Aporte de un sistema predictivo de contraloría médica en la gestión de licencias médicas electrónicas / Contributions of a predictive medical audit system in the electronic management of sick leaves

INTRODUCCIÓN: El retraso del procesamiento de las licencias médicas (LMs) representa un problema de salud pública en Chile, considerando que esto afecta el pago del subsidio a las personas destinado a realizar el reposo médico prescrito mientras no se pueda trabajar. El objetivo de este estudio fue explorar las diferencias en el tiempo de procesamiento de las licencias médicas electrónicas (LMEs) evaluadas por contraloría médica (CM) y las evaluadas por un sistema predictivo de contraloría médica (SPCM) basado en redes neuronales artificiales. MATERIALES Y MÉTODOS: El tiempo de procesamiento de LMEs procesadas con SPCM fue comparado con el tiempo de procesamiento de LMEs examinadas solo con CM, usando curvas de Kaplan Meier, prueba de log-rank y modelos multivariados de Cox. RESULTADOS: La tasa de procesamiento del SPCM fue entre 1,7 a 5,5 veces más rápida que la tasa de procesamiento de la CM, ajustando por potenciales confusores. DISCUSIÓN: La implementación del SPCM permitió disminuir el tiempo de procesamiento de las LMEs, beneficiando a los trabajadores afiliados al seguro público.

INTRODUCTION: The delay in the processing of sick leaves (SLs) is a public health pro-blem in Chile, considering that this affects the payment of the subsidy to the indivi-duals destined to perform the prescribed medical rest while unable to work. The aim of this study was to explore the differences in the processing time of electronic SLs (ESLs) evaluated by medical audit (MA) and the SLs evaluated by a predictive medi-cal audit system (PMAS) based on artificial neural networks. MATERIALS AND METHODS:The processing time of the ESLs that were processed by PMAS was compared with the processing time of those that were examined only by MA, using Kaplan Meier curves, log-rank test, and multivariate Cox models. RESULTS: The processing rate for PMAS was 1.7-fold to 5.5-fold faster than MA, after adjusting for potential confoun-ding variables. DISCUSSION: The implementation of the PMAS reduced the processing time of ESLs, which benefits the workers affiliated to the public insurance system in Chile. (AU)

Night-time cardiac autonomic modulation as a function of sleep-wake stages is modified in otherwise healthy overweight adolescents.

OBJECTIVE: Even though sympathetic dominance during the daytime period is well known, currently, scarce data exist on autonomic nervous system (ANS) regulation during sleep in pediatric obesity. We aimed to evaluate sleep cardiac ANS regulation in normal-weight (NW) and overweight and obese (OW) adolescents. PATIENTS/METHODS: In this study, 60 healthy adolescents (15.7 ± 0.7 years) belonging to a birth cohort since infancy were classified based on body mass index percentiles criteria as: OW (N = 27) or NW (N = 33). Sleep was evaluated by polysomnography (PSG) during two consecutive in-lab overnight sessions. Non-rapid eye movement (non-REM) sleep stages (stages 1, 2, and slow-wave sleep [SWS]), rapid eye movement (REM) sleep, and wakefulness (Wake) were scored. R-waves were detected automatically in the electrocardiographic (ECG) signal. An all-night heart rate variability analysis was conducted in the ECG signal, with several time- and frequency-domain measures calculated for each sleep-wake stage. Sleep time was divided into thirds (T1, T2, T3). The analysis was performed using a mixed-effects linear regression model. RESULTS: Sleep organization was comparable except for reduced REM sleep percentage in the OW group (p < 0.04). Shorter R-R intervals were found for all sleep stages in the OW group; time-domain measured standard deviation of all R-R intervals (RRSD) was lower during stage 2, SWS and REM sleep (all p < 0.05). The square root of the mean of the sum of the squares of differences between adjacent R-R intervals (RMSSD) was also lower only during wake after sleep onset (WASO) in T1 and T3 (p < 0.05). The OW group had increased very low- and low-frequency (LF) power during WASO (in T1 and T2), and LF power during stage 2 and REM sleep (in T2). During WASO in the OW group, high-frequency (HF) power was lower (in T1 and T2), and LF/HF ratio was higher (in T2, p < 0.007). CONCLUSIONS: Several sleep-stage-dependent changes in cardiac autonomic regulation characterized the OW group. As sleep-related ANS balance was disturbed in the absence of concomitant metabolic alterations in this sample of otherwise healthy OW adolescents, their relevance for pediatric obesity should be further explored throughout development.

Automated detection of apnea/hypopnea events in healthy children polysomnograms: preliminary results.

A methodology to detect sleep apnea/hypopnea events in the respiratory signals of polysomnographic recordings is presented. It applies empirical mode decomposition (EMD), Hilbert-Huang transform (HHT), fuzzy logic and signal preprocessing techniques for feature extraction, expert criteria and context analysis. EMD, HHT and fuzzy logic are used for artifact detection and preliminary detection of respiration signal zones with significant variations in the amplitude of the signal; feature extraction, expert criteria and context analysis are used to characterize and validate the respiratory events. An annotated database of 30 all-night polysomnographic recordings, acquired from 30 healthy ten-year-old children, was divided in a training set of 15 recordings (485 sleep apnea/hypopnea events), a validation set of five recordings (109 sleep apnea/hypopnea events), and a testing set of ten recordings (281 sleep apnea/hypopnea events). The overall detection performance on the testing data set was 89.7% sensitivity and 16.3% false-positive rate. The next step is to include discrimination among apneas, hypopneas and respiratory pauses.

Automated detection of rapid eye movements in children.

We present an automated multiple-step tool to identify Rapid Eye Movements (REMs) in the polysomnogram, based on modeling expert criteria. It begins by identifying the polysomnogram segments compatible with REMs presence. On these segments, high-energy REMs are identified. Then, vicinity zones around those REMs are defined, and lesser-energy REMs are sought in these vicinities. This strategy has the advantage that it can detect lesser-energy REMs without increasing much the false positive detections. Signal processing, feature extraction, and fuzzy logic tools are used to achieve the goal. The tool was trained and validated on a database consisting of 20 all-night polysomnogram recordings (160 hr) of healthy ten-year-old children. Preliminary results on the validation set show 85.5% sensitivity and a false positive rate of 16.2%. Our tool works on complete polysomnogram recordings, without the need of preprocessing, prior knowledge of the hypnogram, or noise-free segments selection.

Automated sleep-spindle detection in healthy children polysomnograms.

We present a new methodology to detect and characterize sleep spindles (SSs), based on the nonlinear algorithms, empirical-mode decomposition, and Hilbert-Huang transform, which provide adequate temporal and frequency resolutions in the electroencephalographic analysis. In addition, the application of fuzzy logic allows to emulate expert's procedures. Additionally, we built a database of 56 all-night polysomnographic recordings from children for training and testing, which is among the largest annotated databases published on the subject. The database was split into training (27 recordings), validation (10 recordings), and testing (19 recordings) datasets. The SS events were marked by sleep experts using visual inspection, and these marks were used as golden standard. The overall SS detection performance on the testing dataset of continuous all-night sleep recordings was 88.2% sensitivity, 89.7% specificity, and 11.9% false-positive (FP) rate. Considering only non-REM sleep stage 2, the results showed 92.2% sensitivity, 90.1% specificity, and 8.9% FP rate. In general, our system presents enhanced results when compared with most systems found in the literature, thus improving SS detection precision significantly without the need of hypnogram information.

Dual approach for automated sleep spindles detection within EEG background activity in infant polysomnograms.

An automated system for sleep spindles detection within EEG background activity, combining two different approaches, is presented. The first approach applies detection criteria on the sigma-band filtered EEG signal, including fuzzy thresholds. The second approach mimics an expert's procedure. A sleep spindle detection is validated if both approaches agree. The method was applied on a testing set, consisting of continuous sleep recordings of two patients, totaling 1132 epochs (pages). A total of 803 sleep spindles events were marked by the experts. Results showed an 87.7% agreement between the detection system and the medical experts.