Facial Image Analysis for Fully-Automatic Prediction of Difficult Endotracheal Intubation

Goal: Difficult tracheal intubation is a major cause of anesthesia related injuries with potential life threatening complications. Detection and anticipation of difficult airway in the preoperative period is thus crucial for the patients’ safety. We propose an automatic face analysis approach to detect morphological traits related to difficult intubation and improve its prediction. Methods: For this purpose, we have collected a database of 970 patients including photos, videos and ground truth data. Specific statistical face models have been learned using the faces in our database providing an automated parametrization of the facial morphology. The most discriminative morphological features are selected through the importance ranking provided by the random forest algorithm. The random forest approach has also been used to train a classifier on these selected features. We compare a threshold tuning method based on class prior with two methods which learn an optimal threshold on a training set for tackling the inherent imbalanced nature of the database. Results: Our fully-automated method achieves an AUC of 81.0% in a simplified experimental setup where only easy and difficult patients are considered. A further validation on the entire database has proven that our method is applicable for real-world difficult intubation prediction, with AUC = 77.9%. Conclusion: The system performance is in line with the state-of-the-art medical diagnosis, based on ratings provided by trained anesthesiologists, whose assessment is guided by an extensive set of criteria. Significance: We present the first completely automatic and non-invasive difficult intubation detection system that is suitable for use in clinical settings.

Monitoring of Cardiovascular and Neurological Diseases Using Wearable Devices

Dionisije Sopic

In this thesis, I focus on monitoring of patients suffering from cardiovascular and neurological diseases through the use of wearable devices. The main diseases considered in this thesis are atrial fibrillation (AF), myocardial infarction (MI), and epilepsy. The proposed methods for the detection of the considered cardiovascular diseases use ECG as the main biosignal, whereas the main biosignal used for detecting epileptic seizures is EEG. Firstly, I propose a hierarchical heart-rhythm classification method for AF detection from a single lead ECG recording. The proposed method is based on the features that capture the morphology of important ECG signal segments, along with heart-rate oscillations and time and frequency domain features of the ECG signal. Furthermore, the classification scheme used in this method incorporates two different classifiers: a multiclass classifier and a random forest classifier, resulting in an F1 score of 78.95% for AF detection. Secondly, I address the problem of early detection and prevention of MI by introducing a real-time event-driven classification technique that uses a hierarchical classifier with multiple levels. The main goal of this technique is to maintain a high classification accuracy while reducing the complexity of the classification algorithm. The reduction in computational complexity, in turn, results in a longer battery life, which is an important factor for wearable devices. The proposed technique is validated on a public database and ported on a real-life wearable device. The experimental evaluation of the proposed technique on MI data shows that this scheme reduces the energy consumption by a factor of 2.60, with no significant loss in classification performance. The third chapter of this thesis is split into two parts and it focuses on epilepsy. In the first part, I present a real-time method for personalized epileptic seizure detection that uses EEG signals acquired from two electrode pairs: F7T3, and F8T4. The proposed method reaches a sensitivity of 90.98% and specificity of 92.10% on the database used in this study. Furthermore, this method is ported on a pair of eyeglasses in which the used electrodes are embedded and hidden in the temples, allowing for 2.71 days of operation on a single battery charge. This method overcomes the lack of portability and the effect of social stigma of EEG caps, which are used as a gold standard technique for epilepsy detection. Since the main pitfall of epilepsy detection algorithms is the unacceptably high number of false alarms, in the last part of my thesis, I propose an interpretable patient-specific approach to false alarm reduction for epilepsy detection. This approach is based on similarly occurring morphological EEG signal patterns (seizure signature) that occur frequently during seizures. The proposed approach has been experimentally validated on more than 5500 hours of long-term EEG recordings, resulting in a high classification performance with no false positive alarms. The high degree of interpretability of this method can help physicians discover seizures faster, as well as it can be used to improve data labeling quality in publicly available databases, which confirms its applicability for long-term seizure monitoring.

EPFL2020

Monitoring of Cardiovascular and Neurological Diseases Using Wearable Devices

Dionisije Sopic

EPFL2020