Estimating explainable Alzheimer's disease likelihood map via clinically-guided prototype learning.

Identifying Alzheimer's disease (AD) involves a deliberate diagnostic process owing to its innate traits of irreversibility with subtle and gradual progression. These characteristics make AD biomarker identification from structural brain imaging (e.g., structural MRI) scans quite challenging. Using clinically-guided prototype learning, we propose a novel deep-learning approach through eXplainable AD Likelihood Map Estimation (XADLiME) for AD progression modeling over 3D sMRIs. Specifically, we establish a set of topologically-aware prototypes onto the clusters of latent clinical features, uncovering an AD spectrum manifold. Considering this pseudo map as an enriched reference, we employ an estimating network to approximate the AD likelihood map over a 3D sMRI scan. Additionally, we promote the explainability of such a likelihood map by revealing a comprehensible overview from clinical and morphological perspectives. During the inference, this estimated likelihood map served as a substitute for unseen sMRI scans for effectively conducting the downstream task while providing thorough explainable states.

Stage-Specific Brain Aging in First-Episode Schizophrenia and Treatment-Resistant Schizophrenia.

BACKGROUND: Brain age is a popular brain-based biomarker that offers a powerful strategy for using neuroscience in clinical practice. We investigated the brain-predicted age difference (PAD) in patients with schizophrenia (SCZ), first-episode schizophrenia spectrum disorders (FE-SSDs), and treatment-resistant schizophrenia (TRS) using structural magnetic resonance imaging data. The association between brain-PAD and clinical parameters was also assessed. METHODS: We developed brain age prediction models for the association between 77 average structural brain measures and age in a training sample of controls (HCs) using ridge regression, support vector regression, and relevance vector regression. The trained models in the controls were applied to the test samples of the controls and 3 patient groups to obtain brain-based age estimates. The correlations were tested between the brain PAD and clinical measures in the patient groups. RESULTS: Model performance indicated that, regardless of the type of regression metric, the best model was support vector regression and the worst model was relevance vector regression for the training HCs. Accelerated brain aging was identified in patients with SCZ, FE-SSDs, and TRS compared with the HCs. A significant difference in brain PAD was observed between FE-SSDs and TRS using the ridge regression algorithm. Symptom severity, the Social and Occupational Functioning Assessment Scale, chlorpromazine equivalents, and cognitive function were correlated with the brain PAD in the patient groups. CONCLUSIONS: These findings suggest additional progressive neuronal changes in the brain after SCZ onset. Therefore, pharmacological or psychosocial interventions targeting brain health should be developed and provided during the early course of SCZ.

The effect of hepatic steatosis on liver volume determined by proton density fat fraction and deep learning-measured liver volume.

OBJECTIVES: We aimed to evaluate the effect of hepatic steatosis (HS) on liver volume and to develop a formula to estimate lean liver volume correcting the HS effect. METHODS: This retrospective study included healthy adult liver donors who underwent gadoxetic acid-enhanced MRI and proton density fat fraction (PDFF) measurement from 2015 to 2019. The degree of HS was graded at 5% PDFF intervals from grade 0 (no HS; PDFF < 5.5%). Liver volume was measured with hepatobiliary phase MRI using deep learning algorithm, and standard liver volume (SLV) was calculated as the reference lean liver volume. The association between liver volume and SLV ratio with PDFF grades was evaluated using Spearman's correlation (ρ). The effect of PDFF grades on liver volume was evaluated using the multivariable linear regression model. RESULTS: The study population included 1038 donors (mean age, 31 ± 9 years; 689 men). Mean liver volume to SLV ratio increased according to PDFF grades (ρ = 0.234, p < 0.001). The multivariable analysis indicated that SLV (ß = 1.004, p < 0.001) and PDFF grade*SLV (ß = 0.044, p < 0.001) independently affected liver volume, suggesting a 4.4% increase in liver volume per one-point increment in the PDFF grade. PDFF-adjusted lean liver volume was estimated using the formula, liver volume/[1.004 + 0.044 × PDFF grade]. The mean estimated lean liver volume to SLV ratio approximated to one for all PDFF grades, with no significant association with PDFF grades (p = 0.851). CONCLUSION: HS increases liver volume. The formula to estimate lean liver volume may be useful to adjust for the effect of HS on liver volume. KEY POINTS: • Hepatic steatosis increases liver volume. • The presented formula to estimate lean liver volume using MRI-measured proton density fat fraction and liver volume may be useful to adjust for the effect of hepatic steatosis on measured liver volume.

Deep recurrent model for individualized prediction of Alzheimer's disease progression.

Alzheimer's disease (AD) is known as one of the major causes of dementia and is characterized by slow progression over several years, with no treatments or available medicines. In this regard, there have been efforts to identify the risk of developing AD in its earliest time. While many of the previous works considered cross-sectional analysis, more recent studies have focused on the diagnosis and prognosis of AD with longitudinal or time series data in a way of disease progression modeling. Under the same problem settings, in this work, we propose a novel computational framework that can predict the phenotypic measurements of MRI biomarkers and trajectories of clinical status along with cognitive scores at multiple future time points. However, in handling time series data, it generally faces many unexpected missing observations. In regard to such an unfavorable situation, we define a secondary problem of estimating those missing values and tackle it in a systematic way by taking account of temporal and multivariate relations inherent in time series data. Concretely, we propose a deep recurrent network that jointly tackles the four problems of (i) missing value imputation, (ii) phenotypic measurements forecasting, (iii) trajectory estimation of a cognitive score, and (iv) clinical status prediction of a subject based on his/her longitudinal imaging biomarkers. Notably, the learnable parameters of all the modules in our predictive models are trained in an end-to-end manner by taking the morphological features and cognitive scores as input, with our circumspectly defined loss function. In our experiments over The Alzheimers Disease Prediction Of Longitudinal Evolution (TADPOLE) challenge cohort, we measured performance for various metrics and compared our method to competing methods in the literature. Exhaustive analyses and ablation studies were also conducted to better confirm the effectiveness of our method.

A unified framework for personalized regions selection and functional relation modeling for early MCI identification.

Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely adopted to investigate functional abnormalities in brain diseases. Rs-fMRI data is unsupervised in nature because the psychological and neurological labels are coarse-grained, and no accurate region-wise label is provided along with the complex co-activities of multiple regions. To the best of our knowledge, most studies regarding univariate group analysis or multivariate pattern recognition for brain disease identification have focused on discovering functional characteristics shared across subjects; however, they have paid less attention to individual properties of neural activities that result from different symptoms or degrees of abnormality. In this work, we propose a novel framework that can identify subjects with early-stage mild cognitive impairment (eMCI) and consider individual variability by learning functional relations from automatically selected regions of interest (ROIs) for each subject concurrently. In particular, we devise a deep neural network composed of a temporal embedding module, an ROI selection module, and a disease-identification module. Notably, the ROI selection module is equipped with a reinforcement learning mechanism so it adaptively selects ROIs to facilitate the learning of discriminative feature representations from a temporally embedded blood-oxygen-level-dependent signals. Furthermore, our method allows us to capture the functional relations of a subject-specific ROI subset through the use of a graph-based neural network. Our method considers individual characteristics for diagnosis, as opposed to most conventional methods that identify the same biomarkers across subjects within a group. Based on the ADNI cohort, we validate the effectiveness of our method by presenting the superior performance of our network in eMCI identification. Furthermore, we provide insightful neuroscientific interpretations by analyzing the regions selected for the eMCI classification.

Electrophysiological Decoding of Spatial and Color Processing in Human Prefrontal Cortex.

The prefrontal cortex (PFC) plays a pivotal role in goal-directed cognition, yet its representational code remains an open problem with decoding techniques ineffective in disentangling task-relevant variables from PFC. Here we applied regularized linear discriminant analysis to human scalp EEG data and were able to distinguish a mental-rotation task versus a color-perception task with 87% decoding accuracy. Dorsal and ventral areas in lateral PFC provided the dominant features dissociating the two tasks. Our findings show that EEG can reliably decode two independent task states from PFC and emphasize the PFC dorsal/ventral functional specificity in processing the where rotation task versus the what color task.

Population-based and Personalized Reference Intervals for Liver and Spleen Volumes in Healthy Individuals and Those with Viral Hepatitis.

Background Reference intervals guiding volumetric assessment of the liver and spleen have yet to be established. Purpose To establish population-based and personalized reference intervals for liver volume, spleen volume, and liver-to-spleen volume ratio (LSVR). Materials and Methods This retrospective study consecutively included healthy adult liver donors from 2001 to 2013 (reference group) and from 2014 to 2016 (healthy validation group) and patients with viral hepatitis from 2007 to 2017. Liver volume, spleen volume, and LSVR were measured with CT by using a deep learning algorithm. In the reference group, the reference intervals for the volume indexes were determined by using the population-based (ranges encompassing the central 95% of donors) and personalized (quantile regression modeling of the 2.5th and 97.5th percentiles as a function of age, sex, height, and weight) approaches. The validity of the reference intervals was evaluated in the healthy validation group and the viral hepatitis group. Results The reference and healthy validation groups had 2989 donors (mean age ± standard deviation, 30 years ± 9; 1828 men) and 472 donors (mean age, 30 years ± 9; 334 men), respectively. The viral hepatitis group had 158 patients (mean age, 48 years ± 12; 95 men). The population-based reference intervals were 824.5-1700.0 cm3 for liver volume, 81.1-322.0 cm3 for spleen volume, and 3.96-13.78 for LSVR. Formulae and a web calculator (https://i-pacs.com/calculators) were presented to calculate the personalized reference intervals. In the healthy validation group, both the population-based and personalized reference intervals were used to classify the volume indexes of 94%-96% of the donors as falling within the reference interval. In the viral hepatitis group, when compared with the population-based reference intervals, the personalized reference intervals helped identify more patients with volume indexes outside the reference interval (liver volume, 21.5% [34 of 158] vs 13.3% [21 of 158], P = .01; spleen volume, 29.1% [46 of 158] vs 22.2% [35 of 158], P = .01; LSVR, 35.4% [56 of 158] vs 26.6% [42 of 158], P < .001). Conclusion Reference intervals derived from a deep learning approach in healthy adults may enable evidence-based assessments of liver and spleen volume in clinical practice. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Ringl in this issue.

An index based on deep learning-measured spleen volume on CT for the assessment of high-risk varix in B-viral compensated cirrhosis.

OBJECTIVES: Deep learning enables an automated liver and spleen volume measurements on CT. The purpose of this study was to develop an index combining liver and spleen volumes and clinical factors for detecting high-risk varices in B-viral compensated cirrhosis. METHODS: This retrospective study included 419 patients with B-viral compensated cirrhosis who underwent endoscopy and CT from 2007 to 2008 (derivation cohort, n = 239) and from 2009 to 2010 (validation cohort, n = 180). The liver and spleen volumes were measured on CT images using a deep learning algorithm. Multivariable logistic regression analysis of the derivation cohort developed an index to detect endoscopically confirmed high-risk varix. The cumulative 5-year risk of varix bleeding was evaluated with patients stratified by their index values. RESULTS: The index of spleen volume-to-platelet ratio was devised from the derivation cohort. In the validation cohort, the cutoff index value for balanced sensitivity and specificity (> 3.78) resulted in the sensitivity of 69.4% and the specificity of 78.5% for detecting high-risk varix, and the cutoff index value for high sensitivity (> 1.63) detected all high-risk varices. The index stratified all patients into the low (index value ≤ 1.63; n = 118), intermediate (n = 162), and high (index value > 3.78; n = 139) risk groups with cumulative 5-year incidences of varix bleeding of 0%, 1.0%, and 12.0%, respectively (p < .001). CONCLUSION: The spleen volume-to-platelet ratio obtained using deep learning-based CT analysis is useful to detect high-risk varices and to assess the risk of varix bleeding. KEY POINTS: • The criterion of spleen volume to platelet > 1.63 detected all high-risk varices in the validation cohort, while the absence of visible varix did not exclude all high-risk varices. • Visual varix grade ≥ 2 detected high-risk varix with a high specificity (96.5-100%). • Combining spleen volume-to-platelet ratio ≤ 1.63 and visual varix grade of 0 identified low-risk patients who had no high-risk varix and varix bleeding on 5-year follow-up.

Identifying resting-state effective connectivity abnormalities in drug-naïve major depressive disorder diagnosis via graph convolutional networks.

Major depressive disorder (MDD) is a leading cause of disability; its symptoms interfere with social, occupational, interpersonal, and academic functioning. However, the diagnosis of MDD is still made by phenomenological approach. The advent of neuroimaging techniques allowed numerous studies to use resting-state functional magnetic resonance imaging (rs-fMRI) and estimate functional connectivity for brain-disease identification. Recently, attempts have been made to investigate effective connectivity (EC) that represents causal relations among regions of interest. In the meantime, to identify meaningful phenotypes for clinical diagnosis, graph-based approaches such as graph convolutional networks (GCNs) have been leveraged recently to explore complex pairwise similarities in imaging/nonimaging features among subjects. In this study, we validate the use of EC for MDD identification by estimating its measures via a group sparse representation along with a structured equation modeling approach in a whole-brain data-driven manner from rs-fMRI. To distinguish drug-naïve MDD patients from healthy controls, we utilize spectral GCNs based on a population graph to successfully integrate EC and nonimaging phenotypic information. Furthermore, we devise a novel sensitivity analysis method to investigate the discriminant connections for MDD identification in our trained GCNs. Our experimental results validated the effectiveness of our method in various scenarios, and we identified altered connectivities associated with the diagnosis of MDD.

Toward an interpretable Alzheimer's disease diagnostic model with regional abnormality representation via deep learning.

In this paper, we propose a novel method for magnetic resonance imaging based Alzheimer's disease (AD) or mild cognitive impairment (MCI) diagnosis that systematically integrates voxel-based, region-based, and patch-based approaches into a unified framework. Specifically, we parcellate the brain into predefined regions based on anatomical knowledge (i.e., templates) and derive complex nonlinear relationships among voxels, whose intensities denote volumetric measurements, within each region. Unlike existing methods that use cubical or rectangular shapes, we consider the anatomical shapes of regions as atypical patches. Using complex nonlinear relationships among voxels in each region learned by deep neural networks, we extract a "regional abnormality representation." We then make a final clinical decision by integrating the regional abnormality representations over the entire brain. It is noteworthy that the regional abnormality representations allow us to interpret and understand the symptomatic observations of a subject with AD or MCI by mapping and visualizing these observations in the brain space. On the baseline MRI dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, our method achieves state-of-the-art performance for four binary classification tasks and one three-class classification task. Additionally, we conducted exhaustive experiments and analysis to validate the efficacy and potential of our method.

Modeling regional dynamics in low-frequency fluctuation and its application to Autism spectrum disorder diagnosis.

With the advent of neuroimaging techniques, many studies in the literature have validated the use of resting-state fMRI (rs-fMRI) for understanding functional mechanisms of the brain, as well as for identifying brain disorders or diseases. One of the main streams in recent studies of modeling and analyzing rs-fMRI data is to account for the dynamic characteristics of a brain. In this study, we propose a novel method that directly models the regional temporal BOLD fluctuations in a stochastic manner and estimates the dynamic characteristics in the form of likelihoods. Specifically, we modeled temporal BOLD fluctuation of individual Regions Of Interest (ROIs) by means of Hidden Markov Models (HMMs), and then estimated the 'goodness-of-fit' of each ROI's BOLD signals to the corresponding trained HMM in terms of a likelihood. Using estimated likelihoods of the ROIs over the whole brain as features, we built a classifier that can discriminate subjects with Autism Spectrum Disorder (ASD) from Typically Developing (TD) controls at an individual level. In order to interpret the trained HMMs and a classifier from a neuroscience perspective, we also conducted model analysis. First, we investigated the learned weight coefficients of a classifier by transforming them into activation patterns, from which we could identify the ROIs that are highly associated with ASD and TD groups. Second, we explored the characteristics of temporal BOLD signals in terms of functional networks by clustering them based on sequences of the hidden states decoded with the trained HMMs. We validated the effectiveness of the proposed method by achieving the state-of-the-art performance on the ABIDE dataset and observed insightful patterns related to ASD.

Group sparse reduced rank regression for neuroimaging genetic study.

The neuroimaging genetic study usually needs to deal with high dimensionality of both brain imaging data and genetic data, so that often resulting in the issue of curse of dimensionality. In this paper, we propose a group sparse reduced rank regression model to take the relations of both the phenotypes and the genotypes for the neuroimaging genetic study. Specifically, we propose designing a graph sparsity constraint as well as a reduced rank constraint to simultaneously conduct subspace learning and feature selection. The group sparsity constraint conducts feature selection to identify genotypes highly related to neuroimaging data, while the reduced rank constraint considers the relations among neuroimaging data to conduct subspace learning in the feature selection model. Furthermore, an alternative optimization algorithm is proposed to solve the resulting objective function and is proved to achieve fast convergence. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset showed that the proposed method has superiority on predicting the phenotype data by the genotype data, than the alternative methods under comparison.

Deep Learning in Medical Image Analysis.

This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

Multiple functional networks modeling for autism spectrum disorder diagnosis.

Despite countless studies on autism spectrum disorder (ASD), diagnosis relies on specific behavioral criteria and neuroimaging biomarkers for the disorder are still relatively scarce and irrelevant for diagnostic workup. Many researchers have focused on functional networks of brain activities using resting-state functional magnetic resonance imaging (rsfMRI) to diagnose brain diseases, including ASD. Although some existing methods are able to reveal the abnormalities in functional networks, they are either highly dependent on prior assumptions for modeling these networks or do not focus on latent functional connectivities (FCs) by considering discriminative relations among FCs in a nonlinear way. In this article, we propose a novel framework to model multiple networks of rsfMRI with data-driven approaches. Specifically, we construct large-scale functional networks with hierarchical clustering and find discriminative connectivity patterns between ASD and normal controls (NC). We then learn features and classifiers for each cluster through discriminative restricted Boltzmann machines (DRBMs). In the testing phase, each DRBM determines whether a test sample is ASD or NC, based on which we make a final decision with a majority voting strategy. We assess the diagnostic performance of the proposed method using public datasets and describe the effectiveness of our method by comparing it to competing methods. We also rigorously analyze FCs learned by DRBMs on each cluster and discover dominant FCs that play a major role in discriminating between ASD and NC. Hum Brain Mapp 38:5804-5821, 2017. © 2017 Wiley Periodicals, Inc.

State-space model with deep learning for functional dynamics estimation in resting-state fMRI.

Studies on resting-state functional Magnetic Resonance Imaging (rs-fMRI) have shown that different brain regions still actively interact with each other while a subject is at rest, and such functional interaction is not stationary but changes over time. In terms of a large-scale brain network, in this paper, we focus on time-varying patterns of functional networks, i.e., functional dynamics, inherent in rs-fMRI, which is one of the emerging issues along with the network modelling. Specifically, we propose a novel methodological architecture that combines deep learning and state-space modelling, and apply it to rs-fMRI based Mild Cognitive Impairment (MCI) diagnosis. We first devise a Deep Auto-Encoder (DAE) to discover hierarchical non-linear functional relations among regions, by which we transform the regional features into an embedding space, whose bases are complex functional networks. Given the embedded functional features, we then use a Hidden Markov Model (HMM) to estimate dynamic characteristics of functional networks inherent in rs-fMRI via internal states, which are unobservable but can be inferred from observations statistically. By building a generative model with an HMM, we estimate the likelihood of the input features of rs-fMRI as belonging to the corresponding status, i.e., MCI or normal healthy control, based on which we identify the clinical label of a testing subject. In order to validate the effectiveness of the proposed method, we performed experiments on two different datasets and compared with state-of-the-art methods in the literature. We also analyzed the functional networks learned by DAE, estimated the functional connectivities by decoding hidden states in HMM, and investigated the estimated functional connectivities by means of a graph-theoretic approach.

Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis.

For the last decade, it has been shown that neuroimaging can be a potential tool for the diagnosis of Alzheimer's Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), and also fusion of different modalities can further provide the complementary information to enhance diagnostic accuracy. Here, we focus on the problems of both feature representation and fusion of multimodal information from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). To our best knowledge, the previous methods in the literature mostly used hand-crafted features such as cortical thickness, gray matter densities from MRI, or voxel intensities from PET, and then combined these multimodal features by simply concatenating into a long vector or transforming into a higher-dimensional kernel space. In this paper, we propose a novel method for a high-level latent and shared feature representation from neuroimaging modalities via deep learning. Specifically, we use Deep Boltzmann Machine (DBM)(2), a deep network with a restricted Boltzmann machine as a building block, to find a latent hierarchical feature representation from a 3D patch, and then devise a systematic method for a joint feature representation from the paired patches of MRI and PET with a multimodal DBM. To validate the effectiveness of the proposed method, we performed experiments on ADNI dataset and compared with the state-of-the-art methods. In three binary classification problems of AD vs. healthy Normal Control (NC), MCI vs. NC, and MCI converter vs. MCI non-converter, we obtained the maximal accuracies of 95.35%, 85.67%, and 74.58%, respectively, outperforming the competing methods. By visual inspection of the trained model, we observed that the proposed method could hierarchically discover the complex latent patterns inherent in both MRI and PET.

A novel matrix-similarity based loss function for joint regression and classification in AD diagnosis.

Recent studies on AD/MCI diagnosis have shown that the tasks of identifying brain disease and predicting clinical scores are highly related to each other. Furthermore, it has been shown that feature selection with a manifold learning or a sparse model can handle the problems of high feature dimensionality and small sample size. However, the tasks of clinical score regression and clinical label classification were often conducted separately in the previous studies. Regarding the feature selection, to our best knowledge, most of the previous work considered a loss function defined as an element-wise difference between the target values and the predicted ones. In this paper, we consider the problems of joint regression and classification for AD/MCI diagnosis and propose a novel matrix-similarity based loss function that uses high-level information inherent in the target response matrix and imposes the information to be preserved in the predicted response matrix. The newly devised loss function is combined with a group lasso method for joint feature selection across tasks, i.e., predictions of clinical scores and a class label. In order to validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and showed that the newly devised loss function helped enhance the performances of both clinical score prediction and disease status identification, outperforming the state-of-the-art methods.

EAG-RS: A Novel Explainability-Guided ROI-Selection Framework for ASD Diagnosis via Inter-Regional Relation Learning.

Deep learning models based on resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used to diagnose brain diseases, particularly autism spectrum disorder (ASD). Existing studies have leveraged the functional connectivity (FC) of rs-fMRI, achieving notable classification performance. However, they have significant limitations, including the lack of adequate information while using linear low-order FC as inputs to the model, not considering individual characteristics (i.e., different symptoms or varying stages of severity) among patients with ASD, and the non-explainability of the decision process. To cover these limitations, we propose a novel explainability-guided region of interest (ROI) selection (EAG-RS) framework that identifies non-linear high-order functional associations among brain regions by leveraging an explainable artificial intelligence technique and selects class-discriminative regions for brain disease identification. The proposed framework includes three steps: (i) inter-regional relation learning to estimate non-linear relations through random seed-based network masking, (ii) explainable connection-wise relevance score estimation to explore high-order relations between functional connections, and (iii) non-linear high-order FC-based diagnosis-informative ROI selection and classifier learning to identify ASD. We validated the effectiveness of our proposed method by conducting experiments using the Autism Brain Imaging Database Exchange (ABIDE) dataset, demonstrating that the proposed method outperforms other comparative methods in terms of various evaluation metrics. Furthermore, we qualitatively analyzed the selected ROIs and identified ASD subtypes linked to previous neuroscientific studies.

ADT2R: Adaptive Decision Transformer for Dynamic Treatment Regimes in Sepsis.

Dynamic treatment regimes (DTRs), which comprise a series of decisions taken to select adequate treatments, have attracted considerable attention in the clinical domain, especially from sepsis researchers. Existing sepsis DTR learning studies are mainly based on offline reinforcement learning (RL) approaches working on electronic healthcare records data. However, a trained policy may choose a treatment different from a human clinician's prescription. Furthermore, most of them do not consider: 1) heterogeneity in sepsis; 2) short-term transitions; and 3) the relationship between a patient's health state and the prescription. We propose a novel framework, an adaptive decision transformer for DTR (ADT 2 R), which recommends an optimal treatment action for each time step depending on the heterogeneity of the sepsis and a patient's evolving health states. Specifically, we devise a trajectory-optimization-based module to be trained with supervision for treatments and adaptively aggregate the multihead self-attentions by deliberating on various inherent time-varying patterns among sepsis patients. Furthermore, we estimate the patient's health state by adopting an actor-critic (AC) algorithm and inform the treatment recommendation by learning about its short-term changes. We validated the effectiveness of the proposed framework on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, an extensive intensive care database, by demonstrating performance comparable to the state-of-the-art methods.

Deep Geometric Learning With Monotonicity Constraints for Alzheimer's Disease Progression.

Alzheimer's disease (AD) is a devastating neurodegenerative condition that precedes progressive and irreversible dementia; thus, predicting its progression over time is vital for clinical diagnosis and treatment. For this, numerous studies have implemented structural magnetic resonance imaging (MRI) to model AD progression, focusing on three integral aspects: 1) temporal variability; 2) incomplete observations; and 3) temporal geometric characteristics. However, many pioneer deep learning-based approaches addressing data variability and sparsity have yet to consider inherent geometrical properties sufficiently. These properties are integral to modeling as they correlate with brain region size, thickness, volume, and shape in AD progression. The ordinary differential equation-based geometric modeling method (ODE-RGRU) has recently emerged as a promising strategy for modeling time-series data by intertwining a recurrent neural network (RNN) and an ODE in Riemannian space. Despite its achievements, ODE-RGRU encounters limitations when extrapolating positive definite symmetric matrices from incomplete samples, leading to feature reverse occurrences that are particularly problematic, especially within the clinical facet. Therefore, this study proposes a novel geometric learning approach that models longitudinal MRI biomarkers and cognitive scores by combining three modules: topological space shift, ODE-RGRU, and trajectory estimation. We have also developed a training algorithm that integrates the manifold mapping with monotonicity constraints to reflect measurement transition irreversibility. We verify our proposed method's efficacy by predicting clinical labels and cognitive scores over time in regular and irregular settings. Furthermore, we thoroughly analyze our proposed framework through an ablation study.