Sagar Kamarthi

Zhenyuan Lu, Burcu Ozek, Sagar Kamarthi

Pain is a serious worldwide health problem that affects a vast proportion of the population. For efficient pain management and treatment, accurate classification and evaluation of pain severity are necessary. However, this can be challenging as pain is a subjective sensation-driven experience. Traditional techniques for measuring pain intensity, e.g. self-report scales, are susceptible to bias and unreliable in some instances. Consequently, there is a need for more objective and automatic pain intensity assessment strategies. In this paper, we develop PainAttnNet (PAN), a novel transfomer-encoder deep-learning framework for classifying pain intensities with physiological signals as input. The proposed approach is comprised of three feature extraction architectures: multiscale convolutional networks (MSCN), a squeeze-and-excitation residual network (SEResNet), and a transformer encoder block. On the basis of pain stimuli, MSCN extracts short- and long-window information as well as sequential features. SEResNet highlights relevant extracted features by mapping the interdependencies among features. The third module employs a transformer encoder consisting of three temporal convolutional networks (TCN) with three multi-head attention (MHA) layers to extract temporal dependencies from the features. Using the publicly available BioVid pain dataset, we test the proposed PainAttnNet model and demonstrate that our outcomes outperform state-of-the-art models. These results confirm that our approach can be utilized for automated classification of pain intensity using physiological signals to improve pain management and treatment.

Fatemeh Pouromran, Yingzi Lin, Sagar Kamarthi

Physiological responses to pain have received increasing attention among researchers for developing an automated pain recognition sensing system. Though less explored, Blood Volume Pulse (BVP) is one of the candidate physiological measures that could help objective pain assessment. In this study, we applied machine learning techniques on BVP signals to device a non-invasive modality for pain sensing. Thirty-two healthy subjects participated in this study. First, we investigated a novel set of time-domain, frequency-domain and nonlinear dynamics features that could potentially be sensitive to pain. These include 24 features from BVP signals and 20 additional features from Inter-beat Intervals (IBIs) derived from the same BVP signals. Utilizing these features, we built machine learning models for detecting the presence of pain and its intensity. We explored different machine learning models, including Logistic Regression, Random Forest, Support Vector Machines, Adaptive Boosting (AdaBoost) and Extreme Gradient Boosting (XGBoost). Among them, we found that the XGBoost offered the best model performance for both pain classification and pain intensity estimation tasks. The ROC-AUC of the XGBoost model to detect low pain, medium pain and high pain with no pain as the baseline were 80.06 %, 85.81 %, and 90.05 % respectively. Moreover, the XGboost classifier distinguished medium pain from high pain with ROC-AUC of 91%. For the multi-class classification among three pain levels, the XGBoost offered the best performance with an average F1-score of 80.03%. Our results suggest that BVP signal together with machine learning algorithms is a promising physiological measurement for automated pain assessment. This work will have a national impact on accurate pain assessment, effective pain management, reducing drug-seeking behavior among patients, and addressing national opioid crisis.

Burcu Ozek, Zhenyuan Lu, Srinivasan Radhakrishnan et al.

Improper pain management can lead to severe physical or mental consequences, including suffering, and an increased risk of opioid dependency. Assessing the presence and severity of pain is imperative to prevent such outcomes and determine the appropriate intervention. However, the evaluation of pain intensity is challenging because different individuals experience pain differently. To overcome this, researchers have employed machine learning models to evaluate pain intensity objectively. However, these efforts have primarily focused on point estimation of pain, disregarding the inherent uncertainty and variability present in the data and model. Consequently, the point estimates provide only partial information for clinical decision-making. This study presents a neural network-based method for objective pain interval estimation, incorporating uncertainty quantification. This work explores three algorithms: the bootstrap method, lower and upper bound estimation (LossL) optimized by genetic algorithm, and modified lower and upper bound estimation (LossS) optimized by gradient descent algorithm. Our empirical results reveal that LossS outperforms the other two by providing a narrower prediction interval. As LossS outperforms, we assessed its performance in three different scenarios for pain assessment: (1) a generalized approach (single model for the entire population), (2) a personalized approach (separate model for each individual), and (3) a hybrid approach (separate model for each cluster of individuals). Our findings demonstrate the hybrid approach's superior performance, with notable practicality in clinical contexts. It has the potential to be a valuable tool for clinicians, enabling objective pain intensity assessment while taking uncertainty into account. This capability is crucial in facilitating effective pain management and reducing the risks associated with improper treatment.

Sachini Weerasekara, Natasha Darras, Sagar Kamarthi et al.

Single-cell representation learning (SCRL) from gene expression data offers a way to uncover the complex regulatory logic underlying cellular function. Inspired by large language models in natural language modeling, several single-cell pretrained models have recently been proposed that treat genes as tokens and cells as sentences. However, these models are fundamentally limited by the long-tailed nature of cell-type distributions and struggle to generalize under covariate shifts in gene expression data. While fine-tuning is often used to mitigate these issues, we observe that performance remains bounded. To address this challenge, we introduce CellRefine, a post-pretraining method that operates between the pretraining and fine-tuning stages of a single-cell foundation model. CellRefine uses a multi-faceted objective that incorporates marker-gene sets as structural priors to guide post-pretraining and refine the latent embedding manifold of cells. Across multiple computational biology tasks, empirical results show that CellRefine consistently improves downstream performance, yielding gains up to 15%.

Ramin Mohammadi, Vahab vahdat, Sarthak Jain et al.

With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical data time window to maximize accuracy. This study investigates the impact of various observation windows ranging from the day of surgery to three years prior on predicting 30-day readmission following hip and knee arthroplasties. The dataset encompasses both structured encounter records (over 4 million) and unstructured clinical notes (80,000) from 7,174 patients. To extract meaning from the clinical notes, we employed a suite of non neural (BOW, count BOW, TF IDF, LDA) and neural encoders (BERT, 1D CNN, BiLSTM, Average). We subsequently evaluated models utilizing clinical notes alone, structured data alone, and a combination of both modalities. Our results demonstrate that the optimal time window for unstructured clinical notes is significantly shorter than for structured data, maximum predictive performance was achieved using notes from just three to six months prior to surgery. In contrast, performance using structured data improved as the time window lengthened, but strictly plateaued after twelve months. These modality-specific temporal patterns remained consistent regardless of model complexity or encoder type. Ultimately, these findings challenge the general assumption that more historical data inherently yields better machine learning predictions, establishing targeted time-window guidelines for optimizing readmission prediction models.

Sachini Weerasekara, Sagar Kamarthi, Jacqueline Isaacs

Predicting medical events in advance within critical care settings is paramount for patient outcomes and resource management. Utilizing predictive models, healthcare providers can anticipate issues such as cardiac arrest, sepsis, or respiratory failure before they manifest. Recently, there has been a surge in research focusing on forecasting adverse medical event onsets prior to clinical manifestation using machine learning. However, while these models provide temporal prognostic predictions for the occurrence of a specific adverse event of interest within defined time intervals, their interpretability often remains a challenge. In this work, we explore the applicability of neural temporal point processes in the context of adverse event onset prediction, with the aim of explaining clinical pathways and providing interpretable insights. Our experiments span six state-of-the-art neural point processes and six critical care datasets, each focusing on the onset of distinct adverse events. This work represents a novel application class of neural temporal point processes in event prediction.

Ramin Mohammadi, Sarthak Jain, Stephen Agboola et al.

Hypertension is a major risk factor for stroke, cardiovascular disease, and end-stage renal disease, and its prevalence is expected to rise dramatically. Effective hypertension management is thus critical. A particular priority is decreasing the incidence of uncontrolled hypertension. Early identification of patients at risk for uncontrolled hypertension would allow targeted use of personalized, proactive treatments. We develop machine learning models (logistic regression and recurrent neural networks) to stratify patients with respect to the risk of exhibiting uncontrolled hypertension within the coming three-month period. We trained and tested models using EHR data from 14,407 and 3,009 patients, respectively. The best model achieved an AUROC of 0.719, outperforming the simple, competitive baseline of relying prediction based on the last BP measure alone (0.634). Perhaps surprisingly, recurrent neural networks did not outperform a simple logistic regression for this task, suggesting that linear models should be included as strong baselines for predictive tasks using EHR