A novel machine learning-derived decision tree including uPA/PAI-1 for breast cancer care.

Background uPA and PAI-1 are breast cancer biomarkers that evaluate the benefit of chemotherapy (CT) for HER2-negative, estrogen receptor-positive, low or intermediate grade patients. Our objectives were to observe clinical routine use of uPA/PAI-1 and to build a new therapeutic decision tree integrating uPA/PAI-1. Methods We observed the concordance between CT indications proposed by a canonical decision tree representative of French practices (not including uPA/PAI-1) and actual CT prescriptions decided by a medical board which included uPA/PAI-1. We used a method of machine learning for the analysis of concordant and non-concordant CT prescriptions to generate a novel scheme for CT indications. Results We observed a concordance rate of 71% between indications proposed by the canonical decision tree and actual prescriptions. Discrepancies were due to CT contraindications, high tumor grade and uPA/PAI-1 level. Altogether, uPA/PAI-1 were a decisive factor for the final decision in 17% of cases by avoiding CT prescription in two-thirds of cases and inducing CT in other cases. Remarkably, we noted that in routine practice, elevated uPA/PAI-1 levels seem not to be considered as a sufficient indication for CT for N≤3, Ki 67≤30% tumors, but are considered in association with at least one additional marker such as Ki 67>14%, vascular invasion and ER-H score <150. Conclusions This study highlights that in the routine clinical practice uPA/PAI-1 are never used as the sole indication for CT. Combined with other routinely used biomarkers, uPA/PAI-1 present an added value to orientate the therapeutic choice.

Evaluation of Identified Stressors in Children and Adolescents After Super Storm Sandy.

Super Storm Sandy, one of the largest storms endured by the East Coast of theUnited States, devastated New Jersey and the eastern seaboard. Although naturaldisasters affect individuals of all ages, children are particularly vulnerable becausetheir sense of normalcy is altered. The purpose of this study was to explore theeffects that exposure to Super Storm Sandy had on children who resided in NewJersey. This was a non-experimental, quantitative, cross-sectional research study.Study participants were recruited via printed flyers at disaster resource sites and ona dedicated research team's Facebook site. Each participant completed theHurricane Stressors Assessment Tool for Children and Adolescents as a webbasedsurvey related to their experiences with the hurricane. One hundred andforty-one (141) children participated in this study. Age groups (preschool, child, andadolescent) had varied results based upon developmental level. Age was positivelyassociated with finding it harder to concentrate and pay attention (r = 0.18, p =0.04); feeling sad, down, or depressed (r = 0.17, p < 0.05); being quiet and withdrawn (r = 0.16, p = 0.05); feeling irritable and grouchy (r = 0.26, p < 0.05); and findingit harder to complete schoolwork (r = 0.32, p < 0.001). Certain parental perceptionsof their child's behavior were negatively associated with the age of the child.Children had varying degrees of experiences after Sandy. Adolescents were shownto be more aware and affected by the storm than younger children. Observationscan be used for intervention initiatives in the post-natural disaster period, encouraginghealthcare providers to acknowledge family and community healing to provideadequate mental health referrals in the post-disaster period.

High-throughput ovarian follicle counting by an innovative deep learning approach.

The evaluation of the number of mouse ovarian primordial follicles (PMF) can provide important information about ovarian function, regulation of folliculogenesis or the impact of chemotherapy on fertility. This counting, usually performed by specialized operators, is a tedious, time-consuming but indispensable procedure.The development and increasing use of deep machine learning algorithms promise to speed up and improve this process. Here, we present a new methodology of automatically detecting and counting PMF, using convolutional neural networks driven by labelled datasets and a sliding window algorithm to select test data. Trained from a database of 9 millions of images extracted from mouse ovaries, and tested over two ovaries (3 millions of images to classify and 2 000 follicles to detect), the algorithm processes the digitized histological slides of a completed ovary in less than one minute, dividing the usual processing time by a factor of about 30. It also outperforms the measurements made by a pathologist through optical detection. Its ability to correct label errors enables conducting an active learning process with the operator, improving the overall counting iteratively. These results could be suitable to adapt the methodology to the human ovarian follicles by transfer learning.

Multiplex ligation-dependent probe amplification analysis on capillary electrophoresis instruments for a rapid gene copy number study.

Annotated DNA samples that had been previously analyzed were tested using multiplex ligation-dependent probe amplification (MLPA) assays containing probes targeting BRCA1, BRCA2, and MMR (MLH1/MSH2 genes) and the 9p21 chromosomal region. MLPA polymerase chain reaction products were separated on a capillary electrophoresis platform, and the data were analyzed using GeneMapper v4.0 software (Applied Biosystems, Foster City, CA). After signal normalization, loci regions that had undergone deletions or duplications were identified using the GeneMapper Report Manager and verified using the DyeScale functionality. The results highlight an easy-to-use, optimal sample preparation and analysis workflow that can be used for both small- and large-scale studies.