Abstract
The current algorithm to support platelets stock management assumes that there are always sufficient whole blood donations (WBD) to produce the required amount of pooled platelets. Unfortunately, blood donation rate is uncertain so there is the need to backup pooled platelets productions with single-donor (apheresis) collections to compensate periods of low WBD. The aim of this work was to predict the daily number of WBD to a tertiary care center to preemptively account for a decrease of platelets production. We have collected 62,248 blood donations during 3 years, the daily count of which was used to feed (standalone and ensemble versions of) six prediction models, which were evaluated using the Mean Absolute Error (MAE). Forecast models have shown better performances with a MAE of about 8.6 donations, 34% better than using means or medians alone. Trend lines of donations are better modeled by autoregressive integrated moving average (ARIMA) using a frequency of 365 days, the trade-off being the need for at least two years of data.

Abstract
Missing data is a problem found in real-world datasets that has a considerable impact on the learning process of classifiers. Although extensive work has been done in this field, the MNAR mechanism still remains a challenge for the existing imputation methods, mainly because it is not related with any observed information. Focusing on healthcare contexts, MNAR is present in multiple scenarios such as clinical trials where the participants may be quitting the study for reasons related to the outcome that is being measured. This work proposes an approach that uses different sources of information from the same healthcare context to improve the imputation quality and classification performance for datasets with missing data under MNAR. The experiment was performed with several databases from the medical context and the results show that the use of multiple sources of data has a positive impact in the imputation error and classification performance. © 2019, Springer Nature Switzerland AG.

Abstract

Abstract

Abstract

Abstract
Background Ulcerative colitis [UC] is a chronic inflammatory disease often accompanied by severe and distressing symptoms that, in some patients, might require a surgical intervention [colectomy]. This study aimed at determining the risk of experiencing progressive disease or requiring colectomy. Material and Methods This was a multicentre study: patients' data [n = 1481] were retrieved from the Portuguese database of inflammatory bowel disease patients. Bayesian networks and logistic regression were used to build risk matrices concerning the outcomes of interest. Results The derivation cohort included a total of 1210 patients, of whom 6% required a colectomy and 37% had progressive disease [over a median follow-up period of 12 syears]. The risk matrices show that previously hospitalised patients with extensive disease, who are not on immunomodulators and who are refractory to corticosteroid treatment, are the ones at the highest risk of undergoing a colectomy [88%]; whereas male patients, with extensive disease and less than 40 years old at diagnosis, are the ones at the highest risk of experiencing progressive disease [72%]. These results were internally and externally validated, and the AUC [area under the curve] of the ROC [receiver operating characteristic] analysis for the derivation cohort yielded a high discriminative power [92% for colectomy and 72% for progressive disease]. Conclusions This study allowed the construction of risk matrices that can be used to accurately predict a UC patient's likelihood of requiring a colectomy or of facing progressive disease, and can be used to individualise therapeutic strategies.