Secondary triage classification using an ensemble random forest technique.

BACKGROUND: Triage of patients in the emergency department is a complex task based on several uncertainties and ambiguous information. Triage must be implemented within two to five minutes to avoid potential fatality and increased waiting time. OBJECTIVE: An intelligent triage system has been proposed for use in a triage environment to reduce human error. METHODS: This system was developed based on the objective primary triage scale (OPTS) that is currently used in the Universiti Kebangsaan Malaysia Medical Center. Both primary and secondary triage models are required to develop this system. The primary triage model has been reported previously; this work focused on secondary triage modelling using an ensemble random forest technique. The randomized resampling method was proposed to balance the data unbalance prior to model development. RESULTS: The results showed that the 300% resampling gave a low out-of-bag error of 0.02 compared to 0.37 without pre-processing. This model has a sensitivity and specificity of 0.98 and 0.89, respectively, for the unseen data. CONCLUSION: With this combination, the random forest reduces the variance, and the randomized resembling reduces the bias, leading to the reduced out-of-bag error.

The application of empirical mode decomposition for the enhancement of cardiotocograph signals.

Cardiotocograph (CTG) is widely used in everyday clinical practice for fetal surveillance, where it is used to record fetal heart rate (FHR) and uterine activity (UA). These two biosignals can be used for antepartum and intrapartum fetal monitoring and are, in fact, nonlinear and non-stationary. CTG recordings are often corrupted by artifacts such as missing beats in FHR, high-frequency noise in FHR and UA signals. In this paper, an empirical mode decomposition (EMD) method is applied on CTG signals. A recursive algorithm is first utilized to eliminate missing beats. High-frequency noise is reduced using EMD followed by the partial reconstruction (PAR) method, where the noise order is identified by a statistical method. The obtained signal enhancement from the proposed method is validated by comparing the resulting traces with the output obtained by applying classical signal processing methods such as Butterworth low-pass filtering, linear interpolation and a moving average filter on 12 CTG signals. Three obstetricians evaluated all 12 sets of traces and rated the proposed method, on average, 3.8 out of 5 on a scale of 1(lowest) to 5 (highest).

Real-time signal processing for fetal heart rate monitoring.

An algorithm based on digital filtering, adaptive thresholding, statistical properties in the time domain, and differencing of local maxima and minima has been developed for the simultaneous measurement of the fetal and maternal heart rates from the maternal abdominal electrocardiogram during pregnancy and labor for ambulatory monitoring. A microcontroller-based system has been used to implement the algorithm in real-time. A Doppler ultrasound fetal monitor was used for statistical comparison on five volunteers with low risk pregnancies, between 35 and 40 weeks of gestation. Results showed an average percent root mean square difference of 5.32% and linear correlation coefficient from 0.84 to 0.93. The fetal heart rate curves remained inside a +/- 5-beats-per-minute limit relative to the reference ultrasound method for 84.1% of the time.

A comparison of abdominal ECG and Doppler ultrasound for fetal heart rate detection.

A fetal monitor has been developed for the measurement of the fetal and maternal heart rates from maternal abdominal electrocardiogram during pregnancy and labor for ambulatory monitoring. Developed algorithm of the fetal monitor is based on digital filtering, adaptive thresholding. statistical properties in the time domain and differencing of local maxima and minima. Five volunteers with low risk pregnancies, between 35 to 40 weeks of gestation and no evidence of labor, were studied for the fetal heart rate detection. A Doppler ultrasound fetal monitor was used to compare the accuracy of the measurement system. Results showed an average percent rms difference (PRD) of 5.32% in comparison with the reference ultrasound method. The fetal heart rates curve remained inside a +/- 5 beats/min limit relative to the reference ultrasound method for 84.1% of the time.

Antenatal assessment using the FECG obtained via abdominal electrodes.

During the past decade a variety of intrapartum fetal monitors have been constructed that process the entire fetal electrocardiogram (FECG), obtained via a scalp electrode. They therefore differ from conventional monitors in aiming to extract relevant timing and magnitude information from the morphology of the FECG rather than simply the RR interval and hence heart rate. An intrapartum monitor such as this has been successfully developed by ourselves. This paper describes the early results obtained whilst attempting to extend this form of monitoring forward into the antenatal period. In order to achieve this the FECG must be acquired via surface electrodes placed on the maternal abdomen, which yields a signal containing the FECG amidst a number of noise sources. Our investigations into the feasibility of "antenatal abdominal FECG analysis" have been on two fronts. The first has been to produce a bedside monitor similar in function to our intrapartum device, whilst the second has been to address the possibility of performing such monitoring in ambulant subjects. At present the antenatal bedside monitor has successfully extracted and processed the FECG in approximately 75% of the cases studied, with subjects ranging from 20 weeks through to term having been monitored. We also have demonstrated the feasibility of the long term monitoring of maternal and fetal heart rate using a portable instrument.