Research Publications

Lo, Andrew W., Kien Wei Siah, and Chi Heem Wong, 2019, Harvard Data Science Review, https://doi.org/10.1162/99608f92.5c5f0525.

ABSTRACT We apply machine-learning techniques to predict drug approvals using drug-development and clinical-trial data from 2003 to 2015 involving several thousand drug-indication pairs with over 140 features across 15 disease groups. To deal with missing data, we use imputation methods that allow us to fully exploit the entire dataset, the largest of its kind. We show that our approach outperforms complete-case analysis, which typically yields biased inferences. We achieve predictive measures of 0.78, and 0.81 AUC (“area under the receiver operating characteristic curve,” the estimated probability that a classifier will rank a positive outcome higher than a negative outcome) for predicting transitions from phase 2 to approval and phase 3 to approval, respectively. Using five-year rolling windows, we document an increasing trend in the predictive power of these models, a consequence of improving data quality and quantity. The most important features for predicting success are trial outcomes, trial status, trial accrual rates, duration, prior approval for another indication, and sponsor track records. We provide estimates of the probability of success for all drugs in the current pipeline.

Available Here

More Research >>

Chaudhuri, Shomesh E., Katherine Cheng, Andrew W. Lo, Shirley Pepke, Sergio Rinaudo, Lynda Roman, and Ryan Spencer, 2019, Journal of Investment Management 17(2), 5–16.

ABSTRACT We consider a portfolio-based approach to financing ovarian cancer therapeutics in which multiple candidates are funded within a single structure. Twenty-five potential early-stage drug development projects were identified for inclusion in a hypothetical portfolio through interviews with gynecological oncologists and leading experts, a review of ovarian cancer-related trials registered in the ClinicalTrials.gov database, and an extensive literature review. The annualized returns of this portfolio were simulated under a purely private sector structure both with and without partial funding from philanthropic grants, and a public-private partnership that included government guarantees. We find that public-private structures of this type can increase expected returns and reduce tail risk, allowing greater amounts of private sector capital to fund early-stage research and development.

Download Paper (PDF) Download Software

More Research >>

Isakov, Leah, Andrew W. Lo, and Vahid Montazerhodjat, 2019, Journal of Econometrics 211(1), 117–136.

ABSTRACT Implicit in the drug-approval process is a host of decisions—target patient population, control group, primary endpoint, sample size, follow-up period, etc.—all of which determine the trade-off between Type I and Type II error. We explore the application of Bayesian decision analysis (BDA) to minimize the expected cost of drug approval, where the relative costs of the two types of errors are calibrated using U.S. Burden of Disease Study 2010 data. The results for conventional fixed-sample randomized clinical-trial designs suggest that for terminal illnesses with no existing therapies such as pancreatic cancer, the standard threshold of 2.5% is substantially more conservative than the BDA-optimal threshold of 23.9% to 27.8%. For relatively less deadly conditions such as prostate cancer, 2.5% is more risk-tolerant or aggressive than the BDA-optimal threshold of 1.2% to 1.5%. We compute BDA-optimal sizes for 25 of the most lethal diseases and show how a BDA-informed approval process can incorporate all stakeholders’ views in a systematic, transparent, internally consistent, and repeatable manner.

Available Here

More Research >>

Wong, Chi Heem, Kien Wei Siah, and Andrew W. Lo, 2019, Biostatistics 20, 273–286.

ABSTRACT Previous estimates of drug development success rates rely on relatively small samples from databases curated by the pharmaceutical industry and are subject to potential selection biases. Using a sample of 406 038 entries of clinical trial data for over 21 143 compounds from January 1, 2000 to October 31, 2015, we estimate aggregate clinical trial success rates and durations. We also compute disaggregated estimates across several trial features including disease type, clinical phase, industry or academic sponsor, biomarker presence, lead indication status, and time. In several cases, our results differ significantly in detail from widely cited statistics. For example, oncology has a 3.4% success rate in our sample vs. 5.1% in prior studies. However, after declining to 1.7% in 2012, this rate has improved to 2.5% and 8.3% in 2014 and 2015, respectively. In addition, trials that use biomarkers in patient-selection have higher overall success probabilities than trials without biomarkers.

Available Here

More Research >>

Das, Sonya, Raphaël Rousseau, Peter C. Adamson, and Andrew W. Lo, 2018, JAMA Oncology, published online June 2, doi:10.1001/jamaoncol.2018.1739.

ABSTRACT Few patient populations are as helpless and in need of advocacy as children with cancer. Pharmaceutical companies have historically faced significant financial disincentives to pursue pediatric oncology therapeutics, including low incidence, high costs of conducting pediatric trials, and a lack of funding for early-stage research. Review of published studies of pediatric oncology research and the cost of drug development, as well as clinical trials of pediatric oncology therapeutics at ClinicalTrials.gov, identified 77 potential drug development projects to be included in a hypothetical portfolio. The returns of this portfolio were simulated so as to compute the financial returns and risk. Simulated business strategies include combining projects at different clinical phases of development, obtaining partial funding from philanthropic grants, and obtaining government guarantees to reduce risk. The purely private-sector portfolio exhibited expected returns ranging from −24.2% to 10.2%, depending on the model variables assumed. This finding suggests significant financial disincentives for pursuing pediatric oncology therapeutics and implies that financial support from the public and philanthropic sectors is essential. Phase diversification increases the likelihood of a successful drug and yielded expected returns of −5.3% to 50.1%. Standard philanthropic grants had a marginal association with expected returns, and government guarantees had a greater association by reducing downside exposure. An assessment of a proposed venture philanthropy fund demonstrated stronger performance than the purely private-sector–funded portfolio or those with traditional amounts of philanthropic support. A combination of financial and business strategies has the potential to maximize expected return while eliminating some downside risk—in certain cases enabling expected returns as high as 50.1%—that can overcome current financial disincentives and accelerate the development of pediatric oncology therapeutics.

Available Here

Fernandez, Jose Maria, Roger M. Stein, and Andrew W. Lo, 2012, Nature Biotechnology 30, 964-975.

ABSTRACT Biomedical innovation has become riskier, more expensive and more difficult to finance with traditional sources such as private and public equity. Here we propose a financial structure in which a large number of biomedical programs at various stages of development are funded by a single financial entity to substantially reduce the portfolio’s risk. The portfolio entity can finance its activities by issuing debt, a critical advantage because a much larger pool of capital is available for investment in debt versus equity. By employing financial engineering techniques such as securitization, it can raise even greater amounts of more-patient capital. In a simulation using historical data for new molecular entities in oncology from 1990 to 2011, we find that megafunds of $5−15 billion may yield average investment returns of 8.9−11.4% for equityholders and 5−8% for “research-backed-obligation” holders, which are lower than typical venture-capital hurdle rates but attractive to pension funds, insurance companies and other large institutional investors.

Download Paper (PDF)
Download FAQ (PDF)
Download Software

More Research Publications>>

Montazerhodjat, Vahid, Shomesh E. Chaudhuri, Daniel J. Sargent, and Andrew W. Lo, 2017, JAMA Oncology, published online April 13: doi:10.1001/jamaoncol.2017.0123.

ABSTRACT Randomized clinical trials (RCTs) currently apply the same statistical threshold of alpha = 2.5% for controlling for false-positive results or type 1 error, regardless of the burden of disease or patient preferences. Is there an objective and systematic framework for designing RCTs that incorporates these considerations on a case-by-case basis? Our prior hypothesis was that an alpha of 2.5% would not minimize the overall expected harm to current and future patients for the most deadly cancers, and that a less conservative alpha may be necessary. Our primary study outcomes involve measuring the potential harm to patients under both null and alternative hypotheses using NCI and Alliance data, and then computing BDA-optimal type 1 error rates and sample sizes for oncology RCTs. We computed BDA-optimal parameters for the 23 most common cancer sites using NCI data, and for the 10 Alliance clinical trials. For RCTs involving therapies for cancers with short survival times, no existing treatments, and low prevalence, the BDA-optimal type 1 error rates were much higher than the traditional 2.5%. For cancers with longer survival times, existing treatments, and high prevalence, the corresponding BDA-optimal error rates were much lower, in some cases even lower than 2.5%.

Available Here (subscription required)

More Research Publications>>

Montazerhodjat, Vahid, John J. Frishkopf, and Andrew W. Lo, 2016, Drug Discovery Today 21(3), 410-414.

ABSTRACT We extend the megafund concept for funding drug discovery to enable dynamic leverage in which the portfolio of candidate therapeutic assets is predominantly financed initially by equity, and debt is introduced gradually as assets mature and begin generating cash flows. Leverage is adjusted so as to maintain an approximately constant level of default risk throughout the life of the fund. Numerical simulations show that applying dynamic leverage to a small portfolio of orphan drug candidates can boost the return on equity almost twofold compared with securitization with a static capital structure. Dynamic leverage can also add significant value to comparable all-equity-financed portfolios, enhancing the return on equity without jeopardizing debt performance or increasing risk to equity investors.

Available Here

More Research Publications>>

Montazerhodjat, Vahid, David M. Weinstock, and Andrew W. Lo, 2016, Science Translational Medicine 8(327), 327ps6.

ABSTRACT A crisis is building over the prices of new transformative therapies for cancer, hepatitis C virus infection, and rare diseases. The clinical imperative is to offer these therapies as broadly and rapidly as possible. We propose a practical way to increase drug affordability through health care loans (HCLs)—the equivalent of mortgages for large health care expenses. HCLs allow patients in both multipayer and single-payer markets to access a broader set of therapeutics, including expensive short-duration treatments that are curative. HCLs also link payment to clinical benefit and should help lower per-patient cost while incentivizing the development of transformative therapies rather than those that offer small incremental advances. Moreover, we propose the use of securitization—a well-known financial engineering method—to finance a large diversified pool of HCLs through both debt and equity. Numerical simulations suggest that securitization is viable for a wide range of economic environments and cost parameters, allowing a much broader patient population to access transformative therapies while also aligning the interests of patients, payers, and the pharmaceutical
industry.

Available Here

More Research Publications>>

Kim, Esther S. and Andrew W. Lo, 2016, Journal of Investment Management 14(4), 87-101.

ABSTRACT Duchenne muscular dystrophy (DMD) is a rare genetic disorder affecting thousands of individuals, mainly young males, worldwide. Currently, the disease has no cure, and is fatal in all cases. Advances in our understanding of the disease and innovations in basic science have recently allowed biotechnology companies to pursue promising treatment candidates for the disease, but so far, only one drug with limited application has achieved FDA approval. In this case study, we profile the work of an early-stage life sciences company, Solid Biosciences, founded by a father of a young boy with DMD. In particular, we discuss Solid’s one-disease focus and its strategy to treat the disease with a diversified portfolio of approaches. The company is currently building a product pipeline consisting of genetic interventions, small molecules and biologics, and assistive devices, each aimed at addressing a different aspect of DMD. We highlight the potential for Solid’s business model and portfolio to achieve breakthrough treatments for the DMD patient community.

Download Paper (PDF)

More Research Publications>>