The current AI paradigm at best reveals correlations between model input and output variables. This falls short of addressing health and healthcare challenges where knowing the causal relationship between interventions and outcomes is necessary and desirable. In addition, biases and vulnerability in AI systems arise, as models may pick up unwanted, spurious correlations from historic data, resulting in the widening of already existing health inequalities. Causal AI is the key to unlock robust, responsible and trustworthy AI and transform challenging tasks such as early prediction, diagnosis and prevention of disease. The Causality in Healthcare AI with Real Data (CHAI) Hub will bring together academia, industry, healthcare, and policy stakeholders to co-create the next-generation of world-leading artificial intelligence solutions that can predict outcomes of interventions and help choose personalised treatments, thus transforming health and healthcare. The CHAI Hub will develop novel methods to identify and account for causal relationships in complex data. The Hub will be built by the community for the community, amassing experts and stakeholders from across the UK to 1) push the boundaries of AI innovation; 2) develop cutting-edge solutions that drive desperately needed efficiency in resource-constrained healthcare systems; and 3) cement the UK's standing as a next-gen AI superpower. The data complexity in heterogeneous and distributed environments such as healthcare exacerbates the risks of bias and vulnerability and introduces additional challenges that must be addressed. Modern clinical investigations need to mix structured and unstructured data sources (e.g. patient health records, and medical imaging exams) which current AI cannot integrate effectively. These gaps in current AI technology must be addressed in order to develop algorithms that can help to better understand disease mechanisms, predict outcomes and estimate the effects of treatments. This is important if we want to ensure the safe and responsible use of AI in personalised decision making. Causal AI has the potential to unearth novel insights from observational data, formalise treatment effects, assess outcome likelihood, and estimate 'what-if' scenarios. Incorporating causal principles is critical for delivering on the National AI Strategy to ensure that AI is technically and clinically safe, transparent, fair and explainable. The CHAI Hub will be formed by a founding consortium of powerhouses in AI, healthcare, and data science throughout the UK in a hub-spoke model with geographic reach and diversity. The hub will be based in Edinburgh's Bayes Centre (leveraging world-class expertise in AI, data-driven innovation in health applications, a robust health data ecosystem, entrepreneurship, and translation). Regional spokes will be in Manchester (expertise in both methods and translation of AI through the Institute for Data Science and AI, and Pankhurst Institute), London (hosted at KCL, representing also UCL and Imperial, leveraging London's rapidly growing AI ecosystem) and Exeter (leveraging strengths in philosophy of causal inference and ethics of AI). The hub will develop a UK-wide multidisciplinary network for causal AI. Through extended collaborations with industry, policymakers and other stakeholders, we will expand the hub to deliver next-gen causal AI where it is needed most. We will work together to co-create, moving beyond co-ideation and co-design, to co-implementation, and co-evaluation where appropriate to ensure fit-for-purpose solutions Our programme will be flexible, will embed trusted, responsible innovation and environmental sustainability considerations, will ensure that equality diversity and inclusion principles are reflected through all activities, and will ensure that knowledge generated through CHAI will continue to have real-world impact beyond the initial 60 months.

Clinical need: Every year in the UK, 9,200 patients are diagnosed with cancer of the gullet (oesophagus) but only 15 in 100 patients can expect to live beyond five years. Most patients do not respond to chemotherapy or radiation therapy and this lowers their chances of survival. More effective treatments are urgently needed to improve patient outcomes. A lack of oxygen ('hypoxia') in tumours is a cause of treatment resistance. Promising new drugs have been developed which reduce hypoxia and could improve outcomes for patients. However, previous studies have shown that only certain patients with hypoxic tumours will respond. We currently have no simple method of measuring tumour hypoxia (i.e. a 'biomarker') to predict who will benefit or know if the drugs are working. This makes designing clinical trials challenging, hence no hypoxia-targeted therapies are approved for use in oesophageal cancer. A simple test that measures tumour hypoxia could accelerate clinical trials and make these new drugs available to patients. Solution: Breath testing is safe, acceptable to patients and can be repeated easily. Breath tests are already used in law enforcement to detect blood alcohol levels and in healthcare to diagnose stomach infections (H. pylori) and asthma. At Imperial College London, we have also shown that volatile chemicals in the breath measured using mass spectrometry can accurately diagnose oesophageal cancer. Recent work has shown that some of these chemicals originate from cancer cells and can be influenced by hypoxia. This may mean that we could measure tumour hypoxia through a simple breath test. Aim: The project aim is to develop a non-invasive breath test to predict and monitor the response to hypoxia-targeted therapy in oesophageal cancer. Institutions: This research will be delivered through a strategic collaboration between Imperial College London and Manchester Cancer Research Centre (MCRC). The Volatile Organic Compound (VOC) laboratory at Imperial has recruited more than 3000 patients with cancers of the digestive tract for clinical trials of non-invasive diagnostics over the last 2 years. MCRC has extensive experience in tumour hypoxia research and delivering biomarker-driven trials of hypoxia-targeted therapy. New findings: We have identified: (i) target genes that can be used to detect hypoxia from tumour samples (a hypoxia gene 'signature') and (ii) volatile chemicals that are produced by tumours in response to hypoxia that can be detected in the breath. Project structure: Our aim is to fully characterize the volatile chemicals that are produced by hypoxic tumours and the mechanisms of their production. This will involve analysing volatile chemicals in: (i) breath and cancer tissue from patients retrieved during a camera test ('endoscopy') as part of their routine investigations, and (ii) cancer cells grown under hypoxic and normal conditions. The second aim is to determine how these chemicals change in response to therapy. This will involve analysing: (i) cells grown in a laboratory treated with hypoxia-targeting drugs, and (ii) the breath of oesophageal cancer patients in a clinical trial of a hypoxia-targeting drug. Importance: This project aims to develop a non-invasive breath test to improve patient selection and monitoring of anticancer drugs targeting hypoxia. It is intended that this breath test will accelerate clinical trials to make more effective therapies available to patients. Successful development of a breath test for treatment monitoring would also be the first of its kind worldwide. This innovative approach could promote the concept of breath-based monitoring for a wide range of applications in healthcare.