Sarmad Mehrdad

Sarmad Mehrdad, Farah E. Shamout, Yao Wang et al.

Unrecognized patient deterioration can lead to high morbidity and mortality. Most existing deterioration prediction models require a large number of clinical information, typically collected in hospital settings, such as medical images or comprehensive laboratory tests. This is infeasible for telehealth solutions and highlights a gap in deterioration prediction models that are based on minimal data, which can be recorded at a large scale in any clinic, nursing home, or even at the patient's home. In this study, we propose and develop a prognostic model that predicts if a patient will experience deterioration in the forthcoming 3-24 hours. The model sequentially processes routine triadic vital signs: (a) oxygen saturation, (b) heart rate, and (c) temperature. The model is also provided with basic patient information, including sex, age, vaccination status, vaccination date, and status of obesity, hypertension, or diabetes. We train and evaluate the model using data collected from 37,006 COVID-19 patients at NYU Langone Health in New York, USA. The model achieves an area under the receiver operating characteristic curve (AUROC) of 0.808-0.880 for 3-24 hour deterioration prediction. We also conduct occlusion experiments to evaluate the importance of each input feature, where the results reveal the significance of continuously monitoring the variations of the vital signs. Our results show the prospect of accurate deterioration forecast using a minimum feature set that can be relatively easily obtained using wearable devices and self-reported patient information.

Sarmad Mehrdad, Avadesh Meduri, Ludovic Righetti

We present an iterative inverse reinforcement learning algorithm to infer optimal cost functions in continuous spaces. Based on a popular maximum entropy criteria, our approach iteratively finds a weight improvement step and proposes a method to find an appropriate step size that ensures learned cost function features remain similar to the demonstrated trajectory features. In contrast to similar approaches, our algorithm can individually tune the effectiveness of each observation for the partition function and does not need a large sample set, enabling faster learning. We generate sample trajectories by solving an optimal control problem instead of random sampling, leading to more informative trajectories. The performance of our method is compared to two state of the art algorithms to demonstrate its benefits in several simulated environments.

Sarmad Mehrdad, Maxime Sabbah, Vincent Bonnet et al.

This paper investigates whether a single, unified cost function can explain and predict human reaching movements, in contrast with existing approaches that rely on subject- or posture-specific optimization criteria. Using the Minimal Observation Inverse Reinforcement Learning (MO-IRL) algorithm, together with a seven-dimensional set of candidate cost terms, we efficiently estimate time-varying cost weights for a standard planar reaching task. MO-IRL provides orders-of-magnitude faster convergence than bilevel formulations, while using only a fraction of the available data, enabling the practical exploration of time-varying cost structures. Three levels of generality are evaluated: Subject-Dependent Posture-Dependent, Subject-Dependent Posture-Independent, and Subject-Independent Posture-Independent. Across all cases, time-varying weights substantially improve trajectory reconstruction, yielding an average 27% reduction in RMSE compared to the baseline. The inferred costs consistently highlight a dominant role for joint-acceleration regulation, complemented by smaller contributions from torque-change smoothness. Overall, a single subject- and posture-agnostic time-varying cost function is shown to predict human reaching trajectories with high accuracy, supporting the existence of a unified optimality principle governing this class of movements.

Sarmad Mehrdad, S. Farokh Atashzar

Recently skew-t mixture models have been introduced as a flexible probabilistic modeling technique taking into account both skewness in data clusters and the statistical degree of freedom (S-DoF) to improve modeling generalizability, and robustness to heavy tails and skewness. In this paper, we show that the state-of-the-art skew-t mixture models fundamentally suffer from a hidden phenomenon named here as "S-DoF explosion," which results in local minima in the shapes of normal kernels during the non-convex iterative process of expectation maximization. For the first time, this paper provides insights into the instability of the S-DoF, which can result in the divergence of the kernels from the mixture of t-distribution, losing generalizability and power for modeling the outliers. Thus, in this paper, we propose a regularized iterative optimization process to train the mixture model, enhancing the generalizability and resiliency of the technique. The resulting mixture model is named Finite Mixture of Multivariate Regulated Skew-t (FiMReSt) Kernels, which stabilizes the S-DoF profile during optimization process of learning. To validate the performance, we have conducted a comprehensive experiment on several real-world datasets and a synthetic dataset. The results highlight (a) superior performance of the FiMReSt, (b) generalizability in the presence of outliers, and (c) convergence of S-DoF.