Phenogrouping heart failure with preserved or mildly reduced ejection fraction using electronic health record data.

BACKGROUND: Heart failure (HF) with preserved or mildly reduced ejection fraction includes a heterogenous group of patients. Reclassification into distinct phenogroups to enable targeted interventions is a priority. This study aimed to identify distinct phenogroups, and compare phenogroup characteristics and outcomes, from electronic health record data. METHODS: 2,187 patients admitted to five UK hospitals with a diagnosis of HF and a left ventricular ejection fraction ≥ 40% were identified from the NIHR Health Informatics Collaborative database. Partition-based, model-based, and density-based machine learning clustering techniques were applied. Cox Proportional Hazards and Fine-Gray competing risks models were used to compare outcomes (all-cause mortality and hospitalisation for HF) across phenogroups. RESULTS: Three phenogroups were identified: (1) Younger, predominantly female patients with high prevalence of cardiometabolic and coronary disease; (2) More frail patients, with higher rates of lung disease and atrial fibrillation; (3) Patients characterised by systemic inflammation and high rates of diabetes and renal dysfunction. Survival profiles were distinct, with an increasing risk of all-cause mortality from phenogroups 1 to 3 (p < 0.001). Phenogroup membership significantly improved survival prediction compared to conventional factors. Phenogroups were not predictive of hospitalisation for HF. CONCLUSIONS: Applying unsupervised machine learning to routinely collected electronic health record data identified phenogroups with distinct clinical characteristics and unique survival profiles.

Arrhythmic Mitral Valve Prolapse Phenotype: An Unsupervised Machine Learning Analysis Using a Multicenter Cardiac MRI Registry.

Purpose To use unsupervised machine learning to identify phenotypic clusters with increased risk of arrhythmic mitral valve prolapse (MVP). Materials and Methods This retrospective study included patients with MVP without hemodynamically significant mitral regurgitation or left ventricular (LV) dysfunction undergoing late gadolinium enhancement (LGE) cardiac MRI between October 2007 and June 2020 in 15 European tertiary centers. The study end point was a composite of sustained ventricular tachycardia, (aborted) sudden cardiac death, or unexplained syncope. Unsupervised data-driven hierarchical k-mean algorithm was utilized to identify phenotypic clusters. The association between clusters and the study end point was assessed by Cox proportional hazards model. Results A total of 474 patients (mean age, 47 years ± 16 [SD]; 244 female, 230 male) with two phenotypic clusters were identified. Patients in cluster 2 (199 of 474, 42%) had more severe mitral valve degeneration (ie, bileaflet MVP and leaflet displacement), left and right heart chamber remodeling, and myocardial fibrosis as assessed with LGE cardiac MRI than those in cluster 1. Demographic and clinical features (ie, symptoms, arrhythmias at Holter monitoring) had negligible contribution in differentiating the two clusters. Compared with cluster 1, the risk of developing the study end point over a median follow-up of 39 months was significantly higher in cluster 2 patients (hazard ratio: 3.79 [95% CI: 1.19, 12.12], P = .02) after adjustment for LGE extent. Conclusion Among patients with MVP without significant mitral regurgitation or LV dysfunction, unsupervised machine learning enabled the identification of two phenotypic clusters with distinct arrhythmic outcomes based primarily on cardiac MRI features. These results encourage the use of in-depth imaging-based phenotyping for implementing arrhythmic risk prediction in MVP. Keywords: MR Imaging, Cardiac, Cardiac MRI, Mitral Valve Prolapse, Cluster Analysis, Ventricular Arrhythmia, Sudden Cardiac Death, Unsupervised Machine Learning Supplemental material is available for this article. © RSNA, 2024.

Construction of prediction models for novel subtypes in patients with arteriosclerosis obliterans undergoing endovascular therapy: an unsupervised machine learning study.

BACKGROUND: Arteriosclerosis obliterans (ASO) is a chronic arterial disease that can lead to critical limb ischemia. Endovascular therapy is increasingly used for limb salvage in ASO patients, but the outcomes vary. The development of prediction models using unsupervised machine learning may lead to the identification of novel subtypes to guide patient prognosis and treatment. METHODS: This retrospective study analyzed clinical data from 448 patients with ASOs who underwent endovascular therapy. Unsupervised machine learning algorithms were employed to identify subgroups. To validate the precision of the clustering outcomes, an analysis of the postoperative results of the clusters was conducted. A prediction model was constructed using binary logistic regression. RESULTS: Two distinct subgroups were identified by unsupervised machine learning and characterized by differing patterns of clinical features. Patients in Cluster 2 had significantly worse conditions and prognoses than those in Cluster 1. For the novel ASO subtypes, a nomogram was developed using six predictive factors, namely, platelet count, ankle brachial index, Rutherford category, operation method, hypertension, and diabetes status. The nomogram achieved excellent discrimination for predicting membership in the two identified clusters, with an area under the curve of 0.96 and 0.95 in training cohort and internal test cohort. CONCLUSION: This study demonstrated that unsupervised machine learning can reveal novel phenotypic subgroups of patients with varying prognostic risk who underwent endovascular therapy. The prediction model developed could support clinical decision-making and risk counseling for this complex patient population. Further external validation is warranted to assess the generalizability of the findings.

Unsupervised model for structure segmentation applied to brain computed tomography.

This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for real-world datasets, this approach applies a spatial continuity scoring function tailored to the desired number of structures. The primary objective is to assist medical experts in diagnosis by identifying regions with specific abnormalities. Results indicate a simplified and accessible solution, reducing computational effort, training time, and financial costs. Moreover, the method presents potential for expediting the interpretation of abnormal scans, thereby impacting clinical practice. This proposed approach might serve as a practical tool for segmenting brain computed tomography scans, and make a significant contribution to the analysis of medical images in both research and clinical settings.

Improvement of gram staining effect by ethanol pretreatment and quantization of staining image by unsupervised machine learning.

In this study, we propose an Ethanol Pretreatment Gram staining method that significantly enhances the color contrast of the stain, thereby improving the accuracy of judgement, and demonstrated the effectiveness of the modification by eliminating unaided-eye observational errors with unsupervised machine learning image analysis. By comparing the traditional Gram staining method with the improved method on various bacterial samples, results showed that the improved method offers distinct color contrast. Using multimodal assessment strategies, including unaided-eye observation, manual image segmentation, and advanced unsupervised machine learning automatic image segmentation, the practicality of ethanol pretreatment on Gram staining was comprehensively validated. In our quantitative analysis, the application of the CIEDE2000, and CMC color difference standards confirmed the significant effect of the method in enhancing the discrimination of Gram staining.This study not only improved the efficacy of Gram staining, but also provided a more accurate and standardized strategy for analyzing Gram staining results, which might provide an useful analytical tool in microbiological diagnostics.

DREAMER: a computational framework to evaluate readiness of datasets for machine learning.

BACKGROUND: Machine learning (ML) has emerged as the predominant computational paradigm for analyzing large-scale datasets across diverse domains. The assessment of dataset quality stands as a pivotal precursor to the successful deployment of ML models. In this study, we introduce DREAMER (Data REAdiness for MachinE learning Research), an algorithmic framework leveraging supervised and unsupervised machine learning techniques to autonomously evaluate the suitability of tabular datasets for ML model development. DREAMER is openly accessible as a tool on GitHub and Docker, facilitating its adoption and further refinement within the research community.. RESULTS: The proposed model in this study was applied to three distinct tabular datasets, resulting in notable enhancements in their quality with respect to readiness for ML tasks, as assessed through established data quality metrics. Our findings demonstrate the efficacy of the framework in substantially augmenting the original dataset quality, achieved through the elimination of extraneous features and rows. This refinement yielded improved accuracy across both supervised and unsupervised learning methodologies. CONCLUSION: Our software presents an automated framework for data readiness, aimed at enhancing the integrity of raw datasets to facilitate robust utilization within ML pipelines. Through our proposed framework, we streamline the original dataset, resulting in enhanced accuracy and efficiency within the associated ML algorithms.

TULIP: A transformer-based unsupervised language model for interacting peptides and T cell receptors that generalizes to unseen epitopes.

The accurate prediction of binding between T cell receptors (TCR) and their cognate epitopes is key to understanding the adaptive immune response and developing immunotherapies. Current methods face two significant limitations: the shortage of comprehensive high-quality data and the bias introduced by the selection of the negative training data commonly used in the supervised learning approaches. We propose a method, Transformer-based Unsupervised Language model for Interacting Peptides and T cell receptors (TULIP), that addresses both limitations by leveraging incomplete data and unsupervised learning and using the transformer architecture of language models. Our model is flexible and integrates all possible data sources, regardless of their quality or completeness. We demonstrate the existence of a bias introduced by the sampling procedure used in previous supervised approaches, emphasizing the need for an unsupervised approach. TULIP recognizes the specific TCRs binding an epitope, performing well on unseen epitopes. Our model outperforms state-of-the-art models and offers a promising direction for the development of more accurate TCR epitope recognition models.

Unsupervised Machine Learning in Countermovement Jump and Isometric Mid-Thigh Pull Performance Produces Distinct Combat and Physical Fitness Clusters in Male and Female U.S. Marine Corps Recruits.

INTRODUCTION: Several challenges face the U.S. Marine Corps (USMC) and other services in their efforts to design recruit training to augment warfighter mobility and resilience in both male and female recruits as part of an integrated model. Strength and power underpin many of the physical competencies required to meet the occupational demands one might face in military. As the military considers adopting force plate technology to assess indices of strength and power, an opportunity presents itself for the use of machine learning on large datasets to deduce the relevance of variables related to performance and injury risk. The primary aim of this study was to determine whether cluster analysis on baseline strength and power data derived from countermovement jump (CMJ) and isometric mid-thigh pull (IMTP) adequately partitions men and women entering recruit training into distinct performance clusters. The secondary aim of this study is then to assess the between-cluster frequencies of musculoskeletal injury (MSKI). MATERIALS AND METHODS: Five hundred and sixty-five males (n = 386) and females (n = 179) at the Marine Corps Recruit Depots located at Parris Island and San Diego were enrolled in the study. Recruits performed CMJ and IMTP tests at the onset of training. Injury data were collected via medical chart review. Combat fitness test (CFT) and physical fitness test (PFT) results were provided to the study team by the USMC. A k-means cluster analysis was performed on CMJ relative peak power, IMTP relative peak force, and dynamic strength index. Independent sample t-tests and Cohen's d effect sizes assessed between-cluster differences in CFT and PFT performance. Differences in cumulative incidence of lower extremity %MSKIs were analyzed using Fisher's exact test. Relative risk and 95% confidence intervals (CIs) were also calculated. RESULTS: The overall effects of cluster designation on CMJ and IMTP outcomes ranged from moderate (relative peak power: d = -0.68, 95% CI, -0.85 to -0.51) to large (relative peak force: d = -1.69, 95% CI, -1.88 to -1.49; dynamic strength index: d = 1.20, 95% CI, 1.02-1.38), indicating acceptable k-means cluster partitioning. Independent sample t-tests revealed that both men and women in cluster 2 (C2) significantly outperformed those in cluster 1 (C1) in all events of the CFT and PFT (P < .05). The overall and within-gender effect of cluster designation on both CFT and PFT performance ranged from small (d > 0.2) to moderate (d > 0.5). Men in C2, the high-performing cluster, demonstrated a significantly lower incidence of ankle MSKI (P = .04, RR = 0.2, 95% CI, 0.1-1.0). No other between-cluster differences in MSKI were statistically significant. CONCLUSIONS: Our results indicate that strength and power metrics derived from force plate tests effectively partition USMC male and female recruits into distinct performance clusters with relevance to tactical and physical fitness using k-means clustering. These data support the potential for expanded use of force plates in assessing readiness in a cohort of men and women entering USMC recruit training. The ability to pre-emptively identify high and low performers in the CFT and PFT can aid in leadership developing frameworks for tailoring training to enhance combat and physical fitness with benchmark values of strength and power.

Identification of sleep phenotypes in COPD using machine learning-based cluster analysis.

BACKGROUND: Disturbed sleep in patients with COPD impact quality of life and predict adverse outcomes. RESEARCH QUESTION: To identify distinct phenotypic clusters of patients with COPD using objective sleep parameters and evaluate the associations between clusters and all-cause mortality to inform risk stratification. STUDY DESIGN AND METHODS: A longitudinal observational cohort study using nationwide Veterans Health Administration data of patients with COPD investigated for sleep disorders. Sleep parameters were extracted from polysomnography physician interpretation using a validated natural language processing algorithm. We performed cluster analysis using an unsupervised machine learning algorithm (K-means) and examined the association between clusters and mortality using Cox regression analysis, adjusted for potential confounders, and visualized with Kaplan-Meier estimates. RESULTS: Among 9992 patients with COPD and a clinically indicated baseline polysomnogram, we identified five distinct clusters based on age, comorbidity burden and sleep parameters. Overall mortality increased from 9.4 % to 42 % and short-term mortality (<5.3 years) ranged from 3.4 % to 24.3 % in Cluster 1 to 5. In Cluster 1 younger age, in 5 high comorbidity burden and in the other three clusters, total sleep time and sleep efficiency had significant associations with mortality. INTERPRETATION: We identified five distinct clinical clusters and highlighted the significant association between total sleep time and sleep efficiency on mortality. The identified clusters highlight the importance of objective sleep parameters in determining mortality risk and phenotypic characterization in this population.

Combining EEG Features and Convolutional Autoencoder for Neonatal Seizure Detection.

Neonatal epilepsy is a common emergency phenomenon in neonatal intensive care units (NICUs), which requires timely attention, early identification, and treatment. Traditional detection methods mostly use supervised learning with enormous labeled data. Hence, this study offers a semi-supervised hybrid architecture for detecting seizures, which combines the extracted electroencephalogram (EEG) feature dataset and convolutional autoencoder, called Fd-CAE. First, various features in the time domain and entropy domain are extracted to characterize the EEG signal, which helps distinguish epileptic seizures subsequently. Then, the unlabeled EEG features are fed into the convolutional autoencoder (CAE) for training, which effectively represents EEG features by optimizing the loss between the input and output features. This unsupervised feature learning process can better combine and optimize EEG features from unlabeled data. After that, the pre-trained encoder part of the model is used for further feature learning of labeled data to obtain its low-dimensional feature representation and achieve classification. This model is performed on the neonatal EEG dataset collected at the University of Helsinki Hospital, which has a high discriminative ability to detect seizures, with an accuracy of 92.34%, precision of 93.61%, recall rate of 98.74%, and F1-score of 95.77%, respectively. The results show that unsupervised learning by CAE is beneficial to the characterization of EEG signals, and the proposed Fd-CAE method significantly improves classification performance.

Bioplausible Unsupervised Delay Learning for Extracting Spatiotemporal Features in Spiking Neural Networks.

The plasticity of the conduction delay between neurons plays a fundamental role in learning temporal features that are essential for processing videos, speech, and many high-level functions. However, the exact underlying mechanisms in the brain for this modulation are still under investigation. Devising a rule for precisely adjusting the synaptic delays could eventually help in developing more efficient and powerful brain-inspired computational models. In this article, we propose an unsupervised bioplausible learning rule for adjusting the synaptic delays in spiking neural networks. We also provide the mathematical proofs to show the convergence of our rule in learning spatiotemporal patterns. Furthermore, to show the effectiveness of our learning rule, we conducted several experiments on random dot kinematogram and a subset of DVS128 Gesture data sets. The experimental results indicate the efficiency of applying our proposed delay learning rule in extracting spatiotemporal features in an STDP-based spiking neural network.

MousiPLIER: A Mouse Pathway-Level Information Extractor Model.

High-throughput gene expression profiling measures individual gene expression across conditions. However, genes are regulated in complex networks, not as individual entities, limiting the interpretability of gene expression data. Machine learning models that incorporate prior biological knowledge are a powerful tool to extract meaningful biology from gene expression data. Pathway-level information extractor (PLIER) is an unsupervised machine learning method that defines biological pathways by leveraging the vast amount of published transcriptomic data. PLIER converts gene expression data into known pathway gene sets, termed latent variables (LVs), to substantially reduce data dimensionality and improve interpretability. In the current study, we trained the first mouse PLIER model on 190,111 mouse brain RNA-sequencing samples, the greatest amount of training data ever used by PLIER. We then validated the mousiPLIER approach in a study of microglia and astrocyte gene expression across mouse brain aging. mousiPLIER identified biological pathways that are significantly associated with aging, including one latent variable (LV41) corresponding to striatal signal. To gain further insight into the genes contained in LV41, we performed k-means clustering on the training data to identify studies that respond strongly to LV41. We found that the variable was relevant to striatum and aging across the scientific literature. Finally, we built a Web server (http://mousiplier.greenelab.com/) for users to easily explore the learned latent variables. Taken together, this study defines mousiPLIER as a method to uncover meaningful biological processes in mouse brain transcriptomic studies.

Active Dynamic Weighting for multi-domain adaptation.

Multi-source unsupervised domain adaptation aims to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Existing methods either seek a mixture of distributions across various domains or combine multiple single-source models for weighted fusion in the decision process, with little insight into the distributional discrepancy between different source domains and the target domain. Considering the discrepancies in global and local feature distributions between different domains and the complexity of obtaining category boundaries across domains, this paper proposes a novel Active Dynamic Weighting (ADW) for multi-source domain adaptation. Specifically, to effectively utilize the locally advantageous features in the source domains, ADW designs a multi-source dynamic adjustment mechanism during the training process to dynamically control the degree of feature alignment between each source and target domain in the training batch. In addition, to ensure the cross-domain categories can be distinguished, ADW devises a dynamic boundary loss to guide the model to focus on the hard samples near the decision boundary, which enhances the clarity of the decision boundary and improves the model's classification ability. Meanwhile, ADW applies active learning to multi-source unsupervised domain adaptation for the first time, guided by dynamic boundary loss, proposes an efficient importance sampling strategy to select target domain hard samples to annotate at a minimal annotation budget, integrates it into the training process, and further refines the domain alignment at the category level. Experiments on various benchmark datasets consistently demonstrate the superiority of our method.

Structure enhanced prototypical alignment for unsupervised cross-domain node classification.

Graph Neural Networks (GNNs) have demonstrated remarkable success in graph node classification task. However, their performance heavily relies on the availability of high-quality labeled data, which can be time-consuming and labor-intensive to acquire for graph-structured data. Therefore, the task of transferring knowledge from a label-rich graph (source domain) to a completely unlabeled graph (target domain) becomes crucial. In this paper, we propose a novel unsupervised graph domain adaptation framework called Structure Enhanced Prototypical Alignment (SEPA), which aims to learn domain-invariant representations on non-IID (non-independent and identically distributed) data. Specifically, SEPA captures class-wise semantics by constructing a prototype-based graph and introduces an explicit domain discrepancy metric to align the source and target domains. The proposed SEPA framework is optimized in an end-to-end manner, which could be incorporated into various GNN architectures. Experimental results on several real-world datasets demonstrate that our proposed framework outperforms recent state-of-the-art baselines with different gains.

Unsupervised domain adaptive segmentation algorithm based on two-level category alignment.

To enhance the model's generalization ability in unsupervised domain adaptive segmentation tasks, most approaches have primarily focused on pixel-level local features, but neglected the clue in category information. This limitation results in the segmentation network only learning global inter-domain invariant features but ignoring the category-specific inter-domain invariant features, which degenerates the segmentation performance. To address this issue, we present an Unsupervised Domain Adaptive algorithm based on two-level Category Alignment in two different spaces for semantic segmentation tasks, denoted as UDAca+. The first level is image-level category alignment based on class activation map (CAM), and the second one is pixel-level category alignment based on pseudo label. By utilizing category information, UDAca+ can effectively capture domain-invariant yet category-discriminative feature representations to improve segmentation accuracy. In addition, an adversarial learning-based strategy in mixed domain is designed to train the proposed network. Moreover, a confidence calculation method is introduced to mitigate the misleading issues of negative transfer and over-alignment caused by the noise in image-level pseudo labels. UDAca+ achieves the state-of-the-art (SOTA) performance on two synthetic-to-real adaptative tasks, and verifies its effectiveness for image segmentation.

Unsupervised mutual transformer learning for multi-gigapixel Whole Slide Image classification.

The classification of gigapixel Whole Slide Images (WSIs) is an important task in the emerging area of computational pathology. There has been a surge of interest in deep learning models for WSI classification with clinical applications such as cancer detection or prediction of cellular mutations. Most supervised methods require expensive and labor-intensive manual annotations by expert pathologists. Weakly supervised Multiple Instance Learning (MIL) methods have recently demonstrated excellent performance; however, they still require large-scale slide-level labeled training datasets that require a careful inspection of each slide by an expert pathologist. In this work, we propose a fully unsupervised WSI classification algorithm based on mutual transformer learning. The instances (i.e., patches) from gigapixel WSIs are transformed into a latent space and then inverse-transformed to the original space. Using the transformation loss, pseudo labels are generated and cleaned using a transformer label cleaner. The proposed transformer-based pseudo-label generator and cleaner modules mutually train each other iteratively in an unsupervised manner. A discriminative learning mechanism is introduced to improve normal versus cancerous instance labeling. In addition to the unsupervised learning, we demonstrate the effectiveness of the proposed framework for weakly supervised learning and cancer subtype classification as downstream analysis. Extensive experiments on four publicly available datasets show better performance of the proposed algorithm compared to the existing state-of-the-art methods.

Workflow for the unsupervised clustering of sleep stages identifies light and deep sleep in electrophysiological recordings in mice.

BACKGROUND: Sleep physiology plays a critical role in brain development and aging. Accurate sleep staging, which categorizes different sleep states, is fundamental for sleep physiology studies. Traditional methods for sleep staging rely on manual, rule-based scoring techniques, which limit their accuracy and adaptability. NEW METHOD: We describe, test and challenge a workflow for unsupervised clustering of sleep states (WUCSS) in rodents, which uses accelerometer and electrophysiological data to classify different sleep states. WUCSS utilizes unsupervised clustering to identify sleep states using six features, extracted from 4-second epochs. RESULTS: We gathered high-quality EEG recordings combined with accelerometer data in diverse transgenic mouse lines (male ApoE3 versus ApoE4 knockin; male CNTNAP2 KO versus wildtype littermates). WUCSS showed high recall, precision, and F1-score against manual scoring on awake, NREM, and REM sleep states. Within NREM, WUCSS consistently identified two additional clusters that qualify as deep and light sleep states. COMPARISON WITH EXISTING METHODS: The ability of WUCSS to discriminate between deep and light sleep enhanced the precision and comprehensiveness of the current mouse sleep physiology studies. This differentiation led to the discovery of an additional sleep phenotype, notably in CNTNAP2 KO mice, showcasing the method's superiority over traditional scoring methods. CONCLUSIONS: WUCSS, with its unsupervised approach and classification of deep and light sleep states, provides an unbiased opportunity for researchers to enhance their understanding of sleep physiology. Its high accuracy, adaptability, and ability to save time and resources make it a valuable tool for improving sleep staging in both clinical and preclinical research.

A comparative study of supervised and unsupervised machine learning algorithms applied to human microbiome.

Background: The human microbiome, consisting of diverse bacte-rial, fungal, protozoan and viral species, exerts a profound influence on various physiological processes and disease susceptibility. However, the complexity of microbiome data has presented significant challenges in the analysis and interpretation of these intricate datasets, leading to the development of specialized software that employs machine learning algorithms for these aims. Methods: In this paper, we analyze raw data taken from 16S rRNA gene sequencing from three studies, including stool samples from healthy control, patients with adenoma, and patients with colorectal cancer. Firstly, we use network-based methods to reduce dimensions of the dataset and consider only the most important features. In addition, we employ supervised machine learning algorithms to make prediction. Results: Results show that graph-based techniques reduces dimen-sion from 255 up to 78 features with modularity score 0.73 based on different centrality measures. On the other hand, projection methods (non-negative matrix factorization and principal component analysis) reduce dimensions to 7 features. Furthermore, we apply supervised machine learning algorithms on the most important features obtained from centrality measures and on the ones obtained from projection methods, founding that the evaluation metrics have approximately the same scores when applying the algorithms on the entire dataset, on 78 feature and on 7 features. Conclusions: This study demonstrates the efficacy of graph-based and projection methods in the interpretation for 16S rRNA gene sequencing data. Supervised machine learning on refined features from both approaches yields comparable predictive performance, emphasizing specific microbial features-bacteroides, prevotella, fusobacterium, lysinibacillus, blautia, sphingomonas, and faecalibacterium-as key in predicting patient conditions from raw data.

A retrospective prognostic evaluation using unsupervised learning in the treatment of COVID-19 patients with hypertension treated with ACEI/ARB drugs.

Introduction: This study aimed to evaluate the prognosis of patients with COVID-19 and hypertension who were treated with angiotensin-converting enzyme inhibitor (ACEI)/angiotensin receptor B (ARB) drugs and to identify key features affecting patient prognosis using an unsupervised learning method. Methods: A large-scale clinical dataset, including patient information, medical history, and laboratory test results, was collected. Two hundred patients with COVID-19 and hypertension were included. After cluster analysis, patients were divided into good and poor prognosis groups. The unsupervised learning method was used to evaluate clinical characteristics and prognosis, and patients were divided into different prognosis groups. The improved wild dog optimization algorithm (IDOA) was used for feature selection and cluster analysis, followed by the IDOA-k-means algorithm. The impact of ACEI/ARB drugs on patient prognosis and key characteristics affecting patient prognosis were also analysed. Results: Key features related to prognosis included baseline information and laboratory test results, while clinical symptoms and imaging results had low predictive power. The top six important features were age, hypertension grade, MuLBSTA, ACEI/ARB, NT-proBNP, and high-sensitivity troponin I. These features were consistent with the results of the unsupervised prediction model. A visualization system was developed based on these key features. Conclusion: Using unsupervised learning and the improved k-means algorithm, this study accurately analysed the prognosis of patients with COVID-19 and hypertension. The use of ACEI/ARB drugs was found to be a protective factor for poor clinical prognosis. Unsupervised learning methods can be used to differentiate patient populations and assess treatment effects. This study identified important features affecting patient prognosis and developed a visualization system with clinical significance for prognosis assessment and treatment decision-making.