PSYKOSE: A Motor Activity Database of Patients with Schizophrenia

Abstract

or movements collected via mobile phones to predict certain healthstates or for performance outcomes is a very popular topic in both computer science and medical research. To be able to perform reliable and reproducible research, it is important to share data and results openly. In medicine, this is often difficult due to legal restrictions or due to the fact that data collected from clinical trials is seen as very valuable and something that should be kept "inhouse".In this paper, we, therefore, present PSYKOSE, a publiclyshared dataset consisting of motor activity data collected from body sensors. The dataset contains data collected from patients with schizophrenia, which is a severe mental disorder characterized by psychotic symptoms like hallucinations and delusions, as well as introvert symptoms like cognitive dysfunction and diminished motivation.In total, we have data from 22 patients with schizophreniaand 32 control persons. For each person in the dataset, we provide sensor data collected over several days in a row. In addition to the sensor data, we also provide some demographic data and medical assessments during the observation period. The schizophrenic state was assessed by medical experts from Haukeland University hospital.In addition to the data, we provide a baseline analysis andpossible use-cases of the dataset

ACM Multimedia BioMedia 2020 Grand Challenge Overview

“…In the future, we hope to continue the challenge over the next few years with different medical use-cases each year. The 2021 version will focus on mental health [12] using multimodal data from a variety of different data sources. In conclusion, we believe that the multimedia community can have a great impact on the field of medicine.…”