A wavelet-based algorithm for automated analysis of external tocography: How does it compare to human interpretation?

BACKGROUND: Studies which use external tocography to explore the relationship between increased intrapartum uterine activity and foetal outcomes are feasible because the technology is safe and ubiquitous. However, periods of poor signal quality are common. We developed an algorithm which aims to calculate tocograph summary variables based on well-recorded contractions only, ignoring artefact and excluding sections deemed uninterpretable. The aim of this study was to test that algorithm's reliability. METHODS: Whole recordings from labours at ≥35 weeks of gestation were randomly selected without regard to quality. Contractions and rest intervals were measured by two humans independently, and by the algorithm using two sets of models; one based on a series of pre-defined thresholds, and another trained to imitate one of the human interpreters. The absolute agreement intraclass correlation coefficient (ICC) was calculated using a two-way random effects model. RESULTS: The training dataset included data from 106 tocographs. Of the tested algorithms, AdaBoost showed the highest initial cross-validated accuracy and proceeded to optimization. Forty tocographs were included in the validation set. The ICCs for the per tocograph mean contraction rates were; human B to human A: 0.940 (0.890-0.968), human A to initial models: 0.944 (0.898-0.970), human A to trained models 0.962 (0.927-0.980), human B to initial models: 0.930 (0.872-0.962), human B to trained models: 0.948 (0.903-0.972). CONCLUSIONS: The algorithm described approximates interpretation of external tocography performed by trained humans. The performance of the AdaBoost trained models was marginally superior compared to the initial models.

Sudden unexplained death in childhood (1-4 years) in Ireland: an epidemiological profile and comparison with SIDS.

OBJECTIVE: To examine the incidence of sudden unexplained death in children 1-4 years old (SUDC) in Ireland and to compare the epidemiological profile of SUDC with that of SIDS. DESIGN: All cases of sudden unexplained death in children <5 years in Ireland between 1994 and 2008 were reviewed. Epidemiological information obtained from parental questionnaires and post-mortem reports was examined, and data on cases ≥52 weeks compared with cases <52 weeks. RESULTS: SUDC accounted for 5% (n=44) of deaths in children aged 1-4 years during 1994-2008. During this period, the SIDS rate dropped from 0.71 to 0.34 per 1000 live births, while the SUDC rate increased from 0.08 to 0.18 deaths per 10 000 population aged 1-4 years. The median age of SUDC cases was 71.5 weeks, and the male/female ratio was 1.3:1. All died during a sleep period, 71% between 10pm and 8am, and more than two-thirds were found prone. Fewest cases occurred during July-September (11%), and a greater proportion occurred at weekends (55%). 52% (17/33) had symptoms (any) in the 48 h before death, and 35% (11/31) visited their general practitioner because of illness in the week preceding death. SUDC differed from SIDS in prevalence of maternal smoking (38% vs 72%, p<0.001), bed-sharing (17% vs 49%, p<0.001), and whether found prone (72% vs 23%, p<0.001). CONCLUSION: While SUDC shares some characteristics with SIDS, there are also some important differences. Further data collection will help determine whether SIDS and SUDC represent the same pathophysiological entity. Standardisation of protocols for investigating sudden deaths is urgently required for accurate diagnosis of cases.