Unsupervised Clustering Approach Research Articles

The identification of genes associated T-cell exhaustion and construction of prognostic signature to predict immunotherapy response in lung adenocarcinoma

T-cell exhaustion (Tex) is considered to be a reason for immunotherapy resistance and poor prognosis in lung adenocarcinoma. Therefore, we used weighted correlation network analysis to identify Tex-related genes in the cancer genome atlas (TCGA). Unsupervised clustering approach based on Tex-related genes divided patients into cluster 1 and cluster 2. Then, we utilized random forest and the least absolute shrinkage and selection operator to identify nine key genes to construct a riskscore. Patients were classified as low or high-risk groups. The multivariate cox analysis showed the riskscore was an independent prognostic factor in TCGA and GSE72094 cohorts. Moreover, patients in cluster 2 with high riskscore had the worst prognosis. The immune response prediction analysis showed the low-risk group had higher immune, stromal, estimate scores, higher immunophenscore (IPS), and lower tumor immune dysfunction and exclusion score which suggested a better response to immune checkpoint inhibitors (ICIs) therapy in the low-risk group. In the meantime, we included two independent immunotherapy cohorts that also confirmed a better response to ICIs treatment in the low-risk group. Besides, we discovered differences in chemotherapy and targeted drug sensitivity between two groups. Finally, a nomogram was built to facilitate clinical decision making.

Identification of cuproptosis-related molecular subtypes and a novel predictive model of COVID-19 based on machine learning.

To explicate the pathogenic mechanisms of cuproptosis, a newly observed copper induced cell death pattern, in Coronavirus disease 2019 (COVID-19). Cuproptosis-related subtypes were distinguished in COVID-19 patients and associations between subtypes and immune microenvironment were probed. Three machine algorithms, including LASSO, random forest, and support vector machine, were employed to identify differentially expressed genes between subtypes, which were subsequently used for constructing cuproptosis-related risk score model in the GSE157103 cohort to predict the occurrence of COVID-19. The predictive values of the cuproptosis-related risk score were verified in the GSE163151 cohort, GSE152418 cohort and GSE171110 cohort. A nomogram was created to facilitate the clinical use of this risk score, and its validity was validated through a calibration plot. Finally, the model genes were validated using lung proteomics data from COVID-19 cases and single-cell data. Patients with COVID-19 had higher significantly cuproptosis level in blood leukocytes compared to patients without COVID-19. Two cuproptosis clusters were identified by unsupervised clustering approach and cuproptosis cluster A characterized by T cell receptor signaling pathway had a better prognosis than cuproptosis cluster B. We constructed a cuproptosis-related risk score, based on PDHA1, PDHB, MTF1 and CDKN2A, and a nomogram was created, which both showed excellent predictive values for COVID-19. And the results of proteomics showed that the expression levels of PDHA1 and PDHB were significantly increased in COVID-19 patient samples. Our study constructed and validated an cuproptosis-associated risk model and the risk score can be used as a powerful biomarker for predicting the existence of SARS-CoV-2 infection.

High‐Dimensional Chemostratigraphy of Pelagic Clay in the Western North Pacific Ocean Revealed via an Unsupervised Clustering Approach

AbstractPelagic clay constitutes massive and apparently uniform lithology that limits the stratigraphic correlation between neighboring sediment core samples. Recent studies on the pelagic clay in the western North Pacific Ocean demonstrated that the bulk chemical composition of sediments constitutes multielemental chemostratigraphy, deducing the correlation between visibly featureless pelagic clay layers across several cores. However, this heuristic approach utilized only a few elements. Therefore, this study employed multivariate statistical techniques, includingk‐means cluster analysis, to analyze the chemical composition data set of 1,646 samples × 41 elements of the western North Pacific pelagic clay. The pelagic clay was classified into 10 clusters systematically aligned from the seafloor to the depth in a specific order, constituting stratigraphic units that reflected the high‐dimensional geochemical features of these 41 elements. This finding strongly supports the statistical robustness of the latent chemostratigraphy in the western North Pacific pelagic clay. Additionally, we performed Sr–Nd–Pb isotope analyses of the detrital silicate fractions of the centroid samples representing each cluster. The multi‐isotopic features of the detrital fraction varied from a mixture of North American and Asian dusts to a predominance of Asian dust superimposed by volcanic inputs. This secular variation in the matrix components is attributable to the northwestward motion of the Pacific Plate and the time‐varying influence of arc volcanism throughout sedimentary history. The proposed integrated approach of multivariate statistical and isotopic analyses effectively extracted the essential information hidden in the pelagic clay, which may postulate a new protocol for paleoceanographic reconstructions targeting the pelagic realm.

Midlife Neuropsychological Profiles and Associated Vascular Risk: The Bogalusa Heart Study.

Individuals with Alzheimer's disease (AD) often present with coexisting vascular pathology that is expressed to different degrees and can lead to clinical heterogeneity. To examine the utility of unsupervised statistical clustering approaches in identifying neuropsychological (NP) test performance subtypes that closely correlate with carotid intima-media thickness (cIMT) in midlife. A hierarchical agglomerative and k-means clustering analysis based on NP scores (standardized for age, sex, and race) was conducted among 1,203 participants (age 48±5.3 years) from the Bogalusa Heart Study. Regression models assessed the association between cIMT ≥50th percentile and NP profiles, and global cognitive score (GCS) tertiles for sensitivity analysis. Three NP profiles were identified: Mixed-low performance [16%, n = 192], scores ≥1 SD below the mean on immediate, delayed free recall, recognition verbal memory, and information processing; Average [59%, n = 704]; and Optimal [26%, n = 307] NP performance. Participants with greater cIMT were more likely to have a Mixed-low profile [OR = 3.10, 95% CI (2.13, 4.53), p < 0.001] compared to Optimal. After adjusting for education and cardiovascular (CV) risks, results remained. The association with GCS tertiles was more attenuated [lowest (34%, n = 407) versus highest (33%, n = 403) tertile: adjusted OR = 1.66, 95% CI (1.07, 2.60), p = 0.024]. As early as midlife, individuals with higher subclinical atherosclerosis were more likely to be in the Mixed-low profile, underscoring the potential malignancy of CV risk as related to NP test performance, suggesting that classification approaches may aid in identifying those at risk for AD/vascular dementia spectrum illness.

Validating a Physics-Based Automatic Classification Scheme for Impact Echo Signals on Data Using a Concrete Slab with Known Defects

Impact echo (IE) is capable of locating subsurface defects in concrete slabs from the vibrational response of the slab to a mechanical impact. For an intact slab (“good” condition), the frequency spectrum of the IE is dominated by a single peak corresponding to the slab’s “thickness resonance frequency,” whereas the presence of subsurface defects (“fair” or “poor” conditions) could manifest in various ways such as multiple distinct peaks at frequencies higher, or lower, than the thickness resonance. In previous research, the authors have proposed a frequency partitioning of the spectrum for IE signal classification. Firstly, the thickness resonance frequency band is identified using a data-driven approach and then the IE signals are represented by their energy distribution in three bands—frequencies less than, within, and greater than the thickness resonance. Following this feature extraction, an unsupervised clustering approach is used to identify the centroids for each signal class—good, fair, and poor—which are further used to classify any test signal into one of the three aforementioned classes. The classification is developed by training on unlabeled IE signals from real bridge deck data (the Federal Highway Administration’s [FHWA’s] InfoBridge dataset) without making use of any labeled data. This study aims to validate the proposed methodology on a labeled dataset of eight reinforced concrete specimens constructed at the FHWA Advanced Sensing Technology Nondestructive Evaluation laboratory having known artificial defects. Our findings indicate that the physics-based feature definition and the method developed on real bridge data are robust and can classify IE signals in the labeled data with moderate accuracy.

Stratification of responses to tDCS intervention in a healthy pediatric population based on resting-state EEG profiles

Transcranial Direct Current Stimulation (tDCS) is a non-invasive neuromodulation technique with a wide variety of clinical and research applications. As increasingly acknowledged, its effectiveness is subject dependent, which may lead to time consuming and cost ineffective treatment development phases. We propose the combination of electroencephalography (EEG) and unsupervised learning for the stratification and prediction of individual responses to tDCS. A randomized, sham-controlled, double-blind crossover study design was conducted within a clinical trial for the development of pediatric treatments based on tDCS. The tDCS stimulation (sham and active) was applied either in the left dorsolateral prefrontal cortex or in the right inferior frontal gyrus. Following the stimulation session, participants performed 3 cognitive tasks to assess the response to the intervention: the Flanker Task, N-Back Task and Continuous Performance Test (CPT). We used data from 56 healthy children and adolescents to implement an unsupervised clustering approach that stratify participants based on their resting-state EEG spectral features before the tDCS intervention. We then applied a correlational analysis to characterize the clusters of EEG profiles in terms of participant’s difference in the behavioral outcome (accuracy and response time) of the cognitive tasks when performed after a tDCS-sham or a tDCS-active session. Better behavioral performance following the active tDCS session compared to the sham tDCS session is considered a positive intervention response, whilst the reverse is considered a negative one. Optimal results in terms of validity measures was obtained for 4 clusters. These results show that specific EEG-based digital phenotypes can be associated to particular responses. While one cluster presents neurotypical EEG activity, the remaining clusters present non-typical EEG characteristics, which seem to be associated with a positive response. Findings suggest that unsupervised machine learning can be successfully used to stratify and eventually predict responses of individuals to a tDCS treatment.

Multimodal Phenomap of Stargardt Disease Integrating Structural, Psychophysical, and Electrophysiologic Measures of Retinal Degeneration

To cluster the diverse phenotypic features of Stargardt disease (STGD) using unsupervised clustering of multimodal retinal structure and function data. Retrospective cross-sectional study. Eyes of subjects with STGD and fundus autofluorescence (FAF), OCT, electroretinography (ERG), and microperimetry (MP) data available within 1year of the baseline evaluation. A total of 46 variables from FAF, OCT, ERG, and MP results were recorded for subjects with STGD as defined per published criteria. Factor analysis of mixed data identified the most informative variables. Unsupervised hierarchical clustering and silhouette analysis identified the optimal number of clusters to classify multimodal phenotypes. Phenotypic clusters of STGD subjects and the corresponding cluster features. We included 52 subjects and 102 eyes with a mean visual acuity (VA) at the time of multimodal testing of 0.69±0.494 logarithm of minimum angle of resolution (20/63 Snellen). We identified 4 clusters of eyes. Compared to the other clusters, cluster 1 (n=16) included younger subjects, VA greater than that of clusters 2 and 3, normal or moderately low total macular volume (TMV), greater preservation of scotopic and photopic ERG responses and fixation stability, less atrophy, and fewer flecks. Cluster 2 (n=49) differed from cluster 1 mainly with less atrophy and relatively stable fixation. Cluster 3 (n=10) included older subjects than clusters 1 and 2 and showed the lowest VA, TMV, ERG responses, and fixation stability, with extensive atrophy. Cluster 4 (n=27) showed better VA, TMV similar to clusters 1 and 2, moderate ERG activity, stable fixation, and moderate-high atrophy and flecks. Reflecting the phenotypic complexity of STGD, an unsupervised clustering approach incorporating phenotypic measures can be used to categorize STGD eyes into distinct clusters. The clusters exhibit differences in structural and functional measures including quantity of flecks, extent of retinal atrophy, visual fixation accuracy, and ERG responses, among other features. If novel pharmacologic, gene, or cell therapy modalities become available in the future, the multimodal phenomap approach may be useful to individualize treatment decisions, and its utility in aiding prognostication requires further evaluation. Proprietary or commercial disclosure may be found after the references.

A new automatic gating algorithm replicates expert manual gating of immune cell subsets

Abstract Machine learning is increasingly used for the analysis of flow cytometric immunophenotyping data. Many analysis pipelines leverage unsupervised approaches such as dimensionality reduction or clustering, which may lead to populations characterized differently from expert definition. Here we show a new, supervised algorithm for population identification that faithfully replicates the expert manual gating strategy. Peripheral blood samples were drawn from 41 different donors, stained with a dry, unitized B cell panel and acquired on two cytometer units. A manual gating strategy was established, and an automatic model trained on a subset of samples (n=31 donors, split into training, validation and test set) from this study. The performance of the automatic model was evaluated on the 10 unused samples. The automatic identification of populations with differences in median abundance (lymphocytes, CD19+ B-cells and CD19+ CD10+ cells) showed a high level of correlation and lower variability compared to manual gating. The supervised approach presented here retains the gating hierarchy, in contrast to the unsupervised clustering performed by FlowSOM, which splits cells into exclusive metaclusters, leading to metacluster assignments significantly different from expert gating. By automating the identification of populations, assay reproducibility can be increased by removing inter-operator variability. We show that a supervised machine learning tool that supports user-defined panels and gating strategies can reproduce expert analysis, reduce variability of flow cytometry data analysis, and can provide better fit-for-purpose compared to an unsupervised clustering approach.

Radiomics-based Unsupervised Clustering of Acute Multiple Sclerosis Lesions (P10-3.015)

<h3>Objective:</h3> To leverage radiomics and machine learning to identify clusters of focal acute MS lesions exhibiting similar spatial and/or textural patterns on conventional cross-sectional (pre- and post-contrast) T1-weighted, T2-weighted, PD-weighted and FLAIR brain MRIs. <h3>Background:</h3> Multiple sclerosis (MS) lesions exhibit substantial heterogeneity in terms of underlying pathology, anatomic location, and longitudinal evolution. Conventional MRI is sensitive to some aspects of lesion heterogeneity. Unsupervised clustering approaches may identify subtypes of acute MS lesions with specific pathologic features and help improve disease characterization and prognostication. <h3>Design/Methods:</h3> Brain MRIs from the ADVANCE trial (1,512 patients with relapsing-remitting MS, NCT00906399) were retrospectively analysed. For each scan, focal acute (gadolinium-enhancing and/or new or substantially enlarging) T2 lesions (N=3058) were identified in the white matter (WM). Each lesion was represented via its center of mass in standard ICBM-152 space and radiomics-based textural properties. Similar lesions were grouped together via k-means clustering, applied separately across the spatial and each sequence-specific textural domain. Cluster count was optimized based on the silhouette score, Davies-Bouldin index and Variance Ratio Criterion. <h3>Results:</h3> Optimal clustering quality resulted in 8 prototypical WM sites of lesion emergence, 3 prototypical textural patterns on each of post-contrast T1-, PD-weighted and FLAIR MRI and 5 patterns on each of pre-contrast T1- and T2-weighted MRI. Statistically significant cross-sectional associations were found between the occurrence of these lesion subtypes and patient age, sex, years since disease onset and EDSS score, via logistic regression analysis (p &lt; 0.05). <h3>Conclusions:</h3> Specific spatial and textural patterns of acute MS lesions were identified using unsupervised clustering. Further work will evaluate the clinical relevance of identified acute MS lesion patterns towards predicting clinical and MRI endpoints of disease progression. The longitudinal dynamics of each lesion pattern will be investigated via measurements of future lesion repair or transition towards chronic active/inactive lesion states. <b>Disclosure:</b> Mr. Caba has received personal compensation for serving as an employee of Therapanacea. Mr. Caba has received personal compensation for serving as an employee of Biogen. Mr. Caba has received personal compensation in the range of $50,000-$99,999 for serving as a Research Engineer with Therapanacea. Mr. Caba has received personal compensation in the range of $100,000-$499,999 for serving as a Scientist II, ML/AI with Biogen. Dr. Gafson has stock in Biogen. Dr. Ioannidou has received personal compensation for serving as an employee of Therapanacea. Xiaotong Jiang has nothing to disclose. Elizabeth Fisher has received personal compensation for serving as an employee of Biogen. Elizabeth Fisher has stock in Biogen. Elizabeth Fisher has received intellectual property interests from a discovery or technology relating to health care. Dr. Arnold has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Biogen. Dr. Arnold has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Celgene. Dr. Arnold has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Frequency Therapeutics. Dr. Arnold has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Merck. Dr. Arnold has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Novartis. Dr. Arnold has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Roche. Dr. Arnold has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Sanofi. Dr. Arnold has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Shionogi. Dr. Arnold has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Xfacto communications. Dr. Arnold has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Eli Lilly. Dr. Arnold has received personal compensation in the range of $500-$4,999 for serving as a Consultant for EMD Serono. Dr. Arnold has stock in NeuroRx. Colm Elliott has received personal compensation for serving as an employee of NeuroRx Research. Nikos Paragios has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for AstraZeneca. Nikos Paragios has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for Ipsen. Nikos Paragios has received personal compensation in the range of $500-$4,999 for serving as an officer or member of the Board of Directors for ArteDrone. Nikos Paragios has received personal compensation in the range of $10,000-$49,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for Elsevier. Nikos Paragios has received intellectual property interests from a discovery or technology relating to health care. Nikos Paragios has received personal compensation in the range of $100,000-$499,999 for serving as a CEO with TheraPanacea. Dr. Belachew has received personal compensation for serving as an employee of Biogen Inc. Dr. Belachew has received stock or an ownership interest from Biogen Inc.

Combination of machine learning-based bulk and single-cell genomics reveals necroptosis-related molecular subtypes and immunological features in autism spectrum disorder.

Necroptosis is a novel form of controlled cell death that contributes to the progression of various illnesses. Nonetheless, the function and significance of necroptosis in autism spectrum disorders (ASD) remain unknown and require further investigation. We utilized single-nucleus RNA sequencing (snRNA-seq) data to assess the expression patterns of necroptosis in children with autism spectrum disorder (ASD) based on 159 necroptosis-related genes. We identified differentially expressed NRGs and used an unsupervised clustering approach to divide ASD children into distinct molecular subgroups. We also evaluated immunological infiltrations and immune checkpoints using the CIBERSORT algorithm. Characteristic NRGs, identified by the LASSO, RF, and SVM-RFE algorithms, were utilized to construct a risk model. Moreover, functional enrichment, immune infiltration, and CMap analysis were further explored. Additionally, external validation was performed using RT-PCR analysis. Both snRNA-seq and bulk transcriptome data demonstrated a greater necroptosis score in ASD children. Among these cell subtypes, excitatory neurons, inhibitory neurons, and endothelials displayed the highest activity of necroptosis. Children with ASD were categorized into two subtypes of necroptosis, and subtype2 exhibited higher immune activity. Four characteristic NRGs (TICAM1, CASP1, CAPN1, and CHMP4A) identified using three machine learning algorithms could predict the onset of ASD. Nomograms, calibration curves, and decision curve analysis (DCA) based on 3-NRG have been shown to have clinical benefit in children with ASD. Furthermore, necroptosis-based riskScore was found to be positively associated with immune activation. Finally, RT-PCR demonstrated differentially expressed of these four NRGs in human peripheral blood samples. A comprehensive identification of necroptosis may shed light on the underlying pathogenic process driving ASD onset. The classification of necroptosis subtypes and construction of a necroptosis-related risk model may yield significant insights for the individualized treatment of children with ASD.

Novel Metabolic Subtypes in Pregnant Women and Risk of Early Childhood Obesity in Offspring

The in utero metabolic milieu is associated with offspring adiposity. Standard definitions of maternal obesity (according to prepregnancy body mass index [BMI]) and gestational diabetes (GDM) may not be adequate to capture subtle yet important differences in the intrauterine environment that could be involved in programming. To identify maternal metabolic subgroups during pregnancy and to examine associations of subgroup classification with adiposity traits in their children. This cohort study included mother-offspring pairs in the Healthy Start prebirth cohort (enrollment: 2010-2014) recruited from University of Colorado Hospital obstetrics clinics in Aurora, Colorado. Follow-up of women and children is ongoing. Data were analyzed from March to December 2022. Metabolic subtypes of pregnant women ascertained by applying k-means clustering on 7 biomarkers and 2 biomarker indices measured at approximately 17 gestational weeks: glucose, insulin, Homeostatic Model Assessment for Insulin Resistance, total cholesterol, high-density lipoprotein cholesterol (HDL-C), triglycerides, free fatty acids (FFA), HDL-C:triglycerides ratio, and tumor necrosis factor α. Offspring birthweight z score and neonatal fat mass percentage (FM%). In childhood at approximately 5 years of age, offspring BMI percentile, FM%, BMI in the 95th percentile or higher, and FM% in the 95th percentile or higher. A total of 1325 pregnant women (mean [SD] age, 27.8 [6.2 years]; 322 [24.3%] Hispanic, 207 non-Hispanic Black [15.6%], and 713 [53.8%] non-Hispanic White), and 727 offspring with anthropometric data measured in childhood (mean [SD] age 4.81 [0.72] years, 48% female) were included. We identified the following 5 maternal metabolic subgroups: reference (438 participants), high HDL-C (355 participants), dyslipidemic-high triglycerides (182 participants), dyslipidemic-high FFA (234 participants), and insulin resistant (IR)-hyperglycemic (116 participants). Compared with the reference subgroup, women in the IR-hyperglycemic and dyslipidemic-high FFA subgroups had offspring with 4.27% (95% CI, 1.94-6.59) and 1.96% (95% CI, 0.45-3.47) greater FM% during childhood, respectively. There was a higher risk of high FM% among offspring of the IR-hyperglycemic (relative risk, 8.7; 95% CI, 2.7-27.8) and dyslipidemic-high FFA (relative risk, 3.4; 95% CI, 1.0-11.3) subgroups; this risk was of greater magnitude compared with prepregnancy obesity alone, GDM alone, or both conditions. In this cohort study, an unsupervised clustering approach revealed distinct metabolic subgroups of pregnant women. These subgroups exhibited differences in risk of offspring adiposity in early childhood. Such approaches have the potential to refine understanding of the in utero metabolic milieu, with utility for capturing variation in sociocultural, anthropometric, and biochemical risk factors for offspring adiposity.

Fish Spoilage Classification Based on Color Distribution Analysis of Eye Images

Fish contains many nutrients beneficial to human health, which makes fish an essential component of a healthy diet. Omega-3 fatty acids, primarily found in fresh fish, can play a critical role in protecting heart and brain health. Freshness is one of the most important quality criteria of the fish to be selected for consumption. It is known that there may be pathogenic bacteria and toxins to human health in fish that are not stored in the right conditions and transferred by wrong logistics methods. One of the widely used approaches for evaluating the freshness of fish is sensory, which would be highly subjective and error-prone. Moreover, sensory analysis is widespread and one of the fastest approaches for evaluating large quantities of fish. At that point, a computer-aided diagnostic system can accelerate the evaluation of the degree of spoilage, reduce the human resources required for this task, and minimize the possibility of spoiled fish consumption. In this study, a fully automated freshness assessment mechanism based on the analysis of digital eye images of fish is proposed. Accordingly, the unsupervised clustering approach was used for feature extraction, and each image was divided into three regions according to their color distribution. The freshness was evaluated according to the intensity difference between these clusters. The results show that the proposed feature extraction approach is highly distinctive for the discrimination of spoilage and can be used to distinguish fresh fish from spoiled fish using machine learning methods without supervision.

Abstract PD16-07: Association of MRI morphologic phenotype from unsupervised learning with breast cancer subtypes and treatment response

Abstract Background Breast cancer is a heterogeneous disease and can be categorized into clinically or biologically meaningful subtypes. Predictive models built by MRI biomarkers performed better when they are optimized by breast cancer subtype than models optimized in the full cohort [1]. Functional tumor volume (FTV) measured from breast MRI has been used to assess tumor response to neoadjuvant therapy longitudinally in the I-SPY 2 TRIAL. Tumors show distinct morphological patterns, or phenotypes, on MRI. Previous studies demonstrated that either qualitative or quantitative measurements characterizing these phenotypes may provide additional information about treatment response [2,3]. In this study, we investigated if MRI morphologic phenotypes defined by unsupervised clustering is associated with breast cancer subtype and pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC). Methods A cohort of 990 patients enrolled in the I-SPY 2 TRIAL were included in this retrospective analysis. Patients were randomized to one of nine experimental drug arms or standard NAC, and pCR was assessed at surgery. DCE-MRI data acquired at pretreatment (T0) and early treatment (T1) were analyzed. Four subtypes of breast cancer were defined by immunohistochemistry (IHC) based on hormone receptor (HR) and HER2 status. Radiomic features were extracted by PyRadiomics [4] using FTV masks from DCE-MRI. MRI morphologic phenotypes were determined based on unsupervised hierarchical clustering approach on extracted radiomic shape features plus FTV using Pearson correlation with agglomerative ward linkage. The associations between the unsupervised clusters of radiomic features and FTV with four IHC subtypes and pCR were evaluated using χ2 test of independence. Cramer’s V [5] were computed to measure the strength of association (higher Cramer’s V means stronger association). P-value &amp;lt; 0.05 was considered statistically significant. Results Three clusters were generated by unsupervised hierarchical clustering in a population of 910 patients included in our analysis (80 patients excluded due to missing pCR or DCE-MRIs). At T0, the unsupervised clusters showed statistically significant but weak association with pCR (Cramer’s V = 0.088, p = 0.029), but the association between the clusters and HR/HER2 subtypes did not reach significance (Cramer’s V = 0.055, p = 0.48). The unsupervised clusters based on T1 shape radiomic features showed statistically significant association with both pCR and HR/HER2 subtypes (p &amp;lt; 0.001 for both) with Cramer’s V of 0.231 and 0.154, respectively. Our results showed stronger association between pCR and cancer subtypes with MRI shape radiomic features at T1 than at T0. Various pCR rates were observed in MRI clusters at T1. They were 56%, 36%, and 23% in Cluster 1, 2, 3, respectively. Table 1 shows pCR rates by HR/HER2 subtype in each cluster. In all sub-cohorts, pCR rate was highest in Cluster 1 and lowest in Cluster 3. In HR+/HER2-, the pCR rate in Cluster 1 was 2-fold of the pCR rates in Clusters 2 and 3-fold of Cluster 3. pCR rate was statistically significantly different depending on the MRI clusters in the sub-cohorts except for the HR/HER2+ sub-cohort: HR+/HER2-, p&amp;lt; 0.001; HR+/HER2+, p=0.021; HR-/HER2+, p=0.083; HR-/HER2-, p&amp;lt; 0.001. Conclusion MRI phenotype generated by unsupervised clustering using radiomic shape features at both pretreatment and early-treatment time points was associated with pCR outcome. Stronger association was observed at early-treatment time point. The association differed by subtype, with the strongest observed in HR+/HER2- and triple negative subtypes. Our results suggest that radiomic shape features derived from DCE-MRI may be helpful for early prediction of tumor response to NAC. Citations 1. npj Breast Cancer 6, (2020). 2. Tomography 6, (2020). 3. Annals of Surgical Oncology 20, 3823–3830 (2013). 4. Cancer Research 77, e104–e107 (2017). 5. Korean Stat Soc 42, 323–328 (2013). Table 1. pCR rate by HR/HER2 subtype in each MRI cluster at T1 Citation Format: Nu N. Le, Natsuko Onishi, David C. Newitt, Jessica E. Gibbs, Lisa J. Wilmes, Efstathios Gennatas, Barbara LeStage, Laura J. Esserman, Nola M. Hylton, Wen Li. Association of MRI morphologic phenotype from unsupervised learning with breast cancer subtypes and treatment response [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr PD16-07.

Sparse tree-based clustering of microbiome data to characterize microbiome heterogeneity in pancreatic cancer.

There is a keen interest in characterizing variation in the microbiome across cancer patients, given increasing evidence of its important role in determining treatment outcomes. Here our goal is to discover subgroups of patients with similar microbiome profiles. We propose a novel unsupervised clustering approach in the Bayesian framework that innovates over existing model-based clustering approaches, such as the Dirichlet multinomial mixture model, in three key respects: we incorporate feature selection, learn the appropriate number of clusters from the data, and integrate information on the tree structure relating the observed features. We compare the performance of our proposed method to existing methods on simulated data designed to mimic real microbiome data. We then illustrate results obtained for our motivating data set, a clinical study aimed at characterizing the tumor microbiome of pancreatic cancer patients.

Unsupervised clustering approach for recognizing residual stress and distortion patterns for different parts for directed energy deposition additive manufacturing

Unsupervised clustering approach for recognizing residual stress and distortion patterns for different parts for directed energy deposition additive manufacturing

A Framework for Automatic Clustering of EHR Messages Using a Spatial Clustering Approach.

Although Health Level Seven (HL 7) message standards (v2, v3, Clinical Document Architecture (CDA)) have been commonly adopted, there are still issues associated with them, especially the semantic interoperability issues and lack of support for smart devices (e.g., smartphones, fitness trackers, and smartwatches), etc. In addition, healthcare organizations in many countries are still using proprietary electronic health record (EHR) message formats, making it challenging to convert to other data formats-particularly the latest HL7 Fast Health Interoperability Resources (FHIR) data standard. The FHIR is based on modern web technologies such as HTTP, XML, and JSON and would be capable of overcoming the shortcomings of the previous standards and supporting modern smart devices. Therefore, the FHIR standard could help the healthcare industry to avail the latest technologies benefits and improve data interoperability. The data representation and mapping from the legacy data standards (i.e., HL7 v2 and EHR) to the FHIR is necessary for the healthcare sector. However, direct data mapping or conversion from the traditional data standards to the FHIR data standard is challenging because of the nature and formats of the data. Therefore, in this article, we propose a framework that aims to convert proprietary EHR messages into the HL7 v2 format and apply an unsupervised clustering approach using the DBSCAN (density-based spatial clustering of applications with noise) algorithm to automatically group a variety of these HL7 v2 messages regardless of their semantic origins. The proposed framework's implementation lays the groundwork to provide a generic mapping model with multi-point and multi-format data conversion input into the FHIR. Our experimental results show the proposed framework's ability to automatically cluster various HL7 v2 message formats and provide analytic insight behind them.

Distinct Subtypes of Hepatorenal Syndrome and Associated Outcomes as Identified by Machine Learning Consensus Clustering

The utilization of multi-dimensional patient data to subtype hepatorenal syndrome (HRS) can individualize patient care. Machine learning (ML) consensus clustering may identify HRS subgroups with unique clinical profiles. In this study, we aim to identify clinically meaningful clusters of hospitalized patients for HRS using an unsupervised ML clustering approach. Consensus clustering analysis was performed based on patient characteristics in 5564 patients primarily admitted for HRS in the National Inpatient Sample from 2003-2014 to identify clinically distinct HRS subgroups. We applied standardized mean difference to evaluate key subgroup features, and compared in-hospital mortality between assigned clusters. The algorithm revealed four best distinct HRS subgroups based on patient characteristics. Cluster 1 patients (n = 1617) were older, and more likely to have non-alcoholic fatty liver disease, cardiovascular comorbidities, hypertension, and diabetes. Cluster 2 patients (n = 1577) were younger and more likely to have hepatitis C, and less likely to have acute liver failure. Cluster 3 patients (n = 642) were younger, and more likely to have non-elective admission, acetaminophen overdose, acute liver failure, to develop in-hospital medical complications and organ system failure, and to require supporting therapies, including renal replacement therapy, and mechanical ventilation. Cluster 4 patients (n = 1728) were younger, and more likely to have alcoholic cirrhosis and to smoke. Thirty-three percent of patients died in hospital. In-hospital mortality was higher in cluster 1 (OR 1.53; 95% CI 1.31-1.79) and cluster 3 (OR 7.03; 95% CI 5.73-8.62), compared to cluster 2, while cluster 4 had comparable in-hospital mortality (OR 1.13; 95% CI 0.97-1.32). Consensus clustering analysis provides the pattern of clinical characteristics and clinically distinct HRS phenotypes with different outcomes.

Hybrid Unsupervised Cluster-wise Regression Approach for Representing the Flamelet Tables

A novel hybrid unsupervised cluster-wise regression approach is developed to represent the flamelet tables and speed up the computations in turbulent combustion simulations. The proposed machine learning method utilizes a cluster-wise regression technique where specialized deep neural networks are trained on different parts of the input space. A new recursive unsupervised clustering (RUC) approach is proposed that leads to a lower root-mean-square error by over 30% and improves the individual cluster’s mean absolute error by over 20%. The RUC approach enables identifying different combustion manifolds within the input space. The regression models unique to these identified manifolds accurately capture the thermo-chemical scalars for the given input data set. To balance the tradeoffs between the accuracy of flamelet table predictions and the complexities of the RUC algorithm, a hybrid model is introduced that switches between a single neural network (SNN) which is a single regression model, and the SUC RUC approaches. The hybrid unsupervised cluster-wise-regression model benefits from the lower computational costs of SNN for parts of the input space where the SNN prediction error is low and switches to the unsupervised clustering models, that is, standard (SUC) and recursive (RUC) in areas where the SNN performs poorly. The hybrid model is trained on four-dimensional steady flamelet tables and used to model methane combustion by adopting the Sandia Flame D configuration. The hybrid clustering method more accurately captures the experimental measurements of temperature, carbon monoxide (CO), and hydroxyl radical (OH) mass fraction compared to the SNN model. A new hybrid model offers significant improvements in accuracy as compared to the SNN model along with reduction of computational storage by 2 orders of magnitude compared to the original flamelet approach and reduces the total computational time in 3D reacting flow simulations.

Clustering of Relevant Documents Based on Findability Effort in Information Retrieval

A user expresses their information need in the form of a query on an information retrieval (IR) system that retrieves a set of articles related to the query. The performance of the retrieval system is measured based on the retrieved content to the query, judged by expert topic assessors who are trained to find this relevant information. However, real users do not always succeed in finding relevant information in the retrieved list due to the amount of time and effort needed. This paper aims 1) to utilize the findability features to determine the amount of effort needed to find information from relevant documents using the machine learning approach and 2) to demonstrate changes in IR systems' performance when the effort is included in the evaluation. This study uses a natural language processing technique and unsupervised clustering approach to group documents by the amount of effort needed. The results show that relevant documents can be clustered using the k-means clustering approach, and the retrieval system performance varies by 23%, on average.

Utilizing Ubiquitination Patterns to Predict Prostate Cancer Prognosis and Devise a Therapeutic Response.

Ubiquitination, a post-translational modification, is crucial for cancer regulation. However, the predictive significance of ubiquitination-related genes (URGs) for prostate adenocarcinoma (PRAD) remains unclear. The objectives of the study were to investigate the role of URGs in PRAD and their potential impact on patient prognosis. This study acquired data for more than 800 patients with PRAD from public databases. The unique ubiquitination-related patterns of PRAD were detected by unsupervised clustering approach. URGs relevant to the prognosis of patients with PRAD and a ubiquitination-related prognostic index (URPI) were identified and generated using the log-rank test, univariate and multivariate Cox proportional hazards regression, least absolute shrinkage and selection operator (LASSO) Cox regression, and bootstrap strategy. Four ubiquitination-related subpopulations were then defined, and 39 ubiquitination-related differentially expressed genes in prostate cancer and paracancerous samples were screened, with LASSO analysis distinguishing six of them. The URPI was built and verified using the identified URGs that played critical roles in survival stratification. Several potential URPI-targeting drugs were also analyzed. Subsequently, the URPI was combined with clinical characteristics, which provided a more accurate estimate of PRAD survival and was a superior choice for PRAD prognostic forecasts. This investigation has thus established and verified a URPI, which may provide unique insights to improve survival estimations for patients with PRAD.