Search Results (126)

Diabetic retinopathy (DR) is a common sight-threatening complication of diabetes. Overall, 26% of the 37 million Americans with diabetes suffer from DR, and 5% of people with diabetes suffer from vision-threatening DR. DR is a heterogeneous disease; thus, it is essential to acknowledge this diversity as we advance toward precision medicine. The current classification for DR primarily focuses on the microvascular component of disease progression, which does not fully capture the heterogeneity of disease etiology in different patients. Further, researchers in the field have suggested renewed interest in improving diagnosis and treatment modalities for personalized care in DR management. Moreover, genetic factors, lifestyle, and environmental variation strongly affect the disease outcome. It is important to emphasize that various ocular and peripheral biomarkers, along with imaging techniques, significantly influence the diagnosis of DR. Therefore, in this review, we explore the heterogeneity of DR, genetic variations or polymorphism, lifestyle and environmental factors, and how these factors may affect the development of precision medicine for DR. First, we provide a rationale for the necessity of a multifaceted understanding of disease etiology. Next, we discuss different aspects of DR diagnosis, emphasizing the need for further stratification of patient populations to facilitate personalized treatment. We then discuss different genetics, race, sex, lifestyle, and environmental factors that could help personalize treatments for DR. Lastly, we summarize the available literature to elaborate how artificial intelligence can enhance diagnostics and disease classification and create personalized treatments, ultimately improving disease outcomes in DR patients who do not respond to first-line care. Full article

Background/Objectives: In the United States, Black infants are twice as likely as infants of all other races and ethnicities to die by one year of age. Mediation modeling predicted that preventing low birthweight could alleviate 75% of this disparity. However, the potential confounding and interacting role of preterm birth remains a question. The goal of this study was to determine how birthweight and length of gestation interact in causing racial disparity. Methods: Records from more than 25 million singleton births were retrieved from the United States National Natality Database for the years 2016 to 2022. Two interaction models were evaluated using Bayesian estimation of potential outcomes. The first modeled the interaction between birthweight and length of gestation with both mediators measured as binary (normal/abnormal). The second modeled the interaction using five classifications for both birthweight and length of gestation. Results: Eliminating either abnormal birthweights or abnormal lengths of gestation would reduce racial disparity in infant mortality by approximately 75%. There was no additional reduction of racial disparity by normalizing both. Modeling the combinations of specific categories of birthweight and length of gestation showed Black infants were 2.76 (2.72, 2.79) times more likely to be born with extremely low birthweight and extremely preterm delivery. This single combination explained over 60% of the racial disparity in infant mortality. Conclusions: The current study clarifies how birthweight and preterm birth contribute to racial disparity and illustrates how Bayesian estimation of potential outcomes enables complex mediational investigations. Full article

This article analyzes the dynamics of racial mixing in two regions with diverse colonial administrations in the second half of the eighteenth century: St. Augustine in the province of East Florida (under British and Spanish rule) and New Orleans in the province of Louisiana (under French and Spanish rule). Baptismal records for Black and Brown individuals were used, compiling nominal data from a sample of Afro-descendants born in the latter half of the eighteenth century. Whenever available, information was collected regarding racial classification—for both the baptized individuals and their parents—as well as legal status (enslaved or free) and birth legitimacy. The analysis is conducted from a critical intersectionality framework, highlighting how race, legal status, and gender served as amplifiers of inequality. Among the main results, we must highlight gender and racial classification that, thus, emerge as key differentiators for explaining the legal status and legitimacy of baptized individuals, and they also indicate systemic asymmetries in parental relationships. Full article

Background: The U.S. Medicare Annual Wellness Visit (AWV) offers a structured opportunity for cognitive screening and personalized prevention planning among older adults. Yet, implementation of AWVs, particularly for individuals with cognitive impairment, remains inconsistent across primary care or other diverse care settings. Methods: We conducted a scoping review using the Consolidated Framework for Implementation Research (CFIR) to explore multilevel factors influencing the implementation of the Medicare AWV’s cognitive screening component, with a focus on how these processes support the detection and management of cognitive impairment among older adults. We searched four databases and screened peer-reviewed studies published between 2011 and March 2025. Searches were conducted in Ovid MEDLINE, PubMed, EBSCOhost, and CINAHL databases. The initial search was completed on 3 January 2024 and updated monthly through 30 March 2025. All retrieved citations were imported into EndNote 21, where duplicates were removed. We screened titles and abstracts for relevance using the predefined inclusion criteria. Full-text articles were then reviewed and scored as either relevant (1) or not relevant (0). Discrepancies were resolved through consensus discussions. To assess the methodological quality of the included studies, we used the Joanna Briggs Institute critical appraisal tools appropriate to each study design. These tools evaluate rigor, trustworthiness, relevance, and risk of bias. We extracted the following data from each included study: Author(s), year, title, and journal; Study type and design; Data collection methods and setting; Sample size and population characteristics; Outcome measures; Intervention details (AWV delivery context); and Reported facilitators, barriers, and outcomes related to AWV implementation. The first two authors independently coded and synthesized all relevant data using a table created in Microsoft Excel. The CFIR guided our data analysis, thematizing our findings into facilitators and barriers across its five domains, viz: (1) Intervention Characteristics, (2) Outer Setting, (3) Inner Setting, (4) Characteristics of Individuals, and (5) Implementation Process. Results: Among 19 included studies, most used quantitative designs and secondary data. Our CFIR-based synthesis revealed that AWV implementation is shaped by interdependent factors across five domains. Key facilitators included AWV adaptability, Electronic Health Record (EHR) integration, team-based workflows, policy alignment (e.g., Accountable Care Organization participation), and provider confidence. Barriers included vague Centers for Medicare and Medicaid Services (CMS) guidance, limited reimbursement, staffing shortages, workflow misalignment, and provider discomfort with cognitive screening. Implementation strategies were often poorly defined or inconsistently applied. Conclusions: Effective AWV delivery for older adults with cognitive impairment requires more than sound policy and intervention design; it demands organizational readiness, structured implementation, and engaged providers. Tailored training, leadership support, and integrated infrastructure are essential. These insights are relevant not only for U.S. Medicare but also for global efforts to integrate dementia-sensitive care into primary health systems. Our study has a few limitations that should be acknowledged. First, our scoping review synthesized findings predominantly from quantitative studies, with only two mixed-method studies and no studies using strictly qualitative methodologies. Second, few studies disaggregated findings by race, ethnicity, or geography, reducing our ability to assess equity-related outcomes. Moreover, few studies provided sufficient detail on the specific cognitive screening instruments used or on the scope and delivery of educational materials for patients and caregivers, limiting generalizability and implementation insights. Third, grey literature and non-peer-reviewed sources were not included. Fourth, although CFIR provided a comprehensive analytic structure, some studies did not explicitly fit in with our implementation frameworks, which required subjective mapping of findings to CFIR domains and may have introduced classification bias. Additionally, although our review did not quantitatively stratify findings by year, we observed that studies from more recent years were more likely to emphasize implementation facilitators (e.g., use of templates, workflow integration), whereas earlier studies often highlighted systemic barriers such as time constraints and provider unfamiliarity with AWV components. Finally, while our review focused specifically on AWV implementation in the United States, we recognize the value of comparative analysis with international contexts. This work was supported by a grant from the National Institute on Aging, National Institutes of Health (Grant No. 1R01AG083102-01; PIs: Tzeng, Kuo, & Raji). Full article

Background/Objectives: Thrombotic thrombocytopenic purpura (TTP) is a microangiopathic hemolytic anemia exhibiting 90% mortality without prompt treatment. The aim of this study was to investigate the association of therapeutic plasma exchange (TPE)-treated TTP in end-stage renal disease (ESRD) patients with mortality, demographics, and clinical comorbidities. We queried the United States Renal Data System for ESRD patients starting dialysis between 1 January 2005 and 31 December 2018, using International Classification of Diseases (ICD)-9 and ICD-10 codes for thrombotic microangiopathy, with a TPE procedure code entered within 7 days. Methods: Cox proportional hazards models were used to assess mortality, adjusting for demographic and clinical factors. Results: Among 1,155,136 patients, increased age [adjusted odds ratio (OR) = 0.96, 95% confidence interval (CI): 0.94–0.96]; black race (OR = 0.67, CI: 0.51–0.89); and Hispanic ethnicity (OR = 0.43, CI: 0.28–0.66) were associated with a lower risk of TPE-treated TTP diagnosis, whereas female sex (OR = 1.59, CI: 1.25–2.02) and tobacco use (OR = 2.08, CI: 1.58–2.75) had a higher risk. A claim for TPE-treated TTP carried a lower risk of death (adjusted hazard ratio = 0.024, CI: 0.021–0.028). Female sex, black race, Hispanic ethnicity, and hypothyroidism were also associated with decreased all-cause mortality. Conclusions: These findings suggest that ESRD patients with TPE-treated TTP are significantly protected from mortality compared with ESRD patients without this diagnosis. Full article

Background/Objectives: People are better at recognizing the faces of racial in-group members than out-group members. This own-race bias relies on pattern recognition and memory processes, which rely on hemispheric specialization. We hypothesized that handedness, a proxy for hemispheric specialization, would moderate own-race bias. Specifically, consistently handed individuals perform better on tasks that require the hemispheres to work independently, while inconsistently handed individuals perform better on tasks that require integration. This led to the hypothesis that inconsistently handed individuals would show less own-race bias, driven by an increase in accuracy. Methods: 281 participants completed the study in exchange for course credit. Of those, the sample was isolated to Caucasian (174) and African American individuals (41). Participants were shown two target faces (one Caucasian and one African American), given several distractor tasks, and then asked to identify the target faces during two sequential line-ups, each terminating when participants made an identification judgment. Results: Continuous handedness score and the match between participant race and target face race were entered into a binary logistic regression predicting correct/incorrect identifications. The overall model was statistically significant, Χ² (3, N = 430) = 11.036, p = 0.012, Nagelkerke R² = 0.038, culminating in 76% correct classifications. Analyses of the parameter estimates showed that the racial match, b = 0.53, SE = 0.23, Wald Χ² (1) = 5.217, p = 0.022, OR = 1.703 and the interaction between handedness and the racial match, b = 0.51, SE = 0.23, Wald test = 4.813, p = 0.028, OR = 1.671 significantly contributed to the model. The model indicated that the probability of identification was similar for own- or cross-race targets amongst inconsistently handed individuals. Consistently handed individuals, by contrast, showed an increase in accuracy for the own-race target and a decrease in accuracy for cross-race targets. Conclusions: Results partially supported the hypotheses. Inconsistently handed individuals did show less own-race bias. This finding, however, seemed to be driven by differences in accuracy amongst consistently handed individuals rather than a hypothesized increase in accuracy amongst inconsistently handed individuals. Underlying hemispheric specialization, as measured by proxy with handedness, may impact the own-race bias in facial recognition. Future research is required to investigate the mechanisms, however, as the directional differences were different than hypothesized. Full article

As a core component of machining tools and vehicles, the load-bearing and transmission performance of rolling bearings is directly related to product processing quality and driving safety, highlighting the critical importance of fault detection. To address the nonlinearity, non-stationary modulation, and low signal-to-noise ratio (SNR) observed in bearing vibration signals, we propose a fault feature extraction method based on spectral kurtosis and Hilbert envelope demodulation. First, spectral kurtosis is employed to determine the center frequency and bandwidth of the signal adaptively, and a bandpass filter is constructed to enhance the characteristic frequency components. Subsequently, the envelope spectrum is extracted through the Hilbert transform, allowing for the precise identification of fault characteristic frequencies. In the fault diagnosis stage, a multidimensional feature vector is formed by combining the kurtosis index with the amplitude ratios of inner/outer race characteristic frequencies, and fault pattern classification is accomplished using a Least-Squares Support Vector Machine (LS-SVM). To evaluate the effectiveness of the proposed method, experiments were conducted on the bearing datasets from Case Western Reserve University (CWRU) and the Machine Failure Prevention Technology (MFPT) Society. The experimental results demonstrate that the proposed method surpasses other comparative approaches, achieving identification accuracies of 95% and 100% for the CWRU and MFPT datasets, respectively. Full article

Mississippi has long been one of the most obese states in the U.S., with its obesity rates consistently exceeding the national average. The state’s severe obesity rate is also among the highest in the nation. This study utilized the 2011 to 2021 data from the Mississippi Behavioral Risk Factor Surveillance System (BRFSS) to conduct a comprehensive analysis of obesity and severe obesity trends in Mississippi by sex, age, and race and ethnicity. The data set included a BMI variable calculated by using self-reported height and weight, which the authors categorized into two obesity classification groups—obesity (BMI: 30.00 to 39.99) and severe obesity (BMI: 40.00 or greater)—and demographic characteristics such as sex, age, race and ethnicity. The data were analyzed using SAS 9.4 software to account for the complex design. Weighted prevalence estimates and associated standard errors (SEs) for obesity and severe obesity were calculated. Changes in the prevalence over time were assessed using logistic regression models. The prevalence estimates and SEs were exported to Joinpoint software to calculate the annual percentage change (APC) and associated 95% confidence intervals (CIs) and p-values for the trends. Our analysis of the data revealed a consistent increase in severe obesity, regardless of age, sex, or race. A concerning trend exists where individuals are moving from the obese category to the severely obese category, indicating a worsening trend in overall weight status. This is likely to accelerate the development of chronic disease and, hence, place additional strain on an economically disadvantaged state. Future research should explore the underlying drivers of this shift, including biological, behavioral, and socioeconomic factors, while also evaluating the effectiveness of existing obesity prevention and treatment programs. Full article

Background: Gliomas represent the most prevalent and aggressive primary brain tumors, requiring precise classification to guide treatment strategies and improve patient outcomes. Purpose: This study aimed to develop and evaluate a machine learning-driven approach for glioma classification by identifying the most relevant genetic and clinical biomarkers while demonstrating clinical utility. Methods: A dataset from The Cancer Genome Atlas (TCGA) containing 23 features was analyzed using an integrative approach combining Boruta, Least Absolute Shrinkage and Selection Operator (LASSO), and SHapley Additive exPlanations (SHAP) for feature selection. The refined feature set was used to train four machine learning models: Random Forest, Support Vector Machine, XGBoost, and Logistic Regression. Comprehensive evaluation included class distribution analysis, calibration assessment, and decision curve analysis. Results: The feature selection approach identified 13 key predictors, including IDH1, TP53, ATRX, PTEN, NF1, EGFR, NOTCH1, PIK3R1, MUC16, CIC mutations, along with Age at Diagnosis and race. XGBoost achieved the highest AUC (0.93), while Logistic Regression recorded the highest testing accuracy (88.09%). Class distribution analysis revealed excellent GBM detection (Average Precision 0.840–0.880) with minimal false negatives (5–7 cases). Calibration analysis demonstrated reliable probability estimates (Brier scores 0.103–0.124), and decision curve analysis confirmed substantial clinical utility with net benefit values of 0.36–0.39 across clinically relevant thresholds. Conclusions: The integration of feature selection techniques with machine learning models enhances diagnostic precision, interpretability, and clinical utility in glioma classification, providing a clinically ready framework that bridges computational predictions with evidence-based medical decision-making. Full article

Background: Irritable bowel syndrome (IBS) is a prevalent disorder of gut–brain interaction (DGBI) with a negative impact on quality of life and healthcare expenditure. This study aimed to investigate sex-based differences in a large cohort of IBS patients from a multiracial safety-net hospital. Methods: An electronic query was performed using the International Classification of Diseases, 9th Revision (ICD-9) coding to identify 740 outpatients with IBS between 1 January 2005 and 30 September 2007. Demographic data and ICD-9 coded comorbidities were extracted from electronic records. Data analysis used descriptive statistics and multiple logistic regression analyses. Results: Comorbid anxiety and depression were significantly more prevalent in female patients (A:24%, p = 0.03; D:29%, p = 0.008) compared with male patients. White female IBS patients had a higher risk for anxiety but not depression compared with non-White patients (p = 0.02). Female sex (p = 0.02), obesity (p = 0.007), and age above fifty (p = 0.02) but not race/ethnicity were significant risk factors for depression. IBS with constipation was more prevalent in female patients (p = 0.005) and in Hispanic compared with non-Hispanic patients (p = 0.03). Conclusions: Significant sex-based and racial/ethnic differences were identified related to body mass index (BMI), age, and IBS subtypes in this study. Comorbid mood disorders occurred significantly more frequently in female patients, and risk factors for comorbid depression included female sex, older age, and obesity but not race/ethnicity. Full article

The growing adoption of supercomputers across various scientific disciplines, particularly by researchers without a background in computer science, has intensified the demand for parallel applications. These applications are typically developed using a combination of programming models within languages such as C, C++, and Fortran. However, modern multi-core processors and accelerators necessitate fine-grained control to achieve effective parallelism, complicating the development process. To address this, developers commonly utilize high-level programming models such as Open Multi-Processing (OpenMP), Open Accelerators (OpenACCs), Message Passing Interface (MPI), and Compute Unified Device Architecture (CUDA). These models may be used independently or combined into dual- or tri-model applications to leverage their complementary strengths. However, integrating multiple models introduces subtle and difficult-to-detect runtime errors such as data races, deadlocks, and livelocks that often elude conventional compilers. This complexity is exacerbated in applications that simultaneously incorporate MPI, OpenMP, and CUDA, where the origin of runtime errors, whether from individual models, user logic, or their interactions, becomes ambiguous. Moreover, existing tools are inadequate for detecting such errors in tri-model applications, leaving a critical gap in development support. To address this gap, the present study introduces a static analysis tool designed specifically for tri-model applications combining MPI, OpenMP, and CUDA in C++-based environments. The tool analyzes source code to identify both actual and potential runtime errors prior to execution. Central to this approach is the introduction of error dependency graphs, a novel mechanism for systematically representing and analyzing error correlations in hybrid applications. By offering both error classification and comprehensive static detection, the proposed tool enhances error visibility and reduces manual testing effort. This contributes significantly to the development of more robust parallel applications for high-performance computing (HPC) and future exascale systems. Full article

Background/Objectives: Acute myocardial infarction (AMI) has been a leading cause of mortality in the US. Though AMI mortality has been decreasing in the US, significant disparities have persisted. We aim to evaluate disparities in AMI-related deaths in the US from 1999 to 2022. Methods: Data from the Centers for Disease Control and Prevention Wide-ranging Online Data for Epidemiologic Research (CDC WONDER) multiple causes of death database were used to analyze death certificates from 1999 to 2022 for AMI-related deaths among United States older adults (aged ≥ 65) for overall trend and disparities based on demographic (sex, race/ethnicity, and ten-year age groups) and regional (census regions, rural-urban status, and states) subgroups. Rural and urban status were distinguished using definitions set by the 2013 NCHS Urban-Rural Classification scheme for counties. These data come from the 2010 Census report and are updated from the 2006 NCHS Urban-Rural Classification scheme for counties. The crude mortality rate (CMR) and age-adjusted mortality rates (AAMRs) per 100,000 people were used to calculate annual percentage changes (APCs) and average annual percentage changes (AAPCs) using Joinpoint regression analysis. Results: From 1999 to 2022, there were 3,249,542 deaths due to AMI. Overall, age-adjusted mortality rates (AAMRs) decreased by 62.78% from 563.2 * (95% CI 560.3–565.7) in 1999 to a nadir at 209.6 * (208.3–210.8) in 2019, with an AAPC of −4.96 * (95% CI −5.11 to −4.81). There were a total of 355,441 deaths from AMI from 2020 to 2022; 21,216 (5.97%) of those were from AMI with COVID-19 infection. An increase of 11.4% was observed from an AAMR of 209.6 * (95% CI 208.3–210.8) in 2019 to 233.5 * (95% CI 232.2–234.8) in 2021. From 2021 to 2022, the AAMR of AMI decreased from 233.5 * (95% CI 232.2–234.8) to 209.8 * (95% CI 208.6–211), recovering to the 2019 levels. The AAMR for AMI excluding associated COVID-19 infection was 217.2 at its peak in 2021, which correlates to only a 3.63% increase from 2019. Significant disparities in AMI mortality were observed, with higher mortality rates in men, African Americans, the oldest age group (age ≥ 85), and those living in southern states and rural areas. Conclusions: AMI mortality in the older adult population of the US has significantly decreased from 1999 to 2019, with a brief increase during the pandemic from 2019 to 2021, followed by recovery back to the 2019 level in 2022. The majority of the rise observed during the pandemic was associated with COVID-19 infection. Despite remarkable improvement in mortality, significant disparities have persisted, with men, African Americans, and those living in rural areas and the southern region of the US having disproportionately higher mortality. Full article

Background: Frailty, with a high prevalence of 40–80% in heart failure, may have a significant bearing on outcomes in patients. This study utilizes the Hospital Frailty Risk Score (HFRS), a validated tool derived from the administrative International Classification of Diseases, 10th Revision, Clinical Modifications (ICD-10-CM) codes, in investigating the mortality, morbidity, and healthcare resource utilization among heart failure hospitalizations using the Nationwide Inpatient Sample (NIS). Methods: A retrospective analysis of the 2021 NIS database was assessed to identify adult patients hospitalized with heart failure. These patients were stratified by the HFRS into three groups: low frailty (LF: <5), intermediate frailty (IF: 5–15), and high frailty (HF: >15). The outcomes analyzed included inpatient mortality, length of stay (LOS), hospitalization charges, and complications including cardiogenic shock, cardiac arrest, acute kidney injury, and acute respiratory failure. These outcomes were adjusted for age, race, gender, the Charlson comorbidity score, hospital location, region, and teaching status. Multivariate logistic and linear regression analyses were used to assess the association between frailty and clinical outcomes. STATA/MP 18.0 was used for statistical analysis. Results: Among 1,198,988 heart failure admissions, 47.5% patients were in the LF group, whereas the IF and HF groups had 51.1% and 1.4% patients, respectively. Compared to the LF group, the IF group showed a 4-fold higher (adjusted OR = 4.60, p < 0.01), and the HF group had an 11-fold higher (adjusted OR 10.90, p < 0.01) mortality. Frail patients were more likely to have a longer length of stay (4.24 days, 7.18 days, and 12.1 days in the LF, IF, and HF groups) and higher hospitalization charges (USD 49,081, USD 84,472, and USD 129,516 in the LF, IF, and HF groups). Complications were also noticed to be significantly (p < 0.01) higher with increasing frailty from the LF to HF groups. These included cardiogenic shock (1.65% vs. 4.78% vs. 6.82%), cardiac arrest (0.37% vs. 1.61% vs. 3.16%), acute kidney injury (19.2% vs. 54.9% vs. 74.6%), and acute respiratory failure (29.6% vs. 51.2% vs. 60.3%). Conclusions: This study demonstrates the application of HFRS in a national dataset as a predictor of outcome and resource utilization measures in heart failure admissions. Stratifying patients based on HFRS can help in holistic assessment, aid prognostication, and guide targeted interventions in heart failure. Full article

Background and Objectives: Glaucoma (GL) classification is crucial for early diagnosis and treatment, yet relying solely on stand-alone models or International Classification of Diseases (ICD) codes is insufficient due to limited predictive power and inconsistencies in clinical labeling. This study aims to improve GL classification using stacked weight-based machine learning models. Materials and Methods: We analyzed a subset of 33,636 participants (58% female) with 340,444 visual fields (VFs) from the Mass Eye and Ear (MEE) dataset. Five clinically relevant GL detection models (LoGTS, UKGTS, Kang, HAP2_part1, and Foster) were selected to serve as base models. Two multi-layer perceptron (MLP) models were trained using 52 total deviation (TD) and pattern deviation (PD) values from Humphrey field analyzer (HFA) 24-2 VF tests, along with four clinical variables (age, gender, follow-up time, and race) to extract model weights. These weights were then utilized to train three meta-learners, including logistic regression (LR), extreme gradient boosting (XGB), and MLP, to classify cases as GL or non-GL. Results: The MLP meta-learner achieved the highest performance, with an accuracy of 96.43%, an F-score of 96.01%, and an AUC of 97.96%, while also demonstrating the lowest prediction uncertainty (0.08 ± 0.13). XGB followed with 92.86% accuracy, a 92.31% F-score, and a 96.10% AUC. LR had the lowest performance, with 89.29% accuracy, an 86.96% F-score, and a 94.81% AUC, as well as the highest uncertainty (0.58 ± 0.07). Permutation importance analysis revealed that the superior temporal sector was the most influential VF feature, with importance scores of 0.08 in Kang’s and 0.04 in HAP2_part1 models. Among clinical variables, age was the strongest contributor (score = 0.3). Conclusions: The meta-learner outperformed stand-alone models in GL classification, achieving an accuracy improvement of 8.92% over the best-performing stand-alone model (LoGTS with 87.51%), offering a valuable tool for automated glaucoma detection. Full article

This study uses deep learning techniques to optimize fault diagnosis in rolling element bearings of rotating electrical machines. Leveraging the Case Western Reserve University bearing fault database, the methodology involves transforming one-dimensional vibration signals into two-dimensional scalograms, which are used to train neural networks via transfer learning. By employing SqueezeNet—a pre-trained convolutional neural network—and optimizing hyperparameters, this study significantly reduces the computational resources and time needed for effective fault classification. The analysis evaluates the effectiveness of two wavelet transforms (amor and morse) for feature extraction in correlation with varying learning rates. Results indicate that precise hyperparameter tuning enhances diagnostic accuracy, achieving a classification accuracy of 99.37% using the amor wavelet. Scalograms proved particularly effective in identifying distinct vibration patterns for faults in bearings’ inner and outer races. This research underscores the critical role of advanced signal processing and machine learning in predictive maintenance. The proposed methodology ensures higher reliability and operational efficiency and demonstrates the feasibility of transfer learning in industrial diagnostic applications, particularly for optimizing resource-constrained systems. These findings improve the robustness and precision of machine fault diagnosis systems. Full article