Clinical trials are critical for advancing medical treatments but remain prohibitively expensive and time-consuming. Accurate prediction of clinical trial outcomes can significantly reduce research and development costs and accelerate drug discovery. While recent deep learning models have shown promise by leveraging unstructured data, their black-box nature, lack of interpretability, and vulnerability to label leakage limit their practical use in high-stakes biomedical contexts. In this work, we propose AutoCT, a novel framework that combines the reasoning capabilities of large language models with the explainability of classical machine learning. AutoCT autonomously generates, evaluates, and refines tabular features based on public information without human input. Our method uses Monte Carlo Tree Search to iteratively optimize predictive performance. Experimental results show that AutoCT performs on par with or better than SOTA methods on clinical trial prediction tasks within only a limited number of self-refinement iterations, establishing a new paradigm for scalable, interpretable, and cost-efficient clinical trial prediction.

Therapeutic development for rare diseases is difficult for pharmaceutical companies due to significant scientific challenges, extensive costs, and low financial returns. It is increasingly common for caregivers and patient advocacy groups to partner with biomedical professionals to finance and develop treatments for rare diseases. This case study illustrates the story of Terry Pirovolakis, a father who partnered with biomedical professionals to develop the novel gene therapy, Melpida, within 36 months of the diagnosis of his infant son. We identify the factors that led to the success of Melpida and analyze the business model of Elpida Therapeutics, a social purpose corporation founded by Pirovolakis to reproduce the success of Melpida for other rare diseases. We conclude with four lessons from Melpida to inform caregivers like Pirovolakis on developing novel gene therapies to save their loved ones.

We propose a new approach to funding disease-specific drug development via a variation of the adaptive platform trial. This trial is designed to test a portfolio of drug candidates in parallel, with the cost of the trial partially covered by investors who receive payments from a royalty fund of the candidates in exchange for investment. Under realistic assumptions for cost, revenue, probability of success, drug sales, and royalty rates, investors may expect a return of 28%, but with a 22% probability of total loss. Such return distributions may be attractive to hedge funds, family offices, and philanthropic investors seeking both social impact and financial return. Return distributions palatable to mainstream investors may be achieved by funding multiple platform trials simultaneously and securitizing the aggregate cash flows.

We apply survival analysis as well as machine learning models to predict the duration of clinical trials using the largest dataset so far constructed in this domain. Neural network-based DeepSurv yields the most accurate predictions and we identify key factors that are most predictive of trial duration. This methodology may help clinical researchers optimize trial designs for expedited testing, and can also reduce the financial risk of drug development, which in turn will lower the cost of funding and increase the amount of capital allocated to this sector.

We develop an evolutionary model for individual discriminatory behavior that emerges naturally in a mixed population as an adaptive strategy. Our findings show that, when individuals have finite memory and face uncertain environments, they may rely on prior biases and observable group traits to make decisions, changing their discriminatory practices. We also demonstrate that a finite memory is a consequence of natural selection because it leads to higher fitness in dynamic environments with mutations. This adaptability allows individuals with finite memory to better respond to environmental variability, offering a potential evolutionary advantage. Our study suggests that memory constraints and environmental changes are critical factors in sustaining biased behavior, suggesting insights into the persistence of discrimination in real-world settings and possible mitigation strategies across fields, including education, policymaking, and artificial intelligence.

CONTEXT: Cell and gene therapies (CGTs) offer treatment to rare and oftentimes deadly diseases. Because of their high price and uncertain clinical outcomes, US insurers commonly restrain patient access to CGTs, and these barriers may create or perpetuate existing disparities. A reconsideration of existing insurance policies to improve access and reduce disparities is currently underway. One method insurers use to support access and protect them from large, unexpected claims is the purchase of reinsurance. In exchange for an upfront per-member-per-month (PMPM) premium, the reinsurer pays the claim and rebates the insurer at the end of the contract period if there are funds leftover. However, existing reinsurance plans may not cover CGTs or charge exorbitant fees for coverage.

METHODS: We simulate the incremental annual per-person reinsurer costs to cover CGTs existing or expected between 2023 and 2035 for the US population and by payer type based on previously published estimates of expected US spending on CGTs, assumed US population of 330 persons, and current CGT reinsurance fees. We illustrate our methods by estimating the incremental annual per-person costs overall payers and to state Medicaid plans of sickle cell disease–targeted CGTs.

FINDINGS: We estimate annual incremental spending on CGTs 2023–2035 to amount to $20.4 billion, or $15.69 per person. Total annual estimated spending is expected to concentrate among commercial plans. Sickle cell–targeted CGTs add a maximum of $0.78 PMPM in costs to all payers and will concentrate within state Medicaid programs. Reinsurance fees add to expected costs.

CONCLUSIONS: Annual per-person costs to provide access to CGTs are expected to concentrate in commercial and state Medicaid plans. Policies that improve CGT coverage and affordability are needed.

Fusion energy faces many hurdles. The history of the biotech industry offers lessons for how to build public trust and create a robust investment ecosystem to help fusion achieve its potential.

Biomedicine is experiencing an inflection point in which the origins of many human diseases have been decoded, leading to new treatments and, in some cases, complete cures. Many domain experts acknowledge that the gating factor to innovation is not knowledge, but rather a lack of financial resources to translate theory into practice, the so-called “valley of death” between scientific discovery and the clinical testing that must be done with human subjects before regulators will approve a new drug or medical device. This process of translational medicine is largely an exercise in risk management—organized as a carefully planned sequence of experiments, each one involving a progressively larger number of subjects that may or may not be allowed to continue, depending on the results of the prior experiment. It is, therefore, a natural setting in which to apply modern portfolio theory. The authors describe one such application involving a biotechnology company focused on genetic diseases and the lessons learned from that experience.

Humans are not homo economicus (i.e., rational economic beings). As humans, we exhibit systematic behavioral biases such as loss aversion, anchoring, framing, etc., which lead us to make suboptimal economic decisions. Insofar as such biases may be embedded in text data on which large language models (LLMs) are trained, to what extent are LLMs prone to the same behavioral biases? Understanding these biases in LLMs is crucial for deploying LLMs to support human decision-making. We propose utility theory-a paradigm at the core of modern economic theory-as an approach to evaluate the economic biases of LLMs. Utility theory enables the quantification and comparison of economic behavior against benchmarks such as perfect rationality or human behavior. To demonstrate our approach, we quantify and compare the economic behavior of a variety of open- and closed-source LLMs. We find that the economic behavior of current LLMs is neither entirely human-like nor entirely economicus-like. We also find that most current LLMs struggle to maintain consistent economic behavior across settings. Finally, we illustrate how our approach can measure the effect of interventions such as prompting on economic biases.

We propose a new performance attribution framework that decomposes a constrained portfolio’s holdings, expected returns, variance, expected utility, and realized returns into components attributable to (1) the unconstrained mean-variance optimal portfolio; (2) individual static constraints; and (3) information, if any, arising from those constraints. A key contribution of our framework is the recognition that constraints may contain information that is correlated with returns, in which case imposing such constraints can affect performance. We extend our framework to accommodate estimation risk in portfolio construction using Bayesian portfolio analysis, which allows one to select constraints that improve—or are least detrimental to—future performance. We provide simulations and empirical examples involving constraints on environmental, social, and governance portfolios. Under certain scenarios, constraints may improve portfolio performance relative to a passive benchmark that does not account for the information contained in these constraints.

Within the contemporary context of environmental, social, and governance (ESG) investing principles, the authors explore the risk–reward characteristics of portfolios in the United States, Europe, and Japan constructed using the foundational tenets of Markowitz’s modern portfolio theory with data from six major ESG rating agencies. They document statistically significant excess returns in ESG portfolios from 2014 to 2020 in the United States and Japan. They propose several statistical and voting-based methods to aggregate individual ESG ratings, the latter based on the theory of social choice. They find that aggregating individual ESG ratings improves portfolio performance. In addition, the authors find that a portfolio based on Treynor–Black weights further improves the performance of ESG portfolios. Overall, these results suggest that significant signals in ESG rating scores can enhance portfolio construction despite their noisy nature.

We identify some of the most pressing issues facing the adoption of large language models (LLMs) in practical settings, and propose a research agenda to reach the next technological inflection point in generative AI. We focus on three challenges facing most LLM applications: domain-specific expertise and the ability to tailor that expertise to a user’s unique situation, trustworthiness and adherence to the user’s moral and ethical standards, and conformity to regulatory guidelines and oversight. These challenges apply to virtually all industries and endeavors in which LLMs can be applied, such as medicine, law, accounting, education, psychotherapy, marketing, and corporate strategy. For concreteness, we focus on the narrow context of financial advice, which serves as an ideal test bed both for determining the possible shortcomings of current LLMs and for exploring ways to overcome them. Our goal is not to provide solutions to these challenges—which will likely take years to develop—but to propose a framework and road map for solving them as part of a larger research agenda for improving generative AI in any application.

For precision genetic medicines to fulfill their potential as treatments for ultra-rare diseases, fresh approaches to academic– industry partnerships and data sharing are needed, together with regulatory change and adaptation of reimbursement models. Advances in gene therapy and gene editing technologies could revolutionize the ability to treat individuals with genetic disease, allowing treatments to be devised that target specific genetic mutations in people with even the rarest of disease indications. In 2018, a seven-year-old child with Batten disease received attention for becoming the first recipient of a customized antisense oligonucleotide (ASO) therapy specifically designed for her unique mutation1. Since then, multiple patients with ultra-rare genetic conditions have been treated with precision ASOs through academic-investigator-initiated programs. Development of these ASOs has been rapid, justified by the severity of the conditions being treated (for example, rapidly progressive neurologic degeneration), following streamlined regulatory processes. Here we discuss possible models for drug development, regulation and reimbursement that could allow these tailored genetic interventions to be scaled.

We identify some of the most pressing issues facing the adoption of large language models (LLMs) in practical settings and propose a research agenda to reach the next technological inflection point in generative AI. We focus on three challenges facing most LLM applications: domain-specific expertise and the ability to tailor that expertise to a user’s unique situation, trustworthiness and adherence to the user’s moral and ethical standards, and conformity to regulatory guidelines and oversight. These challenges apply to virtually all industries and endeavors in which LLMs can be applied, such as medicine, law, accounting, education, psychotherapy, marketing, and corporate strategy. For concreteness, we focus on the narrow context of financial advice, which serves as an ideal test bed both for determining the possible shortcomings of current LLMs and for exploring ways to overcome them. Our goal is not to provide solutions to these challenges—which will likely take years to develop—but rather to propose a framework and road map for solving them as part of a larger research agenda for improving generative AI in any application.

This paper explores the relationship between a firm's legal contracting environment and its innovation incentives. Using granular data from the pharmaceutical industry, we examine a contracting mechanism through which incumbents maintain market power: "pay-for-delay'' agreements to delay the market entry of competitors. Exploiting a shock where such contracts become legally tenuous, we find that affected incumbents subsequently increase their innovation activity across a variety of project-level measures. Exploring the nature of this innovation, we also find that it is more "impactful’’ from a scientific and commercial standpoint. The results provide novel evidence that restricting the contracting space can boost innovation at the firm level. However, at the extensive margin we find a reduction in innovation by new entrants in response to increased competition, suggesting a nuanced effect on aggregate innovation.