Diss. (sammanfattning) Stockholm : Karol. inst., 2004. / Härtill 5 uppsatser.

Diss. (sammanfattning) Stockholm : Karol. inst., 2002. / Härtill 5 uppsatser.

Modern intelligent monitoring systems use digital computer technology to analyze and evaluate physiological vital signs. This analytical and evaluative process is performed by algorithms developed for this purpose. The degree of 'intelligence' of the monitoring system is dependent on the 'sensitivity' and 'specificity' of these algorithms. In order to develop robust and clinically valid algorithms, a database of representative waveforms is required. The aim of this thesis was to create a neonatal vital signs database to be used for this purpose, by means of a computer-based central station. The computer was interfaced to a number of neonatal monitors (Neonatal ICU, Groote Schuur Hospital). The monitors were interrogated to obtain patient condition, ECG waveforms and respiration waveforms using the impedance technique. When possible, percentage oxygen saturation was also captured. The database contains 509 documented clinical records obtained from 35 patients and 20 records containing examples of technical alarm conditions and high frequency noise. Additional patient record data is included. Clinical events recorded include apnoea, bradycardia, periodic breathing tachycardia, tachypnoea and normal traces. These events were recorded against a variety of signal quality conditions that have been characterized in Appendix C. A prototype rate detection algorithm was checked using samples from the database.

Diss. (sammanfattning) Stockholm : Karol. inst., 2004. / Härtill 6 uppsatser.

As more diagnostic testing options become available to physicians, it becomes more difficult to combine various types of medical information together in order to optimize the overall diagnosis. To improve diagnostic performance, here we introduce an approach to optimize a decision-fusion technique to combine heterogeneous information, such as from different modalities, feature categories, or institutions. For classifier comparison we used two performance metrics: The receiving operator characteristic (ROC) area under the curve [area under the ROC curve (AUC)] and the normalized partial area under the curve (pAUC). This study used four classifiers: Linear discriminant analysis (LDA), artificial neural network (ANN), and two variants of our decision-fusion technique, AUC-optimized (DF-A) and pAUC-optimized (DF-P) decision fusion. We applied each of these classifiers with 100-fold cross-validation to two heterogeneous breast cancer data sets: One of mass lesion features and a much more challenging one of microcalcification lesion features. For the calcification data set, DF-A outperformed the other classifiers in terms of AUC (p < 0.02) and achieved AUC=0.85 +/- 0.01. The DF-P surpassed the other classifiers in terms of pAUC (p < 0.01) and reached pAUC=0.38 +/- 0.02. For the mass data set, DF-A outperformed both the ANN and the LDA (p < 0.04) and achieved AUC=0.94 +/- 0.01. Although for this data set there were no statistically significant differences among the classifiers' pAUC values (pAUC=0.57 +/- 0.07 to 0.67 +/- 0.05, p > 0.10), the DF-P did significantly improve specificity versus the LDA at both 98% and 100% sensitivity (p < 0.04). In conclusion, decision fusion directly optimized clinically significant performance measures, such as AUC and pAUC, and sometimes outperformed two well-known machine-learning techniques when applied to two different breast cancer data sets. / Dissertation