Software technology enables computerized analysis to offer second opinion in various screening and diagnostic tasks to assist the clinicians. Yet, the performance of these computerized methods for medical images is questioned by experts in CAD research, owing to the use of different databases and criteria for evaluating the computer results for comparison. This paper intends to substantiate this statement by illustrating the effects of such issues with the use of 1D physiologic data and multiple databases. For this purpose, the detection of desaturation events in Sp02 and spike events in EEG are used. This is the first time that comparison between different algorithms on a common basis is carried out on an individual effort. The appraisal for all the algorithms is made on the same databases and criteria. It is surprising to find that issues for 2/3D images concur with those found in 1D data here. In evaluating the accuracy of a new algorithm, a single independent database gives results fast. This paper reveals weaknesses of such an approach. It is hoped that the supportive evidence shown here is enough for researchers to innovate a better platform for credibility in reporting performance comparison of computerized analysis algorithms.
Effect of amplitude criteria on the operating characteristics of algorithms for detecting OSAH events based on the analysis of oxygen saturation alone is investigated. The objective is to establish that there exists an oxygen desaturation level that leverages these algorithms to be more sensitive or more specific, irrespective of the differences in detection mechanism and database, a first ever attempt. Linear classification of algorithms from previous studies discovered that a drop in oxygen saturation of 3% or less makes the detection algorithms more sensitive while a drop of 4% or more makes it more specific. Results from two algorithms developed here also supported this. This finding explains the contradiction cited in the performance of algorithms from the different authors, which casts doubts on their detection ability. It could lead to the establishment of standard oxygen desaturation levels for screening and diagnosis of moderate/severe OSA, thus providing a more credible comparison basis for automated detection algorithms or even clinical tests.
Our objective is to automate the detection of apnea and hypopnea events in obstructive sleep apnea hypopnea (OSAH) syndrome based on analysis of arterial oxygen saturation signal alone. This is the first attempt where wavelet is used to detect OSAH events. Detection of OSAH events through wavelet depends on the fluctuations in the magnitude of the transformed coefficients, thus circumventing the problem of variability in the criteria on the magnitude and duration of the signal. Our work evaluates the performance of the wavelet transform to detect OSAH events against three conventional amplitude and duration algorithms. High performance in the detection of OSAH events can be achieved through the wavelet algorithm (score 96.55%, sensitivity 95.74% and specificity 97.02%) if the threshold on wavelet coefficients is individually tuned for each study. However, this is impossible in clinical practice. It is interesting to observe that the conventional methods based on amplitude and duration are able to attain a performance as close as this. The Nervus algorithm obtains the best result (score 96.66%, sensitivity 95.26% and specificity 97.46%) compared to the amplitude duration algorithm, the drop duration algorithm and the wavelet algorithm with global threshold, in descending order of performance.
Increased inter-equipment connectivity coupled with advances in Web technology allows ever escalating amounts of physiological data to be produced, far too much to be displayed adequately on a single computer screen. The consequence is that large quantities of insignificant data will be transmitted and reviewed. This carries an increased risk of overlooking vitally important transients. This paper describes a technique to provide an integrated solution based on a single algorithm for the efficient analysis, compression and remote display of long-term physiological signals with infrequent short duration, yet vital events, to effect a reduction in data transmission and display cluttering and to facilitate reliable data interpretation. The algorithm analyses data at the server end and flags significant events. It produces a compressed version of the signal at a lower resolution that can be satisfactorily viewed in a single screen width. This reduced set of data is initially transmitted together with a set of 'flags' indicating where significant events occur. Subsequent transmissions need only involve transmission of flagged data segments of interest at the required resolution. Efficient processing and code protection with decomposition alone is novel. The fixed transmission length method ensures clutter-less display, irrespective of the data length. The flagging of annotated events in arterial oxygen saturation, electroencephalogram and electrocardiogram illustrates the generic property of the algorithm. Data reduction of 87% to 99% and improved displays are demonstrated.