Introduction

Machine learning models are increasingly applied to predict the drug development outcomes based on intermediary clinical trial results. A key challenge to this task is to address various forms of bias in the historical drug approval data.

Objective

We aimed to identify and mitigate the bias in drug approval predictions and quantify the impacts of debiasing in terms of financial value and drug safety.

Methods

We instantiated the Debiasing Variational Autoencoder, the state-of-the-art model for automated debiasing. We trained and evaluated the model on the Citeline dataset provided by Informa Pharma Intelligence to predict the final drug development outcome from phase II trial results.

Results

The debiased Debiasing Variational Autoencoder model achieved better performance (measured by the F1�1 score 0.48) in predicting the drug development outcomes than its un-debiased baseline (F1�1 score 0.25). It had a much higher true-positive rate than baseline (60% vs 15%), while its true-negative rate was slightly lower (88% vs 99%). The Debiasing Variational Autoencoder distinguished between drugs developed by large pharmaceutical firms and those by small biotech companies. The model prediction is strongly influenced by multiple factors such as prior approval of the drug for another indication, whether the trial meets the positive/negative endpoints, and the year when the trial is completed. We estimate that the debiased model generates financial value for the drug developer in six major therapeutic areas, with a range of US$763–1,365 million.

Conclusions

Our analysis shows that debiasing improves the financial efficiency of late-stage drug development. From the pharmacovigilance perspective, the debiased model is more likely to identify drugs that are both safe and effective. Meanwhile, it may predict a higher probability of success for drugs with potential adverse effects (because of its lower true-negative rate), thus it must be used with caution to predict the development outcomes of drug candidates currently in the pipeline.

We review the recent literature on financing biomedical innovation, with a specific focus on the drug development process and how it may be enhanced to improve outcomes. We begin by laying out stylized facts about the structure of the drug development process and its associated costs and risks, and we present evidence that the rate of discovery for life-saving treatments has declined over time while costs have increased. We make the argument that these structural features require drug development (i.e., biopharmaceutical) firms to rely on external financing and at the same time amplify market frictions that may hinder the ability of these firms to obtain financing, especially for treatments that may have large societal value relative to the benefits going to the firms and their investors. We then provide an overview of the evidence for various types of market frictions to which these drug development firms are exposed and discuss how these frictions affect their incentive to invest in the development of new drugs, leading to underinvestment in valuable treatments. In light of this evidence, numerous studies have proposed ways to overcome this funding gap, including the use of financial innovation. We discuss the potential of these approaches to improve outcomes.

Background: The authors estimate the probability of successful development and duration of clinical trials for medications to treat neuropathic and nociceptive pain. The authors also consider the effect of the perceived abuse potential of the medication on these variables.

Methods: This study uses the Citeline database to compute the probabilities of success, duration, and survivorship of pain medication development programs between January 1, 2000, and June 30, 2020, conditioned on the phase, type of pain (nociceptive vs. neuropathic), and the abuse potential of the medication.

Results: The overall probability of successful development of all pain medications from phase 1 to approval is 10.4% (standard error, 1.5%).Medications to treat nociceptive and neuropathic pain have a probability of successful development of 13.3% (standard error, 2.3%) and 7.1% (standard error, 1.9%), respectively. The probability of successful development of medications with high abuse potential and low abuse potential are 27.8% (standard error, 4.6%) and 4.7% (standard error, 1.2%), respectively. The most common period for attrition is between phase 3 and approval.

Conclusions: The authors’ data suggest that the unique attributes of pain medications, such as their abuse potential and intended pathology, can influence the probability of successful development and duration of development.

Objective: Provide US FDA and amyotrophic lateral sclerosis (ALS) society with a systematic, transparent, and quantitative framework to evaluate the efficacy of the ALS therapeutic candidate AMX0035 in its phase 2 trial, which showed statistically significant effects (p-value 3%) in slowing the rate of ALS progression on a relatively small sample size of 137 patients. Methods: We apply Bayesian decision analysis (BDA) to determine the optimal type I error rate (p-value) under which the clinical evidence of AMX0035 supports FDA approval. Using rigorous estimates of ALS disease burden, our BDA framework strikes the optimal balance between FDA’s need to limit adverse effects (type I error) and patients’ need for expedited access to a potentially effective therapy (type II error). We apply BDA to evaluate long-term patient survival based on clinical evidence from AMX0035 and Riluzole. Results: The BDA-optimal type I error for approving AMX0035 is higher than the 3% p-value reported in the phase 2 trial if the probability of the therapy being effective is at least 30%. Assuming a 50% probability of efficacy and a signal-to-noise ratio of treatment effect between 25% and 50% (benchmark: 33%), the optimal type I error rate ranges from 2.6% to 26.3% (benchmark: 15.4%). The BDA-optimal type I error rate is robust to perturbations in most assumptions except for a probability of efficacy below 5%. Conclusion: BDA provides a useful framework to incorporate subjective perspectives of ALS patients and objective burden-of-disease metrics to evaluate the therapeutic effects of AMX0035 in its phase 2 trial.

We study the performance of green portfolios in both the US and Chinese markets, constructed using a broad range of climate-related environmental metrics, including carbon emissions, water consumption, waste disposal, land and water pollutants, air pollutants, and natural resource use. We compare several popular long-only and long–short green portfolio construction methodologies and find that a method based on Treynor–Black weights offers the most robust performance, thanks to its ability to quantify alphas for individual assets using only a small number of parameters. In the United States, green portfolios (e.g., low-carbon portfolios) have realized positive alphas in excess of Fama–French factors, a significant portion of which can be explained by an unexpected increase in climate concerns over the past decade, rather than positive expected returns. In contrast, Chinese investors have borne a cost for holding green assets instead of brown assets over the past seven years, implying a positive carbon premium, the opposite of US markets.

Impact investing typically involves ranking and selecting assets based on a non-financial impact factor, such as the environmental, social, and governance (ESG) score and the prospect of developing a disease-curing drug. We develop a framework for constructing optimal impact portfolios and quantifying their financial performances. Under general bivariate distributions of the impact factor and residual returns from a multi-factor asset-pricing model, the construction and performance of optimal impact portfolios depend critically on the dependence structure (copula) between the two, which reduces to a correlation under normality assumptions. More generally, we explicitly derive the optimal portfolio weights under two widely-used copulas---the Gaussian copula and the Archimedean copula family, and find that the optimal weights depend on the tail characteristics of the copula. In addition, when the marginal distribution of residual returns is skewed or heavy-tailed, assets with the most extreme impact factors have lower weights than non-extreme assets due to their high risk. Our framework requires the estimation of only a constant number of parameters as the number of assets grow, an advantage over traditional Markowitz portfolios. Overall, these results provide a recipe for constructing and quantifying the performance of optimal impact portfolios with arbitrary dependence structures and return distributions.

Due to the “boundary effect” bias, PoS estimates in the most recent years are inflated. To address this issue, we compute a bias-adjustment factor using historical data and multiply the PoS in recent years by this factor.

In this article, the authors develop a data-driven peer grouping system using artificial intelligence (AI) tools to capture market perception and, in turn, group companies into clusters at various levels of granularity. In addition, they develop a continuous measure of similarity between companies; they use this measure to group companies into clusters and construct hedged portfolios. In the peer groupings, companies grouped in the same clusters had strong homogeneous risk and return profiles, whereas different clusters of companies had diverse, varying risk exposures. The authors extensively evaluated the clusters and found
that companies grouped by their method had higher out-of-sample return correlation but lower stability and interpretability than companies grouped by a standard industry classification system. The authors also develop an interactive visualization system for identifying AI-based clusters and similar companies.

Following the approval by the FDA of two COVID-19 vaccines, which are administered in two doses three to four weeks apart, we simulate the effects of various vaccine distribution policies on the cumulative number of infections and deaths in the United States in the presence of shocks to the supply of vaccines. Our forecasts suggest that allocating more than 50% of available doses to individuals who have not received their first dose can significantly increase the number of lives saved and significantly reduce the number of COVID-19 infections. We find that a 50% allocation saves on average 33% more lives, and prevents on average 32% more infections relative to a policy that guarantees a second dose within the recommended time frame to all individuals who have already received their first dose. In fact, in the presence of supply shocks, we find that the former policy would save on average 8, 793 lives and prevents on average 607, 100 infections while the latter policy would save on average 6, 609 lives and prevents on average 460, 743 infections.

Despite its success in financial markets and other domains, collective intelligence seems to fall short in many critical contexts, including infrequent but repeated financial crises, political polarization and deadlock, and various forms of bias and discrimination. We propose an evolutionary framework that provides fundamental insights into the role of heterogeneity and feedback loops in contributing to failures of collective intelligence. The framework is based on a binary choice model of behavior that affects fitness; hence, behavior is shaped by evolutionary dynamics and stochastic changes in environmental conditions. We derive collective intelligence as an emergent property of evolution in this framework, and also specify conditions under which it fails. We find that political polarization emerges in stochastic environments with reproductive risks that are correlated across individuals. Bias and discrimination emerge when individuals incorrectly attribute random adverse events to observable features that may have nothing to do with those events. In addition, path dependence and negative feedback in evolution may lead to even stronger biases and levels of discrimination, which are locally evolutionarily stable strategies. These results suggest potential policy interventions to prevent such failures by nudging the “madness of mobs” towards the “wisdom of crowds” through targeted shifts in the environment

We study the relationships between the real-time psychophysiological activity of professional traders, their financial transactions, and market fluctuations. We collected multiple physiological signals such as heart rate, blood volume pulse, and electrodermal activity of 55 traders at a leading global financial institution during their normal working hours over a nfive-day period. Using their physiological measurements, we implemented a novel metric of
trader’s “psychophysiological activation” to capture affect such as excitement, stress and irritation. We find statistically significant relations between traders’ psychophysiological activation levels and such as their financial transactions, market fluctuations, the type of financial products they traded, and their trading experience. We conducted post-measurement interviews with traders who participated in this study to obtain additional insights in the key
factors driving their psychophysiological activation during financial risk processing. Our work illustrates that psychophysiological activation plays a prominent role in financial risk processing for professional traders.

Background: With multimorbidity becoming the norm rather than the exception, the management of multiple chronic diseases is a major challenge facing healthcare systems worldwide.
Methods: Using a large, nationally representative database of electronic medical records from the United Kingdom spanning the years 2005–2016 and consisting over 4.5 million patients, we apply statistical methods and network analysis to identify comorbid pairs and triads of diseases and identify clusters of chronic conditions across different demographic groups. Unlike many previous studies, which generally adopt cross-sectional designs based on single snapshots of closed cohorts, we adopt a longitudinal approach to examine temporal changes in the patterns of multimorbidity. In addition, we perform survival analysis to examine the impact of multimorbidity on mortality.
Results: The proportion of the population with multimorbidity has increased by approximately 2.5 percentage points over the last decade, with more than 17% having at least two chronic morbidities. We find that the prevalence and the severity of multimorbidity, as quantified by the number of co-occurring chronic conditions, increase progressively with age. Stratifying by socioeconomic status, we find that people living in more deprived areas are more likely to be multimorbid compared to those living in more affluent areas at all ages. The same trend holds consistently for all years in our data. In general, hypertension, diabetes, and respiratory-related diseases demonstrate high in-degree centrality and eigencentrality, while cardiac disorders show high out-degree centrality.
Conclusions: We use data-driven methods to characterize multimorbidity patterns in different demographic groups and their evolution over the past decade. In addition to a number of strongly associated comorbid pairs (e.g., cardiac-vascular and cardiac-metabolic disorders), we identify three principal clusters: a respiratory cluster, a cardiovascular cluster, and a mixed cardiovascular-renal-metabolic cluster. These are supported by established pathophysiological mechanisms and shared risk factors, and largely confirm and expand on the results of existing studies in the medical literature. Our findings contribute to a more quantitative understanding of the epidemiology of multimorbidity, an important pre-requisite for developing more effective medical care and policy for multimorbid patients.

Disease-focused foundations have used venture philanthropy (VP) for decades to develop interventions that have patient impact and generate revenue to support their mission. We articulate the distinguishing motives and features of VP funds and their distinct role in the life sciences innovation ecosystem. In particular, we focus on how entrepreneurs and VP funds can work together to help patients and generate economic value. We recommend that entrepreneurs seeking VP support understand a fund’s mission and objectives, and position themselves to fit the fund’s strategic and financial portfolio needs. Finally, we provide case studies of three specific initiatives — the JDRF T1D Fund, targeting type 1 (juvenile) diabetes; MPM Capital’s Oncology Impact Fund; and the American Heart Association’s Cardeation Capital — to showcase these efforts and benefits in practice.