An expert system for the analysis and interpretation of evoked potentials based on fuzzy classification: application to brainstem auditory evoked potentials

Lightweight fuzzy processes in clinical computing

In spite of advances in computing hardware, many hospitals still have a hard time finding extra capacity in their production clinical information system to run artificial intelligence (AI) modules, for example: to support real-time drug-drug or drug-lab interactions; to track infection trends; to monitor compliance with case specific clinical guidelines; or to monitor/ control biomedical devices like an intelligent ventilator. Historically, adding AI functionality was not a major design concern when a typical clinical system is originally specified. AI technology is usually retrofitted 'on top of the old system' or 'run off line' in tandem with the old system to ensure that the routine work load would still get done (with as little impact from the AI side as possible). To compound the burden on system performance, most institutions have witnessed a long and increasing trend for intramural and extramural reporting, (e.g. the collection of data for a quality-control report in microbiology, or a meta-analysis of a suite of coronary artery bypass grafts techniques, etc.) and these place an ever-growing burden on typical the computer system's performance. We discuss a promising approach to adding extra AI processing power to a heavily-used system based on the notion 'lightweight fuzzy processing (LFP)', that is, fuzzy modules designed from the outset to impose a small computational load. A formal model for a useful subclass of fuzzy systems is defined below and is used as a framework for the automated generation of LFPs. By seeking to reduce the arithmetic complexity of the model (a hand-crafted process) and the data complexity of the model (an automated process), we show how LFPs can be generated for three sample datasets of clinical relevance.

Management of vestibular schwannomas (acoustic neuromas): the value of neurophysiology for evaluation and prediction of auditory function in 420 cases

OBJECTIVE

From 1978 to 1993, 1000 vestibular schwannomas were operated on at the Department of Neurosurgery at Nordstadt Hospital. The goal was to improve the chances of hearing preservation by recording auditory brain stem responses (ABRs). ABRs can be used for preoperative classification of cochlear nerve impairment and for prediction of the chances of hearing preservation.

PATIENTS AND METHODS

In addition to the previously described audiometric testing, the patients underwent perioperative and intraoperative bilateral ABR recording at 100-dB condensation and rarefaction click stimulation. The classification system of five types of ABRs, as presented before, is based on the presence and on the latencies of Waves I, III, and V, with a special emphasis on Wave III's representing the activity of the first brain stem nuclei within the auditory pathway. According to an analysis of 420 preoperative ABRs, in case of a preoperative Type 1 or 2, the rate of hearing preservation is 80%.

DISCUSSION

In the case of good clinical and audiometric hearing, a severely deteriorated ABR is mostly an indicator of severe nerve compression and adhesion by the tumor. In view of subsequently reported experiences with intraoperative ABR monitoring, the value of the presented system emphasizing the importance of Wave III is stressed and discussed with other views in the literature. The criteria presented here are not designed for recognition of retrocochlear disease but aim for evaluation of the state of the auditory nerve and its perspective.

CONCLUSION

By the presented classification of ABR Type B1 through B5, preoperative prediction of the likelihood of hearing preservation is improved.