Yu, Kaixian

Accurate prediction of progression in subjects at risk of Alzheimer's disease is crucial for enrolling the right subjects in clinical trials. However, a prospective comparison of state-of-the-art algorithms for predicting disease onset and progression is currently lacking. We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of patient-specific biomarkers. On a limited, cross-sectional subset of the data emulating clinical trials, performance of the best algorithms at predicting clinical diagnosis decreased only slightly (2 percentage points) compared to the full longitudinal dataset. The submission system remains open via the website https://tadpole.grand-challenge.org, while TADPOLE SHARE (https://tadpole-share.github.io/) collates code for submissions. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

Abstract Despite the rapid progress in personalized cancer therapy (PCT) for breast cancer, no previous studies have used genomic predictors to choose among multiple chemotherapy regimens. It is unclear that given the current regimens how much PCT can improve the response rate for patients who will receive chemotherapy. In this study, we reanalyzed data from published studies of 1111 breast cancer patients who were treated with neoadjuvant chemotherapies. Those patients were divided into three regimen groups: an anthracycline alone, anthracycline plus paclitaxel, and anthracycline plus docetaxel. We developed a new strategy called PRES (Personalized REgimen Selection) to reassign the optimal regimen to each of the patients. First, a variable selection scheme was developed to identify significant genetic predictors for chemotherapy response. The selected genetic variables were then combined with clinical variables to build random forest models to predict the response of a patient to each regimen using pCR (pathological complete response) as the measure of response. The models were used to assign an optimal regimen to each patient to maximize the chance of pCR. We found that the expected rate of pCR was improved from 21.2% to 39.6% (95% CI: 34.6% - 43.0%). We also found that 31.1% of the patients may have been overtreated and 8.2% patients undertreated. A validation study on 21 cell lines showed that our prediction agrees with their paclitaxel-sensitivity profiles. We performed additional analysis on the Cancer Genome Atlas (TCGA) data and found that 18 of the 19 genes identified are significantly differentially expressed between normal and tumor tissues, and 2 of them, TAF6L and METRN (meteorin), are associated with overall survival. In conclusion, PRES could substantially increase response rates for breast cancer patients who will receive one of the widely-accepted chemotherapy regimens at present. Citation Format: Jinfeng Zhang, Kaixian Yu, Qingxiang Amy Sang, Winston Tan, Mayassa B. Dargham, Jun S. Liu, Ty Lively, Cedric Sheffield. Personalized chemotherapy regimen selection for breast cancer. [abstract]. In: Proceedings of the 107th Annual Meeting of the American Association for Cancer Research; 2016 Apr 16-20; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2016;76(14 Suppl):Abstract nr 2034.