Neural Information Processing Systems http://nips.cc/

Further evaluation of both the accuracy of the uncertainty calibration and the prediction performance with "I don't know"

We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN represents each time-dependent trajectory as a directed graph and applies an enriched, more expressive GNAN to each graph. It allows users to control the interpretability-expressivity trade-off by grouping features and graphs to encode priors, and it provides feature, node, and graph-level interpretability. On real-world datasets, including mortality prediction from blood tests and fake-news detection, GMAN outperforms strong non-interpretable black-box baselines while delivering actionable, domain-aligned explanations.

Temporal Point Processes (TPPs) are widely used for modeling event sequences in various medical domains, such as disease onset prediction, progression analysis, and clinical decision support. Although TPPs effectively capture temporal dynamics, their lack of interpretability remains a critical challenge. Recent advancements have introduced interpretable TPPs. However, these methods fail to incorporate numerical features, thereby limiting their ability to generate precise predictions. To address this issue, we propose Hybrid-Rule Temporal Point Processes (HRTPP), a novel framework that integrates temporal logic rules with numerical features, improving both interpretability and predictive accuracy in event modeling. HRTPP comprises three key components: basic intensity for intrinsic event likelihood, rule-based intensity for structured temporal dependencies, and numerical feature intensity for dynamic probability modulation. To effectively discover valid rules, we introduce a two-phase rule mining strategy with Bayesian optimization. To evaluate our method, we establish a multi-criteria assessment framework, incorporating rule validity, model fitting, and temporal predictive accuracy. Experimental results on real-world medical datasets demonstrate that HRTPP outperforms state-of-the-art interpretable TPPs in terms of predictive performance and clinical interpretability. In case studies, the rules extracted by HRTPP explain the disease progression, offering valuable contributions to medical diagnosis.

Hypertension, a leading contributor to cardiovascular morbidity, underscores the need for accurate and continuous blood pressure (BP) monitoring. Photoplethysmography (PPG) presents a promising approach to this end. However, the precision of BP estimates derived from PPG signals has been the subject of ongoing debate, necessitating a comprehensive evaluation of their effectiveness and constraints. We developed a calibration-based Siamese ResNet model for BP estimation, using a signal input paired with a reference BP reading. We compared the use of normalized PPG (N-PPG) against the normalized Invasive Arterial Blood Pressure (N-IABP) signals as input. The N-IABP signals do not directly present systolic and diastolic values but theoretically provide a more accurate BP measure than PPG signals since it is a direct pressure sensor inside the body. Our strategy establishes a critical benchmark for PPG performance, realistically calibrating expectations for PPG's BP estimation capabilities. Nonetheless, we compared the performance of our models using different signal-filtering conditions to evaluate the impact of filtering on the results. We evaluated our method using the AAMI and the BHS standards employing the VitalDB dataset. The N-IABP signals meet with AAMI standards for both Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP), with errors of 1.29+-6.33mmHg for systolic pressure and 1.17+-5.78mmHg for systolic and diastolic pressure respectively for the raw N-IABP signal. In contrast, N-PPG signals, in their best setup, exhibited inferior performance than N-IABP, presenting 1.49+-11.82mmHg and 0.89+-7.27mmHg for systolic and diastolic pressure respectively. Our findings highlight the potential and limitations of employing PPG for BP estimation, showing that these signals contain information correlated to BP but may not be sufficient for predicting it accurately.

We propose two novel purpose-built deep learning (DL) models for synthesis of the arterial blood pressure (ABP) waveform in a cuff-less manner, using a single-site photoplethysmography (PPG) signal. We utilize the public UCI dataset on cuff-less blood pressure (CLBP) estimation to train and evaluate our DL models. Firstly, we implement a transformer model that incorporates positional encoding, multi-head attention, layer normalization, and dropout techniques, and synthesizes the ABP waveform with a mean absolute error (MAE) of 14. Secondly, we implement a frequency-domain (FD) learning approach where we first obtain the discrete cosine transform (DCT) coefficients of the PPG and ABP signals corresponding to two cardiac cycles, and then learn a linear/non-linear (L/NL) regression between them. We learn that the FD L/NL regression model outperforms the transformer model by achieving an MAE of 11.87 and 8.01, for diastolic blood pressure (DBP) and systolic blood pressure (SBP), respectively. Our FD L/NL regression model also fulfills the AAMI criterion of utilizing data from more than 85 subjects, and achieves grade B by the BHS criterion.

Inpatient length of stay (LoS) is an important managerial metric which if known in advance can be used to efficiently plan admissions, allocate resources and improve care. Using historical patient data and machine learning techniques, LoS prediction models can be developed. Ethically, these models can not be used for patient discharge in lieu of unit heads but are of utmost necessity for hospital management systems in charge of effective hospital planning. Therefore, the design of the prediction system should be adapted to work in a true hospital setting. In this study, we predict early hospital LoS at the granular level of admission units by applying domain adaptation to leverage information learned from a potential source domain. Time-varying data from 110,079 and 60,492 patient stays to 8 and 9 intensive care units were respectively extracted from eICU-CRD and MIMIC-IV. These were fed into a Long-Short Term Memory and a Fully connected network to train a source domain model, the weights of which were transferred either partially or fully to initiate training in target domains. Shapley Additive exPlanations (SHAP) algorithms were used to study the effect of weight transfer on model explanability. Compared to the benchmark, the proposed weight transfer model showed statistically significant gains in prediction accuracy (between 1% and 5%) as well as computation time (up to 2hrs) for some target domains. The proposed method thus provides an adapted clinical decision support system for hospital management that can ease processes of data access via ethical committee, computation infrastructures and time.

Abstract: We propose a computationally efficient algorithm for seizure detection. Instead of using a purely data-driven approach, we develop a hybrid model-based/data-driven method, combining convolutional neural networks with factor graph inference. On the CHB-MIT dataset, we demonstrate that the proposed method can generalize well in a 6 fold leave-4-patientout evaluation. Moreover, it is shown that our algorithm can achieve as much as 5% absolute improvement in performance compared to previous data-driven methods. Abstract: Documentation of epileptic seizures plays an essential role in planning medical therapy. Solutions for automated epileptic seizure detection can help improve the current problem of incomplete and erroneous manual documentation of epileptic seizures.

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised manner. To overcome this limitation, we introduce the notion of input-dependent uncertainty to the attention mechanism, such that it generates attention for each feature with varying degrees of noise based on the given input, to learn larger variance on instances it is uncertain about. We learn this Uncertainty-aware Attention (UA) mechanism using variational inference, and validate it on various risk prediction tasks from electronic health records on which our model significantly outperforms existing attention models. The analysis of the learned attentions shows that our model generates attentions that comply with clinicians' interpretation, and provide richer interpretation via learned variance. Further evaluation of both the accuracy of the uncertainty calibration and the prediction performance with "I don't know'' decision show that UA yields networks with high reliability as well.