Inverse prediction models have commonly been developed to handle scalar data from physical experiments. However, it is not uncommon for data to be collected in functional form. When data are collected in functional form, it must be aggregated to fit the form of traditional methods, which often results in a loss of information. For expensive experiments, this loss of information can be costly. In this study, we introduce the functional inverse prediction (FIP) framework, a general approach which uses the full information in functional response data to provide inverse predictions with probabilistic prediction uncertainties obtained with the bootstrap. The FIP framework is a general methodology that can be modified by practitioners to accommodate many different applications and types of data. We demonstrate the framework, highlighting points of flexibility, with a simulation example and applications to weather data and to nuclear forensics. Results show how functional models can improve the accuracy and precision of predictions.
Zhang, Adah S.; Ostrom, Quinn T.; Kruchko, Carol; Rogers, Lisa; Peereboom, David M.; Barnholtz-Sloan, Jill S.
Background. Complete prevalence proportions illustrate the burden of disease in a population. This study estimates the 2010 complete prevalence of malignant primary brain tumors overall and by Central Brain Tumor Registry of the United States (CBTRUS) histology groups, and compares the brain tumor prevalence estimates to the complete prevalence of other common cancers as determined by the Surveillance, Epidemiology, and End Results Program (SEER) by age at prevalence (2010): children (0-14 y), adolescent and young adult (AYA) (15-39 y), and adult (40+ y). Methods. Complete prevalence proportions were estimated using a novel regression method extended from the Completeness Index Method, which combines survival and incidence data from multiple sources. In this study, two datasets, CBTRUS and SEER, were used to calculate complete prevalence estimates of interest. Results. Complete prevalence for malignant primary brain tumors was 47.59/100000 population (22.31, 48.49, and 57.75/100000 for child, AYA, and adult populations). The most prevalent cancers by age were childhood leukemia (36.65/100000), AYA melanoma of the skin (66.21/100000), and adult female breast (1949.00/100000). The most prevalent CBTRUS histologies in children and AYA were pilocytic astrocytoma (6.82/100000, 5.92/100000), and glioblastoma (12.76/100000) in adults. Conclusions. The relative impact of malignant primary brain tumors is higher among children than any other age group; it emerges as the second most prevalent cancer among children. Complete prevalence estimates for primary malignant brain tumors flls a gap in overall cancer knowledge, which provides critical information toward public health and health care planning, including treatment, decision making, funding, and advocacy programs.
Ovarian cancer (OvCa) is the fifth leading cause of cancer deaths in women and remains the deadliest gynecological cancer. Our study goal is to examine associations between diagnostic patterns and OvCa stages. We used the data from a web-based survey in which more than 500 women diagnosed with OvCa provided both free text responses and staging information. We employed text mining and natural language processing (NPL) to extract information on clinical diagnostic characteristics, together with 21 dichotomous symptomatic variables, patient-centered advocacy, and polytomous disease severity, with internal validation. We conducted multivariate analyses and developed tree-based classification models with the confirmation of Random Forest to determine important factors in the relationships of the clinical diagnostic characteristics with OvCa stages. Models including the symptoms, patient advocacy tendency, disease severity and doctors' responses as predictors, had a much better predictive power than those limited to doctors' responses alone, indicating that OvCa stage at diagnosis depends on more than just doctors' responses. Although effective early stage diagnosis and treatment remains a challenge, our analysis of patient-centered clinical diagnostic characteristics and symptoms shows that self-advocacy is essential for all women. The frontline physician is critically important in ensuring effective follow-up and timely treatment before diagnosis.