[Knowledge discovery in clinical psychiatry: learning from electronic health records]. / Kennisontwikkeling in de klinische psychiatrie: leren van elektronische patiëntendossiers.

BACKGROUND: Today, almost every psychiatric care institution registers information concerning the care they provide in an electronic health record (EHR). By analyzing these health care data with innovative and advanced techniques, they can be an important source of new knowledge in the near future, and thereby contribute to improving psychiatric care. AIM: To investigate how data from EHRs can provide relevant knowledge and insights for psychiatric care. METHOD: We designed and discussed solutions for some technical, organizational and ethical barriers surrounding unlocking health care data, in order to make analysis possible. We then analyzed the obtained health care data using techniques from knowledge discovery, the process in which new and useful information is extracted from data. We used techniques from data visualization, machine learning and natural language processing, among others, to demonstrate which types of results can be achieved. RESULTS: Our approach showed that it is possible to find new and interesting insights that are hidden in EHRs on an aggregated level, in collaboration with healthcare professionals and patients. In particular we showed how the risk of violent behavior can effectively and accurately be assessed based on clinical text in the EHR. CONCLUSION: After addressing some of the important challenges surrounding analyzing EHR data, learning from data from EHRs is a new and interesting approach with clear potential for improving psychiatric care.

[Data science in psychiatry]. / Datascience in de psychiatrie.

BACKGROUND: The information society is digitalising at a fast pace. New technology enables the collection of real life and real time information from sources that were inaccessible before. This creates an inordinate amount of dynamic data and, consequently, opportunities to introduce new insights and improvement of treatment in the field of psychiatry.
AIM: To clarify the definition of big data and how a big data approach can reform care into a data driven, patient oriented dynamic system which is constantly learning.
METHOD: Brief description of a pilot effected at the UMC Utrecht where the Cross Industry Standard Process for Interactive Data Mining (CRISP-IDM) was performed and description of applications in the future.
RESULTS: The described approach and examples from literature show that there are possibilities to realise quick improvements in practice and implement new insights from existing data sources.
CONCLUSION: Introduction of data science in psychiatric practice offers new prospects.

Functional neuromuscular stimulation neuroprostheses for the tetraplegic hand.

Functional neuromuscular stimulation (FNS) of the C5 and C6 tetraplegic upper extremity has been shown to be a valid clinical tool for restoring controlled movement in the paralyzed hand. The current clinical system consists of a shoulder position transducer controlling an external microprocessor-based stimulator, which excites paralyzed muscle via the peripheral nerve using percutaneous leads or a multichannel, implantable stimulator. Tendon transfer surgery of paralyzed but innervated muscle may augment the neurologically deficient upper extremity by allowing the substitution of stronger motors or the addition of new motors where flaccid paralysis (dennervation) eliminates the usual muscle from a grasp pattern. Sensory feedback in the form of machine state and cognitive information can be provided to the normally innervated C5 dermatome skin by subcutaneous electrodes. C5- and C6-level tetraplegics using FNS can independently perform single-hand manipulative tasks at a level similar to that of subjects with intact C7 roots, although they lack the elbow control.