[NOVEL TECHNOLOGIES AND FUTURE TRENDS IN TRANSLATIONAL RESEARCH IN ONCOLOGY].

INTRODUCTION: Translational research in medicine has undergone significant changes in the last decade, primarily due to the remarkable technological advancements made during this period. Oncology research is at the forefront of translational research in medicine and is heavily influenced by these changes. In this article, we briefly review the technologies that form the basis for the "next generation of translational research" in oncology in the coming decades, as well as the emerging trends in translational research in oncology through the implementation of these technologies.

Masking important information to assess the robustness of a multimodal classifier for emotion recognition.

Deep neural networks have been proven effective in classifying human interactions into emotions, especially by encoding multiple input modalities. In this work, we assess the robustness of a transformer-based multimodal audio-text classifier for emotion recognition, by perturbing the input at inference time using attacks which we design specifically to corrupt information deemed important for emotion recognition. To measure the impact of the attacks on the classifier, we compare between the accuracy of the classifier on the perturbed input and on the original, unperturbed input. Our results show that the multimodal classifier is more resilient to perturbation attacks than the equivalent unimodal classifiers, suggesting that the two modalities are encoded in a way that allows the classifier to benefit from one modality even when the other one is slightly damaged.

Morphological characteristics of spoken language in schizophrenia patients - an exploratory study.

Psychosis is diagnosed based on disruptions in the structure and use of language, including reduced syntactic complexity, derailment, and tangentiality. With the development of computational analysis, natural language processing (NLP) techniques are used in many areas of life to make evaluations and inferences regarding people's thoughts, feelings and behavior. The present study explores morphological characteristic of schizophrenia inpatients using NLP. Transcripts of recorded stories by 49 male subjects (24 inpatients diagnosed with schizophrenia and 25 controls) about 14 Thematic Apperception Test (TAT) pictures were morphologically analyzed. Relative to the control group, the schizophrenic inpatients employed: (1) a similar ratio of nouns, but fewer verbs, adjectives and adverbs; (2) a higher ratio of lemmas to token (LTR) and type to token (TTR); (3) a smaller gap between LTR and TTR; and (4) greater use of the first person. The results were cross-verified using three well-known fitting classifier algorithms (Random Forest, XGBoost and a support vector machine). Tests of prediction accuracy, precision and recall found correct attribution of patients to the schizophrenia group at a rate of between 80 and 90%. Overall, the results suggest that the language of schizophrenic inpatients is significantly different from that of healthy controls, being morphologically less complex, more associative and more focused on the self. The findings support NLP analysis as a complementary addition to the traditional clinical psychosis evaluation for schizophrenia.

The impact of tumor detection method on genomic and clinical risk and chemotherapy recommendation in early hormone receptor positive breast cancer.

BACKGROUND: Symptomatic breast cancers share aggressive clinico-pathological characteristics compared to screen-detected breast cancers. We assessed the association between the method of cancer detection and genomic and clinical risk, and its effect on adjuvant chemotherapy recommendations. PATIENTS AND METHODS: Patients with early hormone receptor positive (HR+) HER2neu-negative (HER2-) breast cancer, and known OncotypeDX Breast Recurrence Score test were included. A natural language processing (NLP) algorithm was used to identify the method of cancer detection. The clinical and genomic risks of symptomatic and screen-detected tumors were compared. RESULTS: The NLP algorithm identified the method of detection of 401 patients, with 216 (54%) diagnosed by routine screening, and the remainder secondary to symptoms. The distribution of OncotypeDX recurrence score (RS) varied between the groups. In the symptomatic group there were lower proportions of low RS (13% vs 23%) and higher proportions of high RS (24% vs. 13%) compared to the screen-detected group. Symptomatic tumors were significantly more likely to have a high clinical risk (59% vs 40%). Based on genomic and clinical risk and current guidelines, we found that women aged 50 and under, with a symptomatic cancer, had an increased probability of receiving adjuvant chemotherapy recommendation compared to women with screen-detected cancers (60% vs. 37%). CONCLUSIONS: We demonstrated an association between the method of cancer detection and both genomic and clinical risk. Symptomatic breast cancer, especially in young women, remains a poor prognostic factor that should be taken into account when evaluating patient prognosis and determining adjuvant treatment plans.

HybridMouse: A Hybrid Convolutional-Recurrent Neural Network-Based Model for Identification of Mouse Ultrasonic Vocalizations.

Mice use ultrasonic vocalizations (USVs) to convey a variety of socially relevant information. These vocalizations are affected by the sex, age, strain, and emotional state of the emitter and can thus be used to characterize it. Current tools used to detect and analyze murine USVs rely on user input and image processing algorithms to identify USVs, therefore requiring ideal recording environments. More recent tools which utilize convolutional neural networks models to identify vocalization segments perform well above the latter but do not exploit the sequential structure of audio vocalizations. On the other hand, human voice recognition models were made explicitly for audio processing; they incorporate the advantages of CNN models in recurrent models that allow them to capture the sequential nature of the audio. Here we describe the HybridMouse software: an audio analysis tool that combines convolutional (CNN) and recurrent (RNN) neural networks for automatically identifying, labeling, and extracting recorded USVs. Following training on manually labeled audio files recorded in various experimental conditions, HybridMouse outperformed the most commonly used benchmark model utilizing deep-learning tools in accuracy and precision. Moreover, it does not require user input and produces reliable detection and analysis of USVs recorded under harsh experimental conditions. We suggest that HybrideMouse will enhance the analysis of murine USVs and facilitate their use in scientific research.