID-19 disease processes by remote elicitation of causal Bayesian networks from medical experts (preprint)

BackgroundCOVID-19 is a new multi-organ disease, caused by the SARS-CoV-2 virus, resulting in considerable worldwide morbidity and mortality. While many recognized pathophysiological mechanisms are involved, their exact causal relationships remain opaque. A better understanding is needed for predicting their progression, targeting therapeutic approaches, and improving patient outcomes. While many mathematical causal models describe COVID-19 epidemiology, none have been developed for its pathophysiology. The viruss rapid and extensive spread and therapeutic responses made this particularly difficult. Initially, no large patient datasets were publicly available, and their data remains limited. The medical literature was flooded with unfiltered, technical and sometimes conflicting pre-review reports. Clinicians in many countries had little time for academic consultations, and in-person meetings were unsafe. Methods and FindingsIn early 2020, we began a major project to develop causal models of the pathophysiological processes underlying the diseases clinical manifestations. We used Bayesian network (BN) models, because they provide both powerful tools for calculation and clear maps of probabilistic causal influence between semantically meaningful variables, as directed acyclic graphs (DAGs). Hence, they can incorporate expert opinion and numerical data, and produce explainable results. Dynamic causal BNs, which represent successive "time slices" of the system, can capture feedback loops and long-term disease progression. To obtain the likely causal structures, we used extensive elicitation of expert opinion in structured online sessions. Centered in Australia, with its exceptionally low COVID-19 burden, we managed to obtain many consultation hours. Groups of clinical and other subject matter specialists, all independent volunteers, were enlisted to filter, interpret and discuss the literature and develop a current consensus. We aimed to capture the experts understanding, so we encouraged discussion and inclusion of theoretically salient latent (i.e., unobservable) variables, documented supporting literature while noting controversies, and allowed experts to propose mechanisms by extrapolation from other diseases. Intermediary experts with some combined expertise facilitated the exchange of knowledge to BN modelers and vice versa. Our method was iterative and incremental: we systematically refined and checked the group output with one-on-one follow-up meetings with the original and new experts to validate previous results. In total, 35 experts contributed 126 face-to-face hours, and could review our products. ConclusionsOur method demonstrates and describes an improved procedure for developing BNs via expert elicitation, which can be implemented rapidly by other teams modeling emergent complex phenomena. The results presented are two key models, for the initial infection of the respiratory tract and the possible progression to complications, as causal DAGs and BNs with corresponding verbal descriptions, dictionaries and sources. These are the first published causal models of COVID-19 pathophysiology, with three anticipated applications: (i) making expert knowledge freely available in a readily understandable and updatable form; (ii) guiding design and analysis of observational and clinical studies, by identifying potential mediators, confounders, and modifiers of treatment effects; (iii) developing and validating parameterized automated tools for causal reasoning and decision support, in clinical and policy settings. We are currently developing such tools for the initial diagnosis, resource management, and prognosis of COVID-19, parameterized using the ISARIC and LEOSS databases.

Controlled evaLuation of Angiotensin Receptor Blockers for COVID-19 respIraTorY disease (CLARITY): Statistical analysis plan for a randomised controlled Bayesian adaptive sample size trial (preprint)

The CLARITY trial (Controlled evaLuation of Angiotensin Receptor Blockers for COVID-19 respIraTorY Disease) investigates the effectiveness of angiotensin receptor blockers in addition to standard care compared to placebo (in Indian sites) with standard care in reducing the duration and severity of lung failure in patients with COVID-19. The CLARITY trial is a multi-centre, randomised controlled Bayesian adaptive trial with regular planned analyses where pre-specified decision rules will be assessed to determine whether the trial should be stopped due to sufficient evidence of treatment effectiveness or futility. Here we describe the statistical analysis plan for the trial, and define the pre-specified decision rules, including those that could lead to the trial being halted. The primary outcome is clinical status on a 7-point ordinal scale adapted from the WHO Clinical Progression scale assessed at Day 14. The primary analysis will follow the intention-to-treat principle. A Bayesian adaptive trial design was selected because there is considerable uncertainty about the extent of potential benefit of this treatment. Trial registrationClinicalTrials.gov, NCT04394117. Registered on 19 May 2020. https://clinicaltrials.gov/ct2/show/NCT04394117 Clinical Trial Registry of India: CTRI/2020/07/026831 Version and revisionsVersion 1.0. No revisions.

Bridging the gaps in test interpretation of SARS-CoV-2 through Bayesian network modelling (preprint)

Background In the absence of an established gold standard, an understanding of the testing cycle from individual exposure to test outcome report is required to guide the correct interpretation of SARS-CoV-2 reverse transcriptase real-time polymerase chain reaction (RT-PCR) results and optimise the testing processes. Bayesian network (BN) models have been used within healthcare to bring clarity to complex problems. We use this modelling approach to construct a comprehensive framework for understanding the real world predictive value of individual RT-PCR results. Methods We elicited knowledge from domain experts to describe the test process from viral exposure to interpretation of the laboratory test, through a facilitated group workshop. A preliminary model was derived based on the elicited knowledge, then subsequently refined, parameterised and validated with a second workshop and one-on-one discussions. Results Causal relationships elicited describe the interactions of multiple variables and their impact on a RT-PCR result. Some interactions are infrequently observable and accounted for across the testing cycle such as pre-testing factors, sample collector experience and RT-PCR platform. By setting the input variables as evidence for a given subject and preliminary parameterisation, three scenarios were simulated to demonstrate potential uses of the model. Conclusions The core value of this model is a deep understanding of the total testing cycle, bridging the gap between a persons true infection status and their test outcome. This model can be adapted to different settings, testing modalities and pathogens, adding much needed nuance to the interpretations of results.