Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

In many machine learning applications, we are faced with incomplete datasets. In the literature, missing data imputation techniques have been mostly concerned with filling missing values. However, the existence of missing values is synonymous with uncertainties not only over the distribution of missing values but also over target class assignments that require careful consideration. In this paper, we propose a simple and effective method for imputing missing features and estimating the distribution of target assignments given incomplete data. In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish. Following this, a predictor network is trained using the imputed samples from the generator network to capture the classification uncertainties and make predictions accordingly. The proposed method is evaluated on CIFAR-10 and MNIST image datasets as well as five real-world tabular classification datasets, under different missingness rates and structures. Our experimental results show the effectiveness of the proposed method in generating imputations as well as providing estimates for the class uncertainties in a classification task when faced with missing values.

Mohammad Kachuee, Hao Yuan, Young-Bum Kim, Sungjin Lee. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Healthcare big data remains under-utilized due to various incompatibility issues between the domains of data analytics and healthcare. The lack of generalizable iterative feature acquisition methods under budget and machine learning models that allow reasoning with a model’s uncertainty are two examples. Meanwhile, a boost to the available data is currently under way with the rapid growth in the Internet of Things applications and personalized healthcare. For the healthcare domain to be able to adopt models that take advantage of this big data, machine learning models should be coupled with more informative, germane feature acquisition methods, consequently adding robustness to the model’s results. We introduce an approach to feature selection that is based on Bayesian learning, allowing us to report the level of uncertainty in the model, combined with false-positive and false-negative rates. In addition, measuring target-specific uncertainty lifts the restriction on feature selection being target agnostic, allowing for feature acquisition based on a target of focus. We show that acquiring features for a specific target is at least as good as deep learning feature selection methods and common linear feature selection approaches for small non-sparse datasets, and surpasses these when faced with real-world data that is larger in scale and sparseness.

Effective representation learning of electronic health records is a challenging task and is becoming more important as the availability of such data is becoming pervasive. The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes. They are preempted by medical conditions the patient may have, and are typically recorded by medical staff. Accompanying codes are notes containing valuable information about patients beyond the structured information contained in electronic health records. We use transformer networks and the recently proposed BERT language model to embed these data streams into a unified vector representation. The presented approach effectively encodes a patient's visit data into a single a distributed representation, which can be used for downstream tasks. Our model demonstrates superior performance and generalization on mortality, readmission and length of stay tasks using the publicly available MIMIC-III ICU dataset.

In real-world scenarios, different features have different acquisition costs at test time which necessitates cost-aware methods to optimize the cost and performance tradeoff. This paper introduces a novel and scalable approach for cost-aware feature acquisition at test time. The method incrementally asks for features based on the available context that are known feature values. The proposed method is based on sensitivity analysis in neural networks and density estimation using denoising autoencoders with binary representation layers. In the proposed architecture, a denoising autoencoder is used to handle unknown features (i.e., features that are yet to be acquired), and the sensitivity of predictions with respect to each unknown feature is used as a context-dependent measure of informativeness. We evaluated the proposed method on eight different real-world data sets as well as one synthesized data set and compared its performance with several other approaches in the literature. According to the results, the suggested method is capable of efficiently acquiring features at test time in a cost- and context-aware fashion.

This paper presents a novel approach based on pulse transit time (PTT) for the estimation of blood pressure (BP). In order to achieve this goal, a data acquisition hardware is designed for high-resolution sampling of phonocardiogram (PCG) and photoplethysmogram (PPG). These two signals can derive PTT values. Meanwhile, a force-sensing resistor (FSR) is placed under the cuff of the BP reference device to mark the moments of measurements accurately via recording instantaneous cuff pressure. For deriving the PTT-BP models, a calibration procedure including a supervised physical exercise is conducted for each individual. The proposed method is evaluated on 24 subjects. The final results prove that using PCG for PTT measurement alongside the proposed models, the BP can be estimated reliably. Since the use of PCG requires a minimal low-cost hardware, the proposed method enables ubiquitous BP estimation in portable healthcare devices.

Recently a few methods have been proposed in the literature for non-invasive cuff-less estimation of systolic and diastolic blood pressures. One of the most prominent methods is to use the Pulse Transit Time (PTT). Although it is proven that PTT has a strong correlation with the systolic and diastolic blood pressures, this relation is highly dependent to each individuals physiological properties. Therefore, it requires per person calibration for accurate and reliable blood pressure estimation from PTT, which is a big drawback. To alleviate this issue, in this paper, a novel method is proposed for accurate and reliable estimation of blood pressure that is calibration-free. This goal is accomplished by extraction of several physiological parameters from Photoplethysmography (PPG) signal as well as utilizing signal processing and machine learning algorithms. The results show that the accuracy of the proposed method achieves grade B for the estimation of the diastolic blood pressure and grade C for the estimation of the mean arterial pressure under the standard British Hypertension Society (BHS) protocol.