Swiss Med Wkly. 2025 Jan 24;155:3885. doi: 10.57187/s.3885.

ABSTRACT

INTRODUCTION: Blastic plasmacytoid dendritic cell neoplasm (BPDCN) is a very rare disease, with unique diagnostic challenges and often dismal outcome. There are no widely accepted treatment guidelines available. Lymphoma-like regimens with or without autologous or allogenic transplantation were the cornerstone of most therapeutic concepts. A few years ago, the CD123-directed immunoconjugate tagraxofusp emerged as a new valuable treatment option. The goal of our research was to collect available data on BPDCN-patients treated at large centres in Switzerland and worldwide and to draw conclusions regarding the incidence, clinical presentation, prognostic factors and therapeutic strategies.

METHODS: We collected data from BPDCN patients from leading Swiss haemato-oncology centres from 2005 to 2022. Furthermore, we reviewed and analysed the published literature (cohorts and case reports in peer-reviewed journals) from 1997 to 2020 (structured review of the literature).

RESULTS: We identified 115 international publications including 600 patients from all over the world. Most of them had very small sample sizes (only ten papers with more than ten patients) and all but one were retrospective or observational respectively. Most included patients were Europeans (n = 385, 64%) and Asians (n = 120, 20%), followed by Americans (n = 90, 15%) and patients from Australia/New Zealand (n = 3) and Africa (n = 2). BPDCN was more common in men with a predominance of 3:1. The median age (n = 414) at diagnosis was 66.5 years ranging from one month to 103 years. Newly diagnosed women were significantly younger than men (median: 62 vs 67 years, mean: 53.4 vs 59.3 years, p = 0.027) and less often had bone marrow infiltration and affected lymph nodes. Upfront allogenic transplantation as well as ALL regimens performed best, with response to first-line therapy clearly associated with better overall survival. The Swiss cohort contained 26 patients (23 males and 3 females) over 18 years (2005-2022). The median age at diagnosis was 68.5 years (range: 20-83). Ten patients underwent upfront stem cell transplantation (seven allogenic and three autologous), at least trending towards a better overall survival than other therapies. With a follow-up of 8 years, the median overall survival was 1.2 years. Eight patients in this cohort were treated with tagraxofusp, which became available in 2020 and was approved by Swissmedic in 2023.

CONCLUSIONS: Our study confirms that BPDCN is a very rare and difficult-to-treat disease. Underdiagnosis and underreporting in the literature pose further challenges. Symptoms at presentation seem to differ slightly between sexes and reaching a complete remission after first-line treatment remains crucial for a prolonged overall survival. Effective treatment protocols in first line include transplantation regimens (mainly allogenic, potentially also autologous) as well as ALL protocols. In order to understand the significance of tagraxofusp as a bridge to transplant or as a continuous monotherapy in elderly patients, further evaluation with longer follow-up periods is required. In general, analysis of the Swiss patients confirmed the results from the worldwide cohort.

PMID:39877935 | DOI:10.57187/s.3885

Front Pharmacol. 2025 Jan 14;15:1516469. doi: 10.3389/fphar.2024.1516469. eCollection 2024.

ABSTRACT

Pharmacogenomics (PGx) is a powerful tool for clinical optimization of drug efficacy and safety. However, due to many factors affecting drugs in the real world, PGx still accounts for a small proportion of actual clinical application scenarios. Therefore, based on the information software, pharmacists use their professional advantages to integrate PGx into all aspects of pharmaceutical care, which is conducive to promoting the development of personalized medicine. In this paper, the establishment of an information software platform is summarized for the optimization of a personalized medication program based on PGx. Taking colorectal cancers (CRC) as an example, this paper also discusses the role of PGx in different working modes and participation in drug management of CRC patients by pharmacists with the help of information systems. Finally, we summarized the recommendations of different PGx guidelines to provide reference for the follow-up personalized pharmaceutical care.

PMID:39877392 | PMC:PMC11772163 | DOI:10.3389/fphar.2024.1516469

Clin Transplant. 2025 Feb;39(2):e70092. doi: 10.1111/ctr.70092.

ABSTRACT

Since 1987, King Chulalongkorn Memorial Hospital (KCMH) has performed a substantial number of heart transplants as a specific therapy for advanced-stage heart failure. This descriptive study aimed to analyze post-transplant survival in the recent era compared to earlier periods and examine the pharmacogenetics of related immunosuppressants. Data from all recipients who underwent heart transplants from 1987 to 2021 were retrospectively retrieved from the electronic medical record. The genotypes of relevant pharmacogenes were analyzed in recipients who were alive during the enrollment period. Kaplan-Meier analysis revealed improved overall survival rates in the recent era compared to the past. Dilated cardiomyopathy was identified as the most common pretransplant diagnosis, while infection remained the leading cause of mortality. In conclusion, the findings demonstrate significant advancements in the quality of heart transplantation in Thailand. Future studies are warranted to explore the correlation between pharmacogenetic variations identified in this study and subsequent clinical outcomes, with a focus on genetic-guided treatment to optimize patient care.

PMID:39876635 | DOI:10.1111/ctr.70092

Intern Med J. 2025 Jan 29. doi: 10.1111/imj.16641. Online ahead of print.

ABSTRACT

BACKGROUND: Return-to-work (RTW) following lung transplant has been associated with increased quality of life, but little is known regarding the rates of and barriers to this in the Australian population.

AIMS: We aimed to describe, characterise and determine predictors of return to work and social participation in Australian lung transplant recipients. We also sought to explore the relationship between return to work and quality of life.

METHODS: We conducted a cross-sectional questionnaire-based study at the Alfred Hospital, Melbourne between October 2018 and August 2019. The questionnaire evaluated demographics, transplant history, respiratory parameters, employment history and social integration prior to and after lung transplantation.

RESULTS: A total of 172 lung transplant recipients were included for analysis. The population was mostly male (56.5%), median age 61 years (interquartile range (IQR) 49.8-67.0) and median time from transplant 4 years (IQR 2-7). A total of 19.2% of patients were working at time of transplant, with 35.5% working after transplant representing an increase in workforce engagement of 84.8% (P < 0.001). A total of 96% of those who returned to work reported an improvement in quality of life. Median time to RTW after transplant was 180 days (IQR 90-360). Multivariable analysis demonstrated an increased rate of RTW in younger recipients (odds ratio (OR) 0.94, 95% confidence interval (CI) 0.89-0.99, adjusted P = 0.029), at greater length of time after transplant (OR 1.09, 95% CI 0.99-1.19, P = 0.084), among those working at the time of transplant (OR 9.55, 95% CI 2.70-33.75, P < 0.001) and with higher socioeconomic status (OR 1.02, 95% CI 1.01-1.04, P = 0.009). Recipients with cystic fibrosis were more likely to RTW (65.8%) than those with other underlying conditions.

CONCLUSIONS: RTW should be encouraged in lung transplant recipients. Targeted supports and resources aimed at younger recipients may result in greater workforce engagement and overall outcomes after transplant.

PMID:39877944 | DOI:10.1111/imj.16641

Cureus. 2024 Dec 28;16(12):e76529. doi: 10.7759/cureus.76529. eCollection 2024 Dec.

ABSTRACT

BACKGROUND: Children who suffer from long-term illnesses, including asthma, cystic fibrosis, diabetes, or epilepsy, sometimes struggle to manage their ailments, which affects their quality of life and how often they use healthcare services.

OBJECTIVE: This study aimed to explore comprehensive long-term management strategies for children with asthma, cystic fibrosis, diabetes, and epilepsy, with a focus on enhancing quality of life and reducing hospital admissions.

METHODOLOGY: A prospective cohort research was conducted involving 480 children, divided into four groups: 120 children with asthma, 120 children with cystic fibrosis, 120 children with diabetes, and 120 children with epilepsy. Participants were evaluated at baseline and at several follow-ups (3, 6, 12, and 24 months) across a 24-month period. Structured surveys, including questions on treatment adherence and quality of life metrics, as well as checks of medical records to monitor hospital admissions, were used to gather data. To investigate changes in hospital admission rates and quality of life scores over time, statistical analyses were performed, including paired t-tests. Statistical significance was defined as a p-value of less than 0.05.

RESULTS: Quality of life scores improved significantly for all groups, with asthma patients demonstrating the most significant increase of 12.53 ± 3.51 points, rising from a baseline score of 62.54 ± 14.03 to 75.07 ± 10.52 (p < 0.001). Hospital admissions also declined substantially, particularly in the asthma group, which reduced from 4.51 ± 2.07 to 2.06 ± 1.37 (p < 0.001). High adherence rates were observed among patients, with 85 (70.83%) in asthma, 90 (75.00%) in cystic fibrosis, 95 (79.17%) in diabetes, and 92 (76.67%) in epilepsy. Additionally, patient satisfaction scores were notably high, averaging 78.02 ± 10.07 in asthma, 80.03 ± 9.52 in cystic fibrosis, 82.21 ± 8.05 in diabetes, and 79.15 ± 9.03 in epilepsy across the different disease categories.

CONCLUSION: Children with chronic illnesses have a much higher quality of life and fewer hospital admissions when family engagement techniques and technology-driven monitoring are used.

PMID:39877791 | PMC:PMC11772561 | DOI:10.7759/cureus.76529

Open Forum Infect Dis. 2025 Jan 8;12(1):ofaf001. doi: 10.1093/ofid/ofaf001. eCollection 2025 Jan.

ABSTRACT

BACKGROUND: Improved diagnostic testing (DT) of infections may optimize outcomes for solid organ transplant recipients (SOTR), but a comprehensive analysis is lacking.

METHODS: We conducted a systematic literature review across multiple databases, including EMBASE and MEDLINE(R), of studies published between 1 January 2012-11 June 2022, to examine the evidence behind DT in SOTR. Eligibility criteria included the use of conventional diagnostic methods (culture, biomarkers, directed-polymerase chain reaction [PCR]) or advanced molecular diagnostics (broad-range PCR, metagenomics) to diagnose infections in hospitalized SOTR. Bias was assessed using tools such as the Cochrane Handbook and PRISMA 2020.

RESULTS: Of 2362 studies, 72 were eligible and evaluated heterogeneous SOT populations, infections, biospecimens, DT, and outcomes. All studies exhibited bias, mainly in reporting quality. Median study sample size was 102 (range, 11-1307). Culture was the most common DT studied (N = 45 studies, 62.5%), with positive results in a median of 27.7% (range, 0%-88.3%). Biomarkers, PCR, and metagenomics were evaluated in 7, 19, and 3 studies, respectively; only 6 reported sensitivity, specificity, and positive/negative predictive values. Directed-PCR performed well for targeted pathogens, but only 1 study evaluated broad-range PCR. Metagenomics approaches detected numerous organisms but required clinical adjudication, with too few studies (N = 3) to draw conclusions. Turnaround time was shorter for PCR/metagenomics than conventional diagnostic methods (N = 4 studies, 5.6%). Only 6 studies reported the impact of DT on outcomes like antimicrobial use and length of stay.

CONCLUSIONS: We identified considerable evidence gaps in infection-related DT among SOT, particularly molecular DT, highlighting the need for further research.

PMID:39877399 | PMC:PMC11773193 | DOI:10.1093/ofid/ofaf001

Biofilm. 2025 Jan 6;9:100250. doi: 10.1016/j.bioflm.2024.100250. eCollection 2025 Jun.

ABSTRACT

Bacterial biofilms formed by Staphylococcus aureus and Pseudomonas aeruginosa pose significant challenges in treating cystic fibrosis (CF) airway infections due to their resistance to antibiotics. New therapeutic approaches are urgently needed to treat these chronic infections. This study aimed to investigate the antibiofilm potential of various plant extracts, specifically targeting mucoid and small colony variants of P. aeruginosa and S. aureus and strains. Moreover, it aimed to gain insights into the mechanisms of action and the potential phytochemicals responsible for antibiofilm activity. Solid-liquid extractions were performed on seven biomasses using water and ethanol (70 and 96 %) under controlled conditions, resulting in 21 distinct plant extracts. These extracts were evaluated for extraction yield, antioxidant activity, phenolic content, chemical composition by HPLC-TOF-MS, and antibiofilm activity using a 96-well plate assay, followed by crystal violet staining, bacterial adhesion assessment, and brightfield microscopy. Our findings revealed that aqueous extracts exhibited the highest inhibition of biofilm formation, with cinnamon bark and moringa seeds showing strong antibiofilm activity against both bacterial species. Brightfield microscopy confirmed that these extracts effectively inhibited biofilm formation. Chemical analysis identified key bioactive compounds, including moringin, benzaldehyde, coumarin, and quinic acid, which likely contribute to the observed antibiofilm effects. Recognizing that the antibiofilm properties of moringin, a common compound in both moringa seed and cinnamon bark extracts, remain underexplored, we conducted potential target identification via PharmMapper and molecular docking analyses to provide a foundation for future research. Computational analyses indicated that moringin might inhibit aspartate-semialdehyde dehydrogenase in P. aeruginosa and potentially interact with an unknown target in S. aureus. In conclusion, moringa seed and cinnamon bark extracts demonstrated significant potential for developing new therapies targeting biofilm-associated infections in CF. Further studies are needed to validate the computational predictions, identify the bacterial targets, and elucidate the precise mechanisms behind moringin's antibiofilm activity, which is likely the potential key contributor to the observed activity of the moringa and cinnamon bark extracts.

PMID:39877233 | PMC:PMC11772965 | DOI:10.1016/j.bioflm.2024.100250

Chron Respir Dis. 2025 Jan-Dec;22:14799731241249476. doi: 10.1177/14799731241249476.

ABSTRACT

Background: The use of non-invasive ventilation (NIV) in patients with advanced cystic fibrosis (CF) has increased in recent years. Research evidence supports its clinical benefits, but less is known about the patients' experience of its long-term use in a domiciliary setting.Objective: To investigate patients' lived experience of using long-term domiciliary NIV.Methods: Semi-structured, qualitative interviews were conducted with adults with CF using long-term domiciliary NIV for respiratory failure. The data collected were subject to thematic analysis.Results: Nine adults (6 female), 5 of whom were awaiting lung transplantation, with a mean age of 39 years and mean FEV1 per cent predicted of 28%, were recruited. Data analysis revealed 2 themes: gratitude, and determination despite challenges. Patients identified some troubling side effects from NIV but were grateful for its symptomatic relief and were determined to continue using it to improve their quality of life.Conclusions: Participants reported experiences of NIV to be generally positive in terms of symptom relief and quality of life. These findings provide an initial insight into patients' experience of NIV and have the potential to help guide and improve care.

PMID:39876815 | DOI:10.1177/14799731241249476

Health Expect. 2025 Feb;28(1):e70156. doi: 10.1111/hex.70156.

ABSTRACT

BACKGROUND: Lung transplantation improves survival and quality of life in young people with end-stage lung disease. Few studies have investigated the clinical care experiences of young people after lung transplantation.

DESIGN: This qualitative study aimed to explore the experiences of young people who underwent lung transplantation. Semi-structured interviews were conducted with 16 lung transplant recipients (< 25 years at transplant). Interviews were analysed to identify themes and categorize and describe the experience of young lung transplant recipients.

RESULTS: The themes that emerged were (1) Hope and spectre: The transplant dilemma; (2) Information delivery and comprehension; (3) Independence and navigating care; and (4) Continuity and youth-appropriate care. Findings suggest that young people have distinct care needs that consider the many parallel life transitions that occur in addition to transplantation. They value consistent and familiar teams, which nurture autonomy and independence in the context of post-transplant survivorship and highlight the importance of feeling that they can relate to the healthcare process.

CONCLUSION: The results highlight key areas where adolescent lung transplant recipients can be supported by clinicians, enabling the development of youth-friendly services that cater to this group's healthcare and psychosocial needs.

PATIENT OR PUBLIC CONTRIBUTION: Sixteen lung transplant recipients participated in the study by completing a semi-structured interview. Two additional lung transplant recipients who received lung transplants as adolescents and one parent of an adolescent lung transplant recipient participated in a Project Advisory Group (PAG) with six clinicians representing paediatric, adolescent, and adult healthcare experience. They provided advice on research design including the development and revision of the interview guide and recruitment methods. They additionally provided feedback on the preliminary findings and outline of the manuscript. A summary of results was presented to the PAG who in conjunction with the writing group developed a list of recommendations based on the themes identified and the tenets of youth-appropriate care as set out by the World Health Organization. One lung transplant recipient was an author on the manuscript contributing to its writing and review before submission. The clinicians who participated in the PAG did not have direct healthcare relationships with the study participants.

PMID:39876587 | DOI:10.1111/hex.70156

Pediatr Pulmonol. 2025 Jan;60(1):e27498. doi: 10.1002/ppul.27498.

NO ABSTRACT

PMID:39876081 | DOI:10.1002/ppul.27498

J Chem Inf Model. 2025 Jan 29. doi: 10.1021/acs.jcim.4c01893. Online ahead of print.

ABSTRACT

Efficient and accurate drug-target affinity (DTA) prediction can significantly accelerate the drug development process. Recently, deep learning models have been widely applied to DTA prediction and have achieved notable success. However, existing methods often encounter several common issues: first, the data representations lack sufficient information; second, the extracted features are not comprehensive; and third, most methods lack interpretability when modeling drug-target binding. To overcome the above-mentioned problems, we propose an interpretable deep learning model called MutualDTA for predicting DTA. MutualDTA leverages the power of pretrained models to obtain accurate representations of drugs and targets. It also employs well-designed modules to extract hidden features from these representations. Furthermore, the interpretability of MutualDTA is realized by the Mutual-Attention module, which (i) establishes relationships between drugs and proteins from the perspective of intermolecular interactions between drug atoms and protein amino acid residues and (ii) allows MutualDTA to capture the binding sites based on attention scores. The test results on two benchmark data sets show that MutualDTA achieves the best performance compared to the 12 state-of-the-art models. Attention visualization experiments show that MutualDTA can capture partial interaction sites, which not only helps drug developers reduce the search space for binding sites, but also demonstrates the interpretability of MutualDTA. Finally, the trained MutualDTA is applied to screen high-affinity drug screens targeting Alzheimer's disease (AD)-related proteins, and the screened drugs are partially present in the anti-AD drug library. These results demonstrate the reliability of MutualDTA in drug development.

PMID:39878060 | DOI:10.1021/acs.jcim.4c01893

iScience. 2024 Dec 28;28(2):111707. doi: 10.1016/j.isci.2024.111707. eCollection 2025 Feb 21.

ABSTRACT

Neurodevelopmental impairments associated with congenital heart disease (CHD) may arise from perturbations in brain developmental pathways, including the formation of sulcal patterns. While genetic factors contribute to sulcal features, the association of noncoding de novo variants (ncDNVs) with sulcal patterns in people with CHD remains poorly understood. Leveraging deep learning models, we examined the predicted impact of ncDNVs on gene regulatory signals. Predicted impact was compared between participants with CHD and a jointly called cohort without CHD. We then assessed the relationship of the predicted impact of ncDNVs with their sulcal folding patterns. ncDNVs predicted to increase H3K9me2 modification were associated with larger disruptions in right parietal sulcal patterns in the CHD cohort. Genes predicted to be regulated by these ncDNVs were enriched for functions related to neuronal development. This highlights the potential of deep learning models to generate hypotheses about the role of noncoding variants in brain development.

PMID:39877905 | PMC:PMC11772982 | DOI:10.1016/j.isci.2024.111707

Cureus. 2024 Dec 28;16(12):e76530. doi: 10.7759/cureus.76530. eCollection 2024 Dec.

ABSTRACT

Background Orthodontic diagnostic workflows often rely on manual classification and archiving of large volumes of patient images, a process that is both time-consuming and prone to errors such as mislabeling and incomplete documentation. These challenges can compromise treatment accuracy and overall patient care. To address these issues, we propose an artificial intelligence (AI)-driven deep learning framework based on convolutional neural networks (CNNs) to automate the classification and archiving of orthodontic diagnostic images. Our AI-based framework enhances workflow efficiency and reduces human errors. This study is an initial step towards fully automating orthodontic diagnosis and treatment planning systems, specifically focusing on the automation of orthodontic diagnostic record classification using AI. Methods This study employed a dataset comprising 61,842 images collected from three dental clinics, distributed across 13 categories. A sequential classification approach was developed, starting with a primary model that categorized images into three main groups: extraoral, intraoral, and radiographic. Secondary models were applied within each group to perform the final classification. The proposed model, enhanced with attention modules, was trained and compared with pre-trained models such as ResNet50 (Microsoft Corporation, Redmond, Washington, United States) and InceptionV3 (Google LLC, Mountain View, California, United States). External validation was performed using 13,729 new samples to assess the artificial intelligence (AI) system's accuracy and generalizability compared to expert assessments. Results The deep learning framework achieved an accuracy of 99.24% on an external validation set, demonstrating performance almost on par with human experts. Additionally, the model demonstrated significantly faster processing times compared to manual methods. Gradient-weighted class activation mapping (Grad-CAM) visualizations confirmed that the model effectively focused on clinically relevant features during classification, further supporting its clinical applicability. Conclusion This study introduces a deep learning framework for automating the classification and archiving of orthodontic diagnostic images. The model achieved impressive accuracy and demonstrated clinically relevant feature focus through Grad-CAM visualizations. Beyond its high accuracy, the framework offers significant improvements in processing speed, making it a viable tool for real-time applications in orthodontics. This approach not only reduces the workload in healthcare settings but also lays the foundation for future automated diagnostic and treatment planning systems in digital orthodontics.

PMID:39877794 | PMC:PMC11774544 | DOI:10.7759/cureus.76530

Neurooncol Adv. 2025 Jan 20;7(1):vdae225. doi: 10.1093/noajnl/vdae225. eCollection 2025 Jan-Dec.

ABSTRACT

BACKGROUND: This study aimed to develop an automated algorithm to noninvasively distinguish gliomas from other intracranial pathologies, preventing misdiagnosis and ensuring accurate analysis before further glioma assessment.

METHODS: A cohort of 1280 patients with a variety of intracranial pathologies was included. It comprised 218 gliomas (mean age 54.76 ± 13.74 years; 136 males, 82 females), 514 patients with brain metastases (mean age 59.28 ± 12.36 years; 228 males, 286 females), 366 patients with inflammatory lesions (mean age 41.94 ± 14.57 years; 142 males, 224 females), 99 intracerebral hemorrhages (mean age 62.68 ± 16.64 years; 56 males, 43 females), and 83 meningiomas (mean age 63.99 ± 13.31 years; 25 males, 58 females). Radiomic features were extracted from fluid-attenuated inversion recovery (FLAIR), contrast-enhanced, and noncontrast T1-weighted MR sequences. Subcohorts, with 80% for training and 20% for testing, were established for model validation. Machine learning models, primarily XGBoost, were trained to distinguish gliomas from other pathologies.

RESULTS: The study demonstrated promising results in distinguishing gliomas from various intracranial pathologies. The best-performing model consistently achieved high area-under-the-curve (AUC) values, indicating strong discriminatory power across multiple distinctions, including gliomas versus metastases (AUC = 0.96), gliomas versus inflammatory lesions (AUC = 1.0), gliomas versus intracerebral hemorrhages (AUC = 0.99), gliomas versus meningiomas (AUC = 0.98). Additionally, across all these entities, gliomas had an AUC of 0.94.

CONCLUSIONS: The study presents an automated approach that effectively distinguishes gliomas from common intracranial pathologies. This can serve as a quality control upstream to further artificial-intelligence-based genetic analysis of cerebral gliomas.

PMID:39877747 | PMC:PMC11773384 | DOI:10.1093/noajnl/vdae225

MethodsX. 2025 Jan 6;14:103158. doi: 10.1016/j.mex.2025.103158. eCollection 2025 Jun.

ABSTRACT

Integrated Circuits are made of various transistors that are embedded on a silicon wafer, these wafers are difficult to process and hence are prone to defects. Defecting these defects manually is a time consuming and labour-intensive task and hence automation is necessary. Deep Learning approach is better suited in this case as it is able to generalize defects if trained properly and can be a solution to segmentation and classification of defects automatically. The segmentation model mentioned in this study achieved a Mean Absolute Error (MAE) of 0.0036, a Root Mean Squared Error (RMSE) of 0.0576, a Dice Index (DSC) of 0.7731, and an Intersection over Union (IoU) of 0.6590. The classification model achieved 0.9705 Accuracy, 0.9678 Precision, 0.9705 Recall, and 0.9676 F1 Score. In order to make this process a more interactive, an LLM with Q&A capabilities was integrated to solve any doubts and answer any questions regarding defects in wafers. This approach helps automate the detection process thus improving quality of end product.•Successful and precise defect segmentation and classification using Deep Learning was achieved.•High-intensity regions after post-processing.•An LLM offering defect analysis and guidance was streamlined.

PMID:39877475 | PMC:PMC11773255 | DOI:10.1016/j.mex.2025.103158

Ophthalmol Sci. 2024 Nov 28;5(2):100664. doi: 10.1016/j.xops.2024.100664. eCollection 2025 Mar-Apr.

ABSTRACT

OBJECTIVE: Detecting and measuring changes in longitudinal fundus imaging is key to monitoring disease progression in chronic ophthalmic diseases, such as glaucoma and macular degeneration. Clinicians assess changes in disease status by either independently reviewing or manually juxtaposing longitudinally acquired color fundus photos (CFPs). Distinguishing variations in image acquisition due to camera orientation, zoom, and exposure from true disease-related changes can be challenging. This makes manual image evaluation variable and subjective, potentially impacting clinical decision-making. We introduce our deep learning (DL) pipeline, "EyeLiner," for registering, or aligning, 2-dimensional CFPs. Improved alignment of longitudinal image pairs may compensate for differences that are due to camera orientation while preserving pathological changes.

DESIGN: EyeLiner registers a "moving" image to a "fixed" image using a DL-based keypoint matching algorithm.

PARTICIPANTS: We evaluate EyeLiner on 3 longitudinal data sets: Fundus Image REgistration (FIRE), sequential images for glaucoma forecast (SIGF), and our internal glaucoma data set from the Colorado Ophthalmology Research Information System (CORIS).

METHODS: Anatomical keypoints along the retinal blood vessels were detected from the moving and fixed images using a convolutional neural network and subsequently matched using a transformer-based algorithm. Finally, transformation parameters were learned using the corresponding keypoints.

MAIN OUTCOME MEASURES: We computed the mean distance (MD) between manually annotated keypoints from the fixed and the registered moving image. For comparison to existing state-of-the-art retinal registration approaches, we used the mean area under the curve (AUC) metric introduced in the FIRE data set study.

RESULTS: EyeLiner effectively aligns longitudinal image pairs from FIRE, SIGF, and CORIS, as qualitatively evaluated through registration checkerboards and flicker animations. Quantitative results show that the MD decreased for this model after alignment from 321.32 to 3.74 pixels for FIRE, 9.86 to 2.03 pixels for CORIS, and 25.23 to 5.94 pixels for SIGF. We also obtained an AUC of 0.85, 0.94, and 0.84 on FIRE, CORIS, and SIGF, respectively, beating the current state-of-the-art SuperRetina (AUCFIRE = 0.76, AUCCORIS = 0.83, AUCSIGF = 0.74).

CONCLUSIONS: Our pipeline demonstrates improved alignment of image pairs in comparison to the current state-of-the-art methods on 3 separate data sets. We envision that this method will enable clinicians to align image pairs and better visualize changes in disease over time.

FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

PMID:39877463 | PMC:PMC11773051 | DOI:10.1016/j.xops.2024.100664

Health Inf Sci Syst. 2025 Jan 26;13(1):18. doi: 10.1007/s13755-025-00338-6. eCollection 2025 Dec.

ABSTRACT

This study introduces a novel classification method to distinguish children with autism from typically developing children. We recruited 50 school-age children in Taiwan, including 44 boys and 6 girls aged 6 to 12 years, and asked them to draw patterns from a visual-motor integration test to collect data and train deep learning classification models. Ensemble learning was adopted to significantly improve the classification accuracy to 0.934. Moreover, we identified five patterns that most effectively differentiate the drawing performance between children with and without ASD. From these five patterns we found that children with ASD had difficulty producing patterns that include circles and spatial relationships. These results align with previous findings in the field of visual-motor perceptions of individuals with autism. Our results offer a potential cross-cultural tool to detect autism, which can further promote early detection and intervention of autism.

PMID:39877430 | PMC:PMC11769875 | DOI:10.1007/s13755-025-00338-6

Res Sq [Preprint]. 2025 Jan 17:rs.3.rs-5584635. doi: 10.21203/rs.3.rs-5584635/v1.

ABSTRACT

The spatial arrangement of cells plays a pivotal role in shaping tissue functions in various biological systems and diseased microenvironments. However, it is still under-investigated of the topological coordinating rules among different cell types as tissue spatial patterns. Here, we introduce the Triangulation cellular community motif Neural Network (TrimNN), a bottom-up approach to estimate the prevalence of sizeable conservative cell organization patterns as Cellular Community (CC) motifs in spatial transcriptomics and proteomics. Different from clustering cell type composition from classical top-down analysis, TrimNN differentiates cellular niches as countable topological blocks in recurring interconnections of various types, representing multicellular neighborhoods with interpretability and generalizability. This graph-based deep learning framework adopts inductive bias in CCs and uses a semi-divide and conquer approach in the triangulated space. In spatial omics studies, various sizes of CC motifs identified by TrimNN robustly reveal relations between spatially distributed cell-type patterns and diverse phenotypical biological functions.

PMID:39877090 | PMC:PMC11774463 | DOI:10.21203/rs.3.rs-5584635/v1

iScience. 2024 Dec 9;28(1):111558. doi: 10.1016/j.isci.2024.111558. eCollection 2025 Jan 17.

ABSTRACT

Flax, as a functional crop with rich essential fatty acids and nutrients, is important in nutrition and industrial applications. However, the current process of flax seed detection relies mainly on manual operation, which is not only inefficient but also prone to error. The development of computer vision and deep learning techniques offers a new way to solve this problem. In this study, based on RT-DETR, we introduced the RepNCSPELAN4 module, ADown module, Context Aggregation module, and TFE module, and designed the HWD-ADown module, HiLo-AIFI module, and DSSFF module, and proposed an improved model, called LEHP-DETR. Experimental results show that LEHP-DETR achieves significant performance improvement on the flax dataset and comprehensively outperforms the comparison model. Compared to the base model, LEHP-DETR reduces the number of parameters by 67.3%, the model size by 66.3%, and the FLOPs by 37.6%. the average detection accuracy mAP50 and mAP50:95 increased by 2.6% and 3.5%, respectively.

PMID:39877068 | PMC:PMC11773470 | DOI:10.1016/j.isci.2024.111558

J Hand Microsurg. 2024 Oct 28;17(1):100171. doi: 10.1016/j.jham.2024.100171. eCollection 2025 Jan.

ABSTRACT

BACKGROUND: Trigger finger is a common disorder of the hand characterized by pain and locking of the digits during flexion or extension. In cases refractory to nonoperative management, surgical release of the A1 pulley can be performed. This study evaluates the ability of machine learning (ML) techniques to predict short-term complications following trigger digit release surgery.

METHODS: A retrospective study was conducted using data for trigger digit release from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) years 2005-2020. Outcomes of interest were 30-day complications and 30-day return to the operating room. Three ML algorithms were evaluated - a Random Forest (RF), Elastic-Net Regression (ENet), and Extreme Gradient Boosted Tree (XGBoost), along with a deep learning Neural Network (NN). Feature importance analysis was performed in the highest performing model for each outcome to identify predictors with the greatest contributions.

RESULTS: We included a total of 1209 cases of trigger digit release. The best algorithm for predicting wound complications was the RF, with an AUC of 0.64 ± 0.04. The XGBoost algorithm was best performing for medical complications (AUC: 0.70 ± 0.06) and reoperations (AUC: 0.60 ± 0.07). All three models had performance significantly above the AUC benchmark of 0.50 ± 0.00. On our feature importance analysis, age was distinctively the highest contributing predictor of wound complications.

CONCLUSIONS: Machine learning can be successfully used for risk stratification in surgical patients. Moving forwards, it is imperative for hand surgeons to continue evaluating applications of ML in the field.

PMID:39876951 | PMC:PMC11770221 | DOI:10.1016/j.jham.2024.100171