Praduman Jain is CEO and founder of Vibrent Health, a digital health technology company powering the future of precision medicine. There has been quite a bit of hype over the last several years about how artificial intelligence (AI) would transform health care. Translating the predictive power of AI algorithms into research methods and clinical practice, however, has proved challenging, which inevitably leads to disillusionment. But rather than getting frustrated with AI and machine learning, I would argue that strategic and ethical deployment of artificial intelligence will, by necessity, be central to the success of precision health research over the next decade. Several factors are coming together to make AI more critical to progress.

Calithera is running registered clinical trials on its products to study their safety, whether they're effective in patients with specific gene mutations, and how well they work in combination with other therapies. The company must collect detailed data on hundreds of patients. While some of its trials are in early stages and involve only a small number of patients, others span more than 100 research centers across the globe. "In the life-sciences world, one of the biggest challenges we have is the enormous amount of data we generate, more than any other business," says Behrooz Najafi, Calithera's lead information technology strategist. Calithera must store and manage the data while making sure it's readily available when needed, even years from now.

Calithera is running registered clinical trials on its products to study their safety, whether they're effective in patients with specific gene mutations, and how well they work in combination with other therapies. The company must collect detailed data on hundreds of patients. While some of its trials are in early stages and involve only a small number of patients, others span more than 100 research centers across the globe. "In the life-sciences world, one of the biggest challenges we have is the enormous amount of data we generate, more than any other business," says Behrooz Najafi, Calithera's lead information technology strategist. Calithera must store and manage the data while making sure it's readily available when needed, even years from now.

Wendy Gonzalez is the CEO of Sama, the provider of accurate data for ambitious AI. We've all seen the headlines on the rapid adoption of artificial intelligence (AI) across industries. From improved efficiencies in inventory management to new capabilities in vaccine development, AI has the power to revolutionize the way we work, interact and are entertained. Less commonly discussed, however, is the importance of implementing an ethical AI supply chain. Much like other large industries, AI can run into trouble when produced at scale.

FDA has been promoting enrollment practices that could enhance the diversity of clinical trial populations, through broadening eligibility criteria. However, how to broaden eligibility remains a significant challenge. We propose an AI approach to Cohort Optimization (AICO) through transformer-based natural language processing of the eligibility criteria and evaluation of the criteria using real-world data. The method can extract common eligibility criteria variables from a large set of relevant trials and measure the generalizability of trial designs to real-world patients. It overcomes the scalability limits of existing manual methods and enables rapid simulation of eligibility criteria design for a disease of interest. A case study on breast cancer trial design demonstrates the utility of the method in improving trial generalizability.

Artificial Intelligence (AI) has been used to revolutionize healthcare for some time, but all the signs suggest that AI is poised to completely take the medicinal world by storm over the next few years. Governments -- from the U.K. and the U.S. to Germany, Qatar and China -- have published strategy papers on AI in healthcare and backed up their words with multimillion-dollar funding. The WHO recently issued its first global report on AI in healthcare. And global equity funding in AI health start-ups has risen quarter on quarter since the end of 2019, reaching a record $2.5 billion in the first quarter of 2021. All this buzz is a reflection of the enormous range of healthcare-related activities in which AI can have a big impact.

Established approaches to assuring safety-critical systems and software are difficult to apply to systems employing machine learning (ML). In many cases, ML is used on ill-defined problems, e.g. optimising sepsis treatment, where there is no clear, pre-defined specification against which to assess validity. This problem is exacerbated by the "opaque" nature of ML where the learnt model is not amenable to human scrutiny. Explainable AI methods have been proposed to tackle this issue by producing human-interpretable representations of ML models which can help users to gain confidence and build trust in the ML system. However, there is not much work explicitly investigating the role of explainability for safety assurance in the context of ML development. This paper identifies ways in which explainable AI methods can contribute to safety assurance of ML-based systems. It then uses a concrete ML-based clinical decision support system, concerning weaning of patients from mechanical ventilation, to demonstrate how explainable AI methods can be employed to produce evidence to support safety assurance. The results are also represented in a safety argument to show where, and in what way, explainable AI methods can contribute to a safety case. Overall, we conclude that explainable AI methods have a valuable role in safety assurance of ML-based systems in healthcare but that they are not sufficient in themselves to assure safety.

New research has found that artificial intelligence (AI) analyzing medical scans can identify the race of patients with an astonishing degree of accuracy, while their human counterparts cannot. With the Food and Drug Administration (FDA) approving more algorithms for medical use, the researchers are concerned that AI could end up perpetuating racial biases. They are especially concerned that they could not figure out precisely how the machine-learning models were able to identify race, even from heavily corrupted and low-resolution images. In the study, published on pre-print service Arxiv, an international team of doctors investigated how deep learning models can detect race from medical images. Using private and public chest scans and self-reported data on race and ethnicity, they first assessed how accurate the algorithms were, before investigating the mechanism.

We introduce Reflective Hamiltonian Monte Carlo (ReHMC), an HMC-based algorithm, to sample from a log-concave distribution restricted to a convex body. We prove that, starting from a warm start, the walk mixes to a log-concave target distribution $\pi(x) \propto e^{-f(x)}$, where $f$ is $L$-smooth and $m$-strongly-convex, within accuracy $\varepsilon$ after $\widetilde O(\kappa d^2 \ell^2 \log (1 / \varepsilon))$ steps for a well-rounded convex body where $\kappa = L / m$ is the condition number of the negative log-density, $d$ is the dimension, $\ell$ is an upper bound on the number of reflections, and $\varepsilon$ is the accuracy parameter. We also developed an efficient open source implementation of ReHMC and we performed an experimental study on various high-dimensional data-sets. The experiments suggest that ReHMC outperfroms Hit-and-Run and Coordinate-Hit-and-Run regarding the time it needs to produce an independent sample and introduces practical truncated sampling in thousands of dimensions.

This announcement accelerates Optellum's market entry, building on its FDA clearance earlier this year and deployments underway at hospitals in the USA and ongoing clinical trials in the United Kingdom. It identifies and tracks at-risk patients and assigns a Lung Cancer Prediction score to lung nodules: small lesions, frequently detected in chest Computed Tomography (CT) scans that may or may not be cancerous. The Optellum AI will be used to drive accurate early diagnosis and optimal treatment decisions with the aim of treating patients earlier, potentially at a pre-cancerous stage, increasing survival rates.