Detecting central apneas using multichannel signals in premature infants.

Objective. Monitoring of apnea of prematurity, performed in neonatal intensive care units by detecting central apneas (CAs) in the respiratory traces, is characterized by a high number of false alarms. A two-step approach consisting of a threshold-based apneic event detection algorithm followed by a machine learning model was recently presented in literature aiming to improve CA detection. However, since this is characterized by high complexity and low precision, we developed a new direct approach that only consists of a detection model based on machine learning directly working with multichannel signals.Approach. The dataset used in this study consisted of 48 h of ECG, chest impedance and peripheral oxygen saturation extracted from 10 premature infants. CAs were labeled by two clinical experts. 47 features were extracted from time series using 30 s moving windows with an overlap of 5 s and evaluated in sets of 4 consecutive moving windows, in a similar way to what was indicated for the two-step approach. An undersampling method was used to reduce imbalance in the training set while aiming at increasing precision. A detection model using logistic regression with elastic net penalty and leave-one-patient-out cross-validation was then tested on the full dataset.Main results. This detection model returned a mean area under the receiver operating characteristic curve value equal to 0.86 and, after the selection of a FPR equal to 0.1 and the use of smoothing, an increased precision (0.50 versus 0.42) at the expense of a decrease in recall (0.70 versus 0.78) compared to the two-step approach around suspected apneic events.Significance. The new direct approach guaranteed correct detections for more than 81% of CAs with lengthL≥ 20 s, which are considered among the most threatening apneic events for premature infants. These results require additional verifications using more extensive datasets but could lead to promising applications in clinical practice.

Prediction of Late-Onset Sepsis in Preterm Infants Using Monitoring Signals and Machine Learning.

OBJECTIVES: Prediction of late-onset sepsis (onset beyond day 3 of life) in preterm infants, based on multiple patient monitoring signals 24 hours before onset. DESIGN: Continuous high-resolution electrocardiogram and respiration (chest impedance) data from the monitoring signals were extracted and used to create time-interval features representing heart rate variability, respiration, and body motion. For each infant with a blood culture-proven late-onset sepsis, a Cultures, Resuscitation, and Antibiotics Started Here moment was defined. The Cultures, Resuscitation, and Antibiotics Started Here moment served as an anchor point for the prediction analysis. In the group with controls (C), an "equivalent crash moment" was calculated as anchor point, based on comparable gestational and postnatal age. Three common machine learning approaches (logistic regressor, naive Bayes, and nearest mean classifier) were used to binary classify samples of late-onset sepsis from C. For training and evaluation of the three classifiers, a leave-k-subjects-out cross-validation was used. SETTING: Level III neonatal ICU. PATIENTS: The patient population consisted of 32 premature infants with sepsis and 32 age-matched control patients. INTERVENTIONS: No interventions were performed. MEASUREMENTS AND MAIN RESULTS: For the interval features representing heart rate variability, respiration, and body motion, differences between late-onset sepsis and C were visible up to 5 hours preceding the Cultures, Resuscitation, and Antibiotics Started Here moment. Using a combination of all features, classification of late-onset sepsis and C showed a mean accuracy of 0.79 ± 0.12 and mean precision rate of 0.82 ± 0.18 3 hours before the onset of sepsis. CONCLUSIONS: Information from routine patient monitoring can be used to predict sepsis. Specifically, this study shows that a combination of electrocardiogram-based, respiration-based, and motion-based features enables the prediction of late-onset sepsis hours before the clinical crash moment.

Estimation of Heart Rate Directly from ECG Spectrogram in Neonate Intensive Care Units.

This paper presents a simple yet novel method to estimate the heart frequency (HF) of neonates directly from the ECG signal, instead of using the RR-interval signals as generally done in clinical practices. From this, the heart rate (HR) can be derived. Thus, we avoid the use of peak detectors and the inherent errors that come with them.Our method leverages the highest Power Spectral Densities (PSD) of the ECG, for the bins around the frequencies related to heart rates for neonates, as they change in time (spectrograms).We tested our approach with the monitoring data of 6 days for 52 patients in a Neonate Intensive Care Unit (NICU) and compared against the HR from a commercial monitor, which produced a sample every second. The comparison showed that 92.4% of the samples have a difference lower than 5bpm. Moreover, we obtained a median MAE (Mean Absolute Error) between subjects equal to 2.28 bpm and a median RMSE (Root Mean Square Error) equal to 5.82 bpm. Although tested for neonates, we hypothesize that this method can also be customized for other populations.Finally, we analyze the failure cases of our method and found a direct co-allocation of errors due to moments with higher PSD in the lower frequencies with the presence of critical alarms related to other physiological systems (e.g. desaturation).

Identifying User Preferences for a Digital Educational Solution for Young Seniors With Diabetes.

The Eindhoven Diabetes Education Simulator project was initiated to develop an educational solution that helps diabetes patients understand and learn more about their diabetes. This article describes the identification of user preferences for the development of such solutions. Young seniors (aged 50-65 years) with type 2 diabetes were chosen as the target group because they are likely to have more affinity with digital devices than older people and because 88% of the Dutch diabetes population is >50 years of age. Data about the target group were gathered through literature research and interviews. The literature research covered data about their device use and education preferences. To gain insight into the daily life of diabetes patients and current diabetes education processes, 20 diabetes patients and 10 medical experts were interviewed. The interviews were analyzed using affinity diagrams. Those diagrams, together with the literature data, formed the basis for two personas and corresponding customer journey maps. Literature showed that diabetes prevalence is inversely correlated to educational level. Computer and device use is relatively low within the target group, but is growing. The interviews showed that young seniors like to play board, card, and computer games, with others or alone. Family and loved ones play an important role in their lives. Medical experts are crucial in the diabetes education of young senior diabetes patients. These findings are translated into a list of design aspects that can be used for creating educational solutions.

Concept Development of the Eindhoven Diabetes Education Simulator Project.

OBJECTIVE: This study was designed to define the concept of an educational diabetes game following a user-centered design approach. MATERIALS AND METHODS: The concept development of the Eindhoven Diabetes Education Simulator (E-DES) project can be divided in two phases: concept generation and concept evaluation. Four concepts were designed by the multidisciplinary development team based on the outcomes of user interviews. Four other concepts resulted from the Diabetes Game Jam. Several users and experts evaluated the concepts. These user evaluations and a feasibility analysis served as input for an overall evaluation and discussion by the development team resulting in the final concept choice. RESULTS: The four concepts of the development team are a digital board game, a quiz platform, a lifestyle simulator, and a puzzle game. The Diabetes Game Jam resulted in another digital board game, two mobile swipe games, and a fairy tale-themed adventure game. The combined user evaluations and feasibility analysis ranked the quiz platform and the digital board game equally high. Each of these games fits one specific subgroup of users best: the quiz platform best fits an eager-to-learn, more individualistic patient, whereas the board game best fits a less-eager-to-learn, family-oriented patient. The choice for a specific concept is therefore highly dependent on the choice of our specific target audience. CONCLUSIONS: The user-centered design approach with multiple evaluations has enabled us to choose the most promising concept from eight different options. A digital board game is chosen for further development because the target audience for E-DES is the less-motivated, family-oriented patients.