Raum:
Saal New York 1
Topic:
Wissenschaftliches Programm
Topic 30: Weitere Themen
English programme
Format:
Symposium
Dauer:
90 Minuten
Besonderheiten:
Q&A-Funktion
In contrast to many other medical fields psychiatry still primarily relies on sparse information collected during in-clinic visits. Also, the accuracy of the patient-/care-giver reported measures is limited by the ability of introspection, compliance and memory performance. Symptoms that are observable by the clinician during in-clinic visits are restricted to a very sparse, artificial and highly controlled setting limiting their interpretability with respect to variability and manifestation in daily life. Smartphones and other smart devices and technologies are now part of daily life and provide the possibility to collect subjective (i.e. ecological momentary assessments) as well as objective (i.e sensor and task data) information with high frequency in real time both in the clinic and at home. In this symposium, we will illustrate how such technologies are now deployed to complement and potentially improve diagnostic procedures and the monitoring and implementation of treatment across different psychiatric and neurological diseases. In addition, it will be demonstrated how these tools are also used to study associations between mental health and environmental (risk) factors in the general population. We will show how such technologies provide valuable new insights into the interaction of patients and clinicians, but also everyday encounters as well as high-frequency information about the subjective and objective variability of symptoms in daily life both in the context of routine clinical assessments as well as in pharmaceutical clinical trials.
abgesagt: Deep learning for biomarkers in psychiatry
Details anzeigen
Psychiatry today must gain a better understanding of the common and distinct pathophysiological mechanisms underlying psychiatric disorders in order to deliver more effective, person-tailored treatments. To this end, it appears that the analysis of 'small' experimental samples using conventional statistical approaches has largely failed to capture the heterogeneity underlying psychiatric phenotypes. Modern algorithms and approaches from machine learning, particularly deep learning, provide new hope to address these issues given their outstanding prediction performance in other disciplines. The strength of deep learning algorithms is that they can implement very complicated, and in principle arbitrary predictor-response mappings efficiently. This power comes at a cost, the need for large training (and test) samples to infer the (sometimes over millions of) model parameters. This appears to be at odds with the as yet rather 'small' samples available in psychiatric human research to date (n < 10,000), and the ambition of predicting treatment at the single subject level (n = 1). Here, we aim at giving an overview on how we can yet use such models for prediction in psychiatry. We review how machine learning approaches compare to more traditional statistical hypothesis-driven approaches, how their complexity relates to the need of large sample sizes, and what we can do to optimally use these powerful techniques in psychiatric neuroscience.
abgesagt: Using interaction-based phenotyping to assess the behavioral and neural mechanisms of transdiagnostic social impairments in psychiatry
abgesagt: Digital biomarker monitoring of disease progession in clinical drug development for neuropsychiatric disorders
abgesagt: Digital phenotyping as a means for exploring associations between behaviour and subjective perception in health and in psychiatric conditions