A guide to machine learning for biologists

Anxiety about artificial intelligence from patient and doctor-physician

OBJECTIVE

This paper investigates the anxiety surrounding the integration of artificial intelligence (AI) in doctor-patient interactions, analyzing the perspectives of both patients and healthcare providers to identify key concerns and potential solutions.

METHODS

The study employs a comprehensive literature review, examining existing research on AI in healthcare, and synthesizes findings from various surveys and studies that explore the attitudes of patients and doctors towards AI applications in medical settings.

RESULTS

The analysis reveals that patient anxiety encompasses algorithm aversion, robophobia, lack of humanistic care, challenges in human-machine interaction, and concerns about AI's universal applicability. Doctors' anxieties stem from fears of replacement, legal liabilities, emotional impacts of work environment changes, and technological apprehension. The paper highlights the need for patient participation, humanistic care, improved interaction methods, educational training, and policy guidelines to foster public understanding and trust in AI.

CONCLUSION

The paper concludes that addressing AI anxiety in doctor-patient relationships is crucial for successfully integrating AI in healthcare. It emphasizes the importance of respecting patient autonomy, addressing the lack of humanistic care, and improving patient-AI interaction to enhance the patient experience and reduce medical errors.

PRACTICE IMPLICATIONS

The study suggests that future research should focus on understanding the needs and concerns of patients and doctors, strengthening medical humanities education, and establishing policies to guide the ethical use of AI in medicine. It also recommends public education to enhance understanding and trust in AI to improve medical services and ensure professional development and stable work environment for doctors.

AI-driven 3D bioprinting for regenerative medicine: From bench to bedside

In recent decades, 3D bioprinting has garnered significant research attention due to its ability to manipulate biomaterials and cells to create complex structures precisely. However, due to technological and cost constraints, the clinical translation of 3D bioprinted products (BPPs) from bench to bedside has been hindered by challenges in terms of personalization of design and scaling up of production. Recently, the emerging applications of artificial intelligence (AI) technologies have significantly improved the performance of 3D bioprinting. However, the existing literature remains deficient in a methodological exploration of AI technologies' potential to overcome these challenges in advancing 3D bioprinting toward clinical application. This paper aims to present a systematic methodology for AI-driven 3D bioprinting, structured within the theoretical framework of Quality by Design (QbD). This paper commences by introducing the QbD theory into 3D bioprinting, followed by summarizing the technology roadmap of AI integration in 3D bioprinting, including multi-scale and multi-modal sensing, data-driven design, and in-line process control. This paper further describes specific AI applications in 3D bioprinting's key elements, including bioink formulation, model structure, printing process, and function regulation. Finally, the paper discusses current prospects and challenges associated with AI technologies to further advance the clinical translation of 3D bioprinting.

Unmasking the chameleons: A benchmark for out-of-distribution detection in medical tabular data

BACKGROUND

Machine Learning (ML) models often struggle to generalize effectively to data that deviates from the training distribution. This raises significant concerns about the reliability of real-world healthcare systems encountering such inputs known as out-of-distribution (OOD) data. These concerns can be addressed by real-time detection of OOD inputs. While numerous OOD detection approaches have been suggested in other fields - especially in computer vision - it remains unclear whether similar methods effectively address challenges posed by medical tabular data.

OBJECTIVE

To answer this important question, we propose an extensive reproducible benchmark to compare different OOD detection methods in medical tabular data across a comprehensive suite of tests.

METHOD

To achieve this, we leverage 4 different and large public medical datasets, including eICU and MIMIC-IV, and consider various kinds of OOD cases within these datasets. For example, we examine OODs originating from a statistically different dataset than the training set according to the membership model introduced by Debray et al. [1], as well as OODs obtained by splitting a given dataset based on a value of a distinguishing variable. To identify OOD instances, we explore a range of 10 density-based methods that learn the marginal distribution of the data, alongside 17 post-hoc detectors that are applied on top of prediction models already trained on the data. The prediction models involve three distinct architectures, namely MLP, ResNet, and Transformer.

MAIN RESULTS

In our experiments, when the membership model achieved an AUC of 0.98, which indicated a clear distinction between OOD data and the training set, we observed that the OOD detection methods had achieved AUC values exceeding 0.95 in distinguishing OOD data. In contrast, in the experiments with subtler changes in data distribution such as selecting OOD data based on ethnicity and age characteristics, many OOD detection methods performed similarly to a random classifier with AUC values close to 0.5. This may suggest a correlation between separability, as indicated by the membership model, and OOD detection performance, as indicated by the AUC of the detection model. This warrants future research.

A methodological approach to age estimation of the intra-puparial period of the forensically relevant blow fly Calliphora vicina via Fourier transform infrared spectroscopy

Estimating the age of immature blow flies is of great importance for forensic entomology. However, no gold-standard technique for an accurate determination of the intra-puparial age has yet been established. Fourier transform infrared (FTIR) spectroscopy is a method to (bio-)chemically characterise material based on the absorbance of electromagnetic energy by functional groups of molecules. In recent years, it also has become a powerful tool in forensic and life sciences, as it is a fast and cost-effective way to characterise all kinds of material and biological traces. This study is the first to collect developmental reference data on the changes in absorption spectra during the intra-puparial period of the forensically important blow fly Calliphora vicina Robineau-Desvoidy (Diptera: Calliphoridae). Calliphora vicina was reared at constant 20°C and 25°C and specimens were killed every other day throughout their intra-puparial development. In order to investigate which part yields the highest detectable differences in absorption spectra throughout the intra-puparial development, each specimen was divided into two different subsamples: the pupal body and the former cuticle of the third instar, that is, the puparium. Absorption spectra were collected with a FTIR spectrometer coupled to an attenuated total reflection (ATR) unit. Classification accuracies of different wavenumber regions with two machine learning models, i.e., random forests (RF) and support vector machines (SVMs), were tested. The best age predictions for both temperature settings and machine learning models were obtained by using the full spectral range from 3700 to 600 cm-1. While SVMs resulted in better accuracies for C. vicina reared at 20°C, RFs performed almost as good as SVMs for data obtained from 25°C. In terms of sample type, the pupal body gave smoother spectra and usually better classification accuracies than the puparia. This study shows that FTIR spectroscopy is a promising technique in forensic entomology to support the estimation of the minimum post-mortem interval (PMImin), by estimating the age of a given insect specimen.

Assessing Axillary Lymph Node Burden and Prognosis in cT1-T2 Stage Breast Cancer Using Machine Learning Methods: A Retrospective Dual-Institutional MRI Study

BACKGROUND

Pathological axillary lymph node (pALN) burden is an important factor for treatment decision-making in clinical T1-T2 (cT1-T2) stage breast cancer. Preoperative assessment of the pALN burden and prognosis aids in the individualized selection of therapeutic approaches.

PURPOSE

To develop and validate a machine learning (ML) model based on clinicopathological and MRI characteristics for assessing pALN burden and survival in patients with cT1-T2 stage breast cancer.

STUDY TYPE

Retrospective.

POPULATION

A total of 506 females (range: 24-83 years) with cT1-T2 stage breast cancer from two institutions, forming the training (N = 340), internal validation (N = 85), and external validation cohorts (N = 81), respectively.

FIELD STRENGTH/SEQUENCE

This study used 1.5-T, axial fat-suppressed T2-weighted turbo spin-echo sequence and axial three-dimensional dynamic contrast-enhanced fat-suppressed T1-weighted gradient echo sequence.

ASSESSMENT

Four ML methods (eXtreme Gradient Boosting [XGBoost], Support Vector Machine, k-Nearest Neighbor, Classification and Regression Tree) were employed to develop models based on clinicopathological and MRI characteristics. The performance of these models was evaluated by their discriminative ability. The best-performing model was further analyzed to establish interpretability and used to calculate the pALN score. The relationships between the pALN score and disease-free survival (DFS) were examined.

STATISTICAL TESTS

Chi-squared test, Fisher's exact test, univariable logistic regression, area under the curve (AUC), Delong test, net reclassification improvement, integrated discrimination improvement, Hosmer-Lemeshow test, log-rank, Cox regression analyses, and intraclass correlation coefficient were performed. A P-value <0.05 was considered statistically significant.

RESULTS

The XGB II model, developed based on the XGBoost algorithm, outperformed the other models with AUCs of 0.805, 0.803, and 0.818 in the three cohorts. The Shapley additive explanation plot indicated that the top variable in the XGB II model was the Node Reporting and Data System score. In multivariable Cox regression analysis, the pALN score was significantly associated with DFS (hazard ratio: 4.013, 95% confidence interval: 1.059-15.207).

DATA CONCLUSION

The XGB II model may allow to evaluate pALN burden and could provide prognostic information in cT1-T2 stage breast cancer patients.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

AI-based non-invasive imaging technologies for early autism spectrum disorder diagnosis: A short review and future directions

Autism Spectrum Disorder (ASD) is a neurological condition, with recent statistics from the CDC indicating a rising prevalence of ASD diagnoses among infants and children. This trend emphasizes the critical importance of early detection, as timely diagnosis facilitates early intervention and enhances treatment outcomes. Consequently, there is an increasing urgency for research to develop innovative tools capable of accurately and objectively identifying ASD in its earliest stages. This paper offers a short overview of recent advancements in non-invasive technology for early ASD diagnosis, focusing on an imaging modality, structural MRI technique, which has shown promising results in early ASD diagnosis. This brief review aims to address several key questions: (i) Which imaging radiomics are associated with ASD? (ii) Is the parcellation step of the brain cortex necessary to improve the diagnostic accuracy of ASD? (iii) What databases are available to researchers interested in developing non-invasive technology for ASD? (iv) How can artificial intelligence tools contribute to improving the diagnostic accuracy of ASD? Finally, our review will highlight future trends in ASD diagnostic efforts.

Advancements in omics technologies: Molecular mechanisms of acute lung injury and acute respiratory distress syndrome (Review)

Acute lung injury (ALI)/acute respiratory distress syndrome (ARDS) is an inflammatory response arising from lung and systemic injury with diverse causes and associated with high rates of morbidity and mortality. To date, no fully effective pharmacological therapies have been established and the relevant underlying mechanisms warrant elucidation, which may be facilitated by multi‑omics technology. The present review summarizes the application of multi‑omics technology in identifying novel diagnostic markers and therapeutic strategies of ALI/ARDS as well as its pathogenesis.

Unveiling the effect of urinary xenoestrogens on chronic kidney disease in adults: A machine learning model

Exposure to three primary xenoestrogens (XEs), including phthalates, parabens, and phenols, has been strongly associated with chronic kidney disease (CKD). An interpretable machine learning (ML) model was developed to predict CKD using data from the National Health and Nutrition Examination Survey (NHANES) database spanning from 2007 to 2016. Four ML algorithms-random forest classifier (RF), XGBoost (XGB), k-nearest neighbors (KNN), and support vector machine (SVM)-were used alongside traditional logistic regression to predict CKD. The study included 6910 U.S. adults, with XGB showing the highest predictive accuracy, achieving an area under the curve (AUC) of 0.817 (95 % CI: 0.789, 0.844). The selected model was interpreted using Shapley additive explanations (SHAP) and partial dependence plot (PDP). The SHAP method identified key predictive features for CKD in urinary metabolites of XEs-methyl paraben (MeP), mono-(carboxynonyl) phthalate (MCNP), and triclosan (TCS)-and suggested personalized CKD care should focus on XE control. PDP results confirmed that, within certain ranges, MeP levels positively impacted the model, MCNP levels negatively impacted it, and TCS had a mixed effect. The synergistic effects suggested that managing urinary MeP levels could be essential for the effective control of CKD. In summary, our research highlights the significant predictive potential of XEs for CKD, especially MeP, MCNP, and TCS.

Visit-to-visit blood pressure variability and clinical outcomes in peritoneal dialysis - based on machine learning algorithms

This study aims to investigate the association between visit-to-visit blood pressure variability (VVV) in early stage of continuous ambulatory peritoneal dialysis (CAPD) and long-term clinical outcomes, utilizing machine learning algorithms. Patients who initiated CAPD therapy between January 1, 2006, and December 31, 2009 were enrolled. VVV parameters were collected during the first six months of CAPD therapy. Patient follow-up extended to December 31, 2021, for up to 15.8 years. The primary outcome was the occurrence of a three-point major adverse cardiovascular event (MACE). Four machine learning algorithms and competing risk regression analysis were applied to construct predictive models. A total of 666 participants were included in the analysis with a mean age of 47.9 years. One of the six VVV parameters, standard deviation of diastolic blood pressure (SDDBP), was finally enrolled into the MACE predicting model and mortality predicting model. In the MACE predicting model, higher SDDBP was associated with 99% higher MACE risk. The association between SDDBP and MACE risk was attenuated by better residual renal function (p for interaction <0.001). In the mortality predicting model, higher SDDBP was associated with 46% higher mortality risk. This cohort study discerned that high SDDBP in early stage of CAPD indicated increased long-term MACE and mortality risks.

Comprehensive analysis of aging-related gene expression patterns and identification of potential intervention targets

PURPOSE

This study aims to understand the molecular mechanisms underlying the aging process and identify potential interventions to mitigate age-related decline and diseases.

METHODS

This study utilized the GSE168753 dataset to conduct comprehensive differential gene expression analysis and co-expression module analysis. Machine learning and Mendelian randomization analyses were employed to identify core aging-associated genes and potential drug targets. Molecular docking simulations and mediation analysis were also performed to explore potential compounds and mediators involved in the aging process.

RESULTS

The analysis identified 4164 differentially expressed genes, with 1893 upregulated and 2271 downregulated genes. Co-expression analysis revealed 21 modules, including both positively and negatively correlated modules between older age and younger age groups. Further exploration identified 509 aging-related genes with distinct biological functions. Machine learning and Mendelian randomization analyses identified eight core genes associated with aging, including DPP9, GNAZ, and RELL2. Molecular docking simulations suggested resveratrol, folic acid, and ethinyl estradiol as potential compounds capable of attenuating aging through modulation of RELL2 expression. Mediation analysis indicated that eosinophil counts and neutrophil count might act as mediators in the causal relationship between genes and aging-related indicators.

CONCLUSION

This comprehensive study provides valuable insights into the molecular mechanisms of aging and offers important implications for the development of anti-aging therapeutics. Key Messages What is already known on this topic - Prior research outlines aging's complexity, necessitating precise molecular targets for intervention. What this study adds - This study identifies novel aging-related genes, potential drug targets, and therapeutic compounds, advancing our understanding of aging mechanisms. How this study might affect research, practice, or policy - Findings may inform targeted therapies for age-related conditions, influencing future research and clinical practices.

Machine Learning Prognostic Model for Post-Radical Resection Hepatocellular Carcinoma in Hepatitis B Patients

Purpose

Primary liver cancer, predominantly hepatocellular carcinoma (HCC), constitutes a substantial global health challenge, characterized by a poor prognosis, particularly in regions with high prevalence of hepatitis B virus (HBV) infection, such as China. This study sought to develop and validate a machine learning-based prognostic model to predict survival outcomes in patients with HBV-related HCC following radical resection, with the potential to inform personalized treatment strategies.

Patients and Methods

This study retrospectively analyzed clinical data from 146 patients at Xinjiang Medical University and 75 patients from The Cancer Genome Atlas (TCGA) database. A prognostic model was developed using a machine learning algorithm and evaluated for predictive performance using the concordance index (C-index), calibration curve, decision curve analysis (DCA), and receiver operating characteristic (ROC) curves.

Results

Key predictors for constructing the best model included body mass index (BMI), albumin (ALB) levels, surgical resection method (SRM), and the American Joint Committee on Cancer (AJCC) stage. The model achieved a C-index of 0.736 in the training set and performed well in both training and validation datasets. It accurately predicted 1-, 3-, and 5-year survival rates, with Area Under the Curve (AUC) values of 0.843, 0.797, and 0.758, respectively. Calibration curve analysis and Decision Curve Analysis (DCA) further validated the model's predictive capability, suggesting its potential use in clinical decision-making.

Conclusion

The study highlights the importance of BMI, ALB, SRM, and AJCC staging in predicting HBV-related HCC outcomes. The machine learning model aids clinicians in making better treatment decisions, potentially enhancing patient outcomes.

The Optimization of Culture Conditions for Injectable Recombinant Collagen Hydrogel Preparation Using Machine Learning

Injectable recombinant collagen hydrogels (RCHs) are crucial in biomedical applications. Culture conditions play an important role in the preparation of hydrogels. However, determining the characteristics of hydrogels under certain conditions and determining the optimal conditions swiftly still remain challenging tasks. In this study, a machine learning approach was introduced to explore the correlation between hydrogel characteristics and culture conditions and determine the optimal culture conditions. The study focused on four key factors as independent variables: initial substrate concentration, reaction temperature, pH level, and reaction time, while the dependent variable was the elastic modulus of the hydrogels. To analyze the impact of these factors on the elastic modulus, four mathematical models were employed, including multiple linear regression (ML), decision tree (DT), support vector machine (SVM), and neural network (NN). The theoretical outputs of NN were closest to the actual values. Therefore, NN proved to be the most suitable model. Subsequently, the optimal culture conditions were identified as a substrate concentration of 15% (W/V), a reaction temperature of 4 °C, a pH of 7.0, and a reaction time of 12 h. The hydrogels prepared under these specific conditions exhibited a predicted elastic modulus of 15,340 Pa, approaching that of natural elastic cartilage.

Research on the development of an intelligent prediction model for blood pressure variability during hemodialysis

OBJECTIVE

Blood pressure fluctuations during dialysis, including intradialytic hypotension (IDH) and intradialytic hypertension (IDHTN), are common complications among patients undergoing maintenance hemodialysis. Early prediction of IDH and IDHTN can help reduce the occurrence of these fluctuations. With the development of artificial intelligence, machine learning and deep learning models have become increasingly sophisticated in the field of hemodialysis. Utilizing machine learning to predict blood pressure fluctuations during dialysis has become a viable predictive method.

METHODS

Our study included data from 67,524 hemodialysis sessions conducted at Ningbo No.2 Hospital and Xiangshan First People's Hospital from August 1, 2019, to September 30, 2023. 47,053 sessions were used for model training and testing, while 20,471 sessions were used for external validation. We collected 45 features, including general information, vital signs, blood routine, blood biochemistry, and other relevant data. Data not meeting the inclusion criteria were excluded, and feature engineering was performed. The definitions of IDH and IDHTN were clarified, and 10 machine learning algorithms were used to build the models. For model development, the dialysis data were randomly split into a training set (80%) and a testing set (20%). To evaluate model performance, six metrics were used: accuracy, precision, recall, F1 score, ROC-AUC, and PR-AUC. Shapley Additive Explanation (SHAP) method was employed to identify eight key features, which were used to develop a clinical application utilizing the Streamlit framework.

RESULTS

Statistical analysis showed that IDH occurred in 56.63% of hemodialysis sessions, while the incidence of IDHTN was 23.53%. Multiple machine learning models (e.g., CatBoost, RF) were developed to predict IDH and IDHTN events. XGBoost performed the best, achieving ROC-AUC scores of 0.89 for both IDH and IDHTN in internal validation, with PR-AUC scores of 0.95 and 0.78, and high accuracy, precision, recall, and F1 scores. The SHAP method identified pre-dialysis systolic blood pressure, BMI, and pre-dialysis mean arterial pressure as the top three important features. It has been translated into a convenient application for use in clinical settings.

CONCLUSION

Using machine learning models to predict IDH and IDHTN during hemodialysis is feasible and provides clinically reliable predictive performance. This can help timely implement interventions during hemodialysis to prevent problems, reduce blood pressure fluctuations during dialysis, and improve patient outcomes.

A machine-learning approach to optimize nutritional properties and organic wastes recycling efficiency conversed by black soldier fly (Hermetia illucens)

Suboptimal nutrition in organic waste limits the growth of black soldier fly (BSF) larvae, thereby reducing biowaste recycling efficiency. In this study, weight gain data from BSF larvae fed diets with distinct nutrient compositions were used to build a machine learning model. Among the algorithms tested, the XGBoost model demonstrated the best performance in predicting weight gain. The model identified protein as the most critical nutrient factor for larval biomass and was used to determine the optimal diet by calculating the highest weight gain from 30,000 randomly generated nutrient combinations. Supplementing the missing nutrients in organic waste according to the optimal diet improved the weight gain and feed conversion rate of BSF larvae. Feeding larvae a mixture of organic wastes, a cost-effective strategy to meet dietary nutrition requirements, resulted in significant increases in both the bioconversion rate (up to 9.7%) and mass reduction rate (up to 22.8%) of organic waste.

Advantages and Challenges of Using Antimicrobial Peptides in Synergism with Antibiotics for Treating Multidrug-Resistant Bacteria

Multidrug-resistant bacteria (MDR) have become a global threat, impairing positive outcomes in many cases of infectious diseases. Treating bacterial infections with antibiotic monotherapy has become a huge challenge in modern medicine. Although conventional antibiotics can be efficient against many bacteria, there is still a need to develop antimicrobial agents that act against MDR bacteria. Bioactive peptides, particularly effective against specific types of bacteria, are recognized for their selective and effective action against microorganisms and, at the same time, are relatively safe and well tolerated. Therefore, a growing number of works have proposed the use of antimicrobial peptides (AMPs) in synergism with commercial antibiotics as an alternative therapeutic strategy. This review provides an overview of the critical parameters for using AMPs in synergism with antibiotics as well as addressing the strengths and weaknesses of this combination therapy using in vitro and in vivo models of infection. We also cover the challenges and perspectives of using this approach for clinical practice and the advantages of applying artificial intelligence strategies to predict the most promising combination therapies between AMPs and antibiotics.

Generative Artificial Intelligence in Academic Surgery: Ethical Implications and Transformative Potential

Artificial intelligence (AI) is rapidly being used in medicine due to its advanced capabilities in image and video recognition, clinical decision support, surgical education, and administrative task automation. Large language models such as OpenAI's Generative Pretrained Transformer (GPT)-4 and Google's Bard have particularly revolutionized text generation, offering substantial benefits for the academic surgeon, including aiding in manuscript and grant writing. However, integrating AI into academic surgery necessitates addressing ethical concerns such as bias, transparency, and intellectual property. This paper provides guidelines and recommendations based on current literature around the opportunities and ethical challenges of AI in academic surgery. We discuss the underlying mechanisms of large language models, their potential biases, and the importance of responsible usage. Furthermore, we explore the ethical implications of AI in clinical documentation, highlighting improved efficiency and necessary privacy concerns. This review also addresses the critical issue of intellectual property dilemmas posed by AI-generated innovations in university settings. Finally, we propose guidelines for the responsible adoption of AI in academic and clinical environments, stressing the need for transparency, ethical training, and robust governance frameworks to ensure AI enhances, rather than undermines, academic integrity and patient care.

A Plasma Proteomics-Based Model for Identifying the Risk of Postpartum Depression Using Machine Learning

Postpartum depression (PPD) poses significant risks to maternal and infant health, yet proteomic analyses of PPD-risk women remain limited. This study analyzed plasma samples from 30 healthy postpartum women and 30 PPD-risk women using mass spectrometry, identifying 98 differentially expressed proteins (29 upregulated and 69 downregulated). Principal component analysis revealed distinct protein expression profiles between the groups. Functional enrichment and PPI analyses further explored the biological functions of these proteins. Machine learning models (XGBoost and LASSO regression) identified 17 key proteins, with the optimal logistic regression model comprising P13797 (PLS3), P56750 (CLDN17), O43173 (ST8SIA3), P01593 (IGKV1D-33), and P43243 (MATR3). The model demonstrated excellent predictive performance through ROC curves, calibration, and decision curves. These findings suggest potential biomarkers for early PPD risk assessment, paving the way for personalized prediction. However, limitations include the lack of diagnostic interviews, such as the Structured Clinical Interview for DSM-V (SCID), to confirm PPD diagnosis, a small sample size, and limited ethnic diversity, affecting generalizability. Future studies should expand sample diversity, confirm diagnoses with SCID, and validate biomarkers in larger cohorts to ensure their clinical applicability.

A Guide to Metabolic Network Modeling for Plant Biology

Plants produce a diverse array of compounds that play crucial roles in growth, in development, and in responses to abiotic and biotic stresses. Understanding the fluxes within metabolic pathways is essential for guiding strategies aimed at directing metabolism for crop improvement and the plant natural product industry. Over the past decade, metabolic network modeling has emerged as a predominant tool for the integration, quantification, and prediction of the spatial and temporal distribution of metabolic flows. In this review, we present the primary methods for constructing mathematical models of metabolic systems and highlight recent achievements in plant metabolism using metabolic modeling. Furthermore, we discuss current challenges in applying network flux analysis in plants and explore the potential use of machine learning technologies in plant metabolic modeling. The practical application of mathematical modeling is expected to provide significant insights into the structure and regulation of plant metabolic networks.

Identification and validation of biomarkers related to mitochondria during ex vivo lung perfusion for lung transplants based on machine learning algorithm

BACKGROUND

Ex vivo lung perfusion (EVLP) is a critical strategy to rehabilitate marginal donor lungs, thereby increasing lung transplantation (LTx) rates. Ischemia-reperfusion (I/R) injury inevitably occurs during LTx. Exploring the common mechanisms between EVLP and I/R may unveil new treatment targets to enhance LTx outcomes.

METHODS

We obtained datasets from the public Gene Expression Omnibus (GEO) for EVLP (GSE127055 and GSE127057) and I/R (GSE145989) processes. We performed analysis of differentially expressed genes (DEGs) and Gene Set Enrichment Analysis (GSEA). Mitochondrial genes were sourced from the MitoCarta 3.0 database. Hub mitochondrial-related DEGs (MitoDEGs) were identified using a combination of protein-protein interaction networks and machine learning methods, which were further validated in cell and mice models of EVLP.

RESULTS

GSEA analysis of DEGs following EVLP and I/R revealed significant inhibition of mitochondrial function pathways, encompassing mitochondrial central dogma, mtRNA metabolism, OXPHOS assembly factors, metals and cofactors, and heme synthesis and processing processes. Machine learning algorithms including Random Forest, LASSO, and XGBoost identified five downregulated genes (MTERF1, ACACA, COX15, OSGEPL1, and COQ9) as hub MitoDEGs for both EVLP and I/R processes. We confirmed the reduced expression of these hub MitoDEGs in endothelial cells during EVLP and observed mitochondrial damage in endothelial cells characterized by swollen morphology and cristae disappearance.

CONCLUSIONS

Imbalance in mitochondrial homeostasis is a shared pathological process during EVLP and I/R-induced lung injury. The identified hub mitochondrial-related genes (MTERF1, ACACA, COX15, OSGEPL1, and COQ9) suggest promising therapeutic targets for lung injury during LTx. The downregulation of these genes indicates a significant disruption in mitochondrial function. This study provides potential mitochondrial-related therapeutic targets for I/R-induced lung injury and for donor lung repair during EVLP procedure in LTx.

Data-driven machine learning models for predicting the maximum absorption and emission wavelengths of single benzene fluorophores

Single benzene fluorophores (SBFs) have garnered significant research attention due to their ease of preparation, seamless diffusion into biological samples, and low molecular weight. Accurately predicting the molecular photophysical properties, specifically the maximum absorption and emission wavelengths, is pivotal in advancing functional SBFs. In this study, we introduce a machine-learning model to estimate the maximum absorption and emission wavelengths of SBFs precisely. This model leverages a Full Connect Neural Network and computational chemistry and is tailored to address the challenges associated with a relatively small dataset (81 SBFs). Remarkably, our model (SBFs-ML) demonstrates impressive accuracy, yielding a mean relative error of 1.54 % and 2.93 % for SBFs' maximum absorption and emission wavelengths, respectively. Importantly, the SBFs-ML was bullied based on only three descriptors, resulting in strong interpretability. Experimental results have strongly corroborated these predictions. Our prediction methods are poised to facilitate significantly the efficient design and creation of SBFs.

Predicting Fitness-Related Traits Using Gene Expression and Machine Learning

Evolution by natural selection occurs at its most basic through the change in frequencies of alleles; connecting those genomic targets to phenotypic selection is an important goal for evolutionary biology in the genomics era. The relative abundance of gene products expressed in a tissue can be considered a phenotype intermediate to the genes and genomic regulatory elements themselves and more traditionally measured macroscopic phenotypic traits such as flowering time, size, or growth. The high dimensionality, low sample size nature of transcriptomic sequence data is a double-edged sword, however, as it provides abundant information but makes traditional statistics difficult. Machine learning (ML) has many features which handle high-dimensional data well and is thus useful in genetic sequence applications. Here, we examined the association of fitness components with gene expression data in Ipomoea hederacea (Ivyleaf morning glory) grown under field conditions. We combine the results of two different ML approaches and find evidence that expression of photosynthesis-related genes is likely under selection. We also find that genes related to stress and light responses were overall important in predicting fitness. With this study, we demonstrate the utility of ML models for smaller samples and their potential application for understanding natural selection.

Machine Learning in Solid-State Hydrogen Storage Materials: Challenges and Perspectives

Machine learning (ML) has emerged as a pioneering tool in advancing the research application of high-performance solid-state hydrogen storage materials (HSMs). This review summarizes the state-of-the-art research of ML in resolving crucial issues such as low hydrogen storage capacity and unfavorable de-/hydrogenation cycling conditions. First, the datasets, feature descriptors, and prevalent ML models tailored for HSMs are described. Specific examples include the successful application of ML in titanium-based, rare-earth-based, solid solution, magnesium-based, and complex HSMs, showcasing its role in exploiting composition-structure-property relationships and designing novel HSMs for specific applications. One of the representative ML works is the single-phase Ti-based HSM with superior cost-effective and comprehensive properties, tailored to fuel cell hydrogen feeding system at ambient temperature and pressure through high-throughput composition-performance scanning. More importantly, this review also identifies and critically analyzes the key challenges faced by ML in this domain, including poor data quality and availability, and the balance between model interpretability and accuracy, together with feasible countermeasures suggested to ameliorate these problems. In summary, this work outlines a roadmap for enhancing ML's utilization in solid-state hydrogen storage research, promoting more efficient and sustainable energy storage solutions.

Integrated Approach for Biomarker Discovery and Mechanistic Insights into the Co-Pathogenesis of Type 2 Diabetes Mellitus and Non-Hodgkin Lymphoma

Background

Type 2 diabetes mellitus (T2DM) is associated with an increased risk of non-Hodgkin lymphoma (NHL), but the underlying mechanisms remain unclear. This study aimed to identify potential biomarkers and elucidate the molecular mechanisms underlying the co-pathogenesis of T2DM and NHL.

Methods

Microarray datasets of T2DM and NHL were downloaded from the Gene Expression Omnibus database. Subsequently, a protein-protein interaction network was constructed based on the common differentially expressed genes (DEGs) between T2DM and NHL to explore regulatory interactions. Functional analyses were performed to explore underlying mechanisms. Topological analysis and machine learning algorithms were applied to refine hub gene selection. Finally, quantitative real-time polymerase chain reaction was performed to validate hub genes in clinical samples.

Results

Intersection analysis of DEGs from the T2DM and NHL datasets identified 81 shared genes. Functional analyses suggested that immune-related pathways played a significant role in the co-pathogenesis of T2DM and NHL. Topological analysis and machine learning identified three hub genes: GZMM, HSPG2, and SERPING1. Correlation analysis revealed significant correlations between these hub genes and immune cells, underscoring the importance of immune dysregulation in shared pathogenesis. The expression of these genes was successfully validated in clinical samples.

Conclusion

This study suggested the pivotal role of immune dysregulation in the co-pathogenesis of T2DM and NHL and identified and validated three hub genes as key contributors. These findings provide insight into the complex interplay between T2DM and NHL.

Evaluation of inflammatory-thrombosis panel as a diagnostic tool for vascular Behçet's disease

OBJECTIVES

Vascular Behçet's disease (VBD) is prevalent in 40% of BD, but lacks laboratory biomarker for timely diagnosis. We aimed to establish a diagnostic panel for discerning VBD and non-VBD patients and identify hemostatic-thrombotic markers most related to VBD pathogenesis using machine learning algorithm.

OBJECTIVES

A total of 338 BD patients comprising 123 VBD and 215 non-VBD were enrolled. Twenty-six clinical and laboratory features selected from LassoCV were included in multiple classifier to choose the optimal model for VBD differentiation. The Shapley Additive exPlanations (SHAP) was employed to interpret the contribution of model features for VBD prediction. Logistic regression analysis and nomogram were conducted to screen risk factors of VBD.

RESULTS

Inflammatory (neutrophils%, NK cells, IL-6), hematological (hemoglobin, hemoglobin distribution width (HDW)) and thrombosis (activated partial thromboplastin clotting time (APTT), D-dimer) parameters were elevated in VBD. Then we chose top contributors from XGBoost model and performed ten-fold cross validation, the diagnostic accuracy of which exceeded 0.90. Utilizing SHAP method, we identified higher incidence of arterial thrombosis or aneurysm and deep vein thrombosis, upregulated NK cell count, HDW, APTT and D-dimer, downregulated reticulocyte%, B cell count, red blood cell distribution width, cellular hemoglobin (CH) and TNF-α would ultimately generate the phenotype of VBD. Severity, hemoglobin, mean corpuscular hemoglobin, CH, HDW, APTT and D-dimer were found as potential risk factors for vascular outcomes among BD.

RESULTS

Our study developed a well-performed model leveraging clinical and laboratory parameters for differentiating VBD. Inflammatory and thrombotic risk factors are potential contributors to VBD. Key Points • Inflammatory (neutrophils%, NK cells, IL-6), hematological (HGB, HDW) and thrombosis (APTT, D-dimer) parameters were elevated in VBD. • We firstly developed an inflammatory-thrombosis model as a diagnostic tool for VBD. • HGB, MCH, CH, HDW, APTT and D-dimer are potential risk factors for VBD.

Machine Learning Analysis of Nutrient Associations with Peripheral Artery Disease: Insights from NHANES 1999-2004

OBJECTIVE

To investigate the relationship between nutrient intake and peripheral artery disease (PAD) using machine learning (ML) methods.

METHODS

Data from NHANES (1999-2004) were analyzed, including demographic, clinical, and dietary information. Nutrient intake was assessed through 24-hour dietary recalls using CADI and AMPM methods. PAD was defined as an Ankle-Brachial Index (ABI) <0.9. Six ML models-Extreme Gradient Boosting (XGBoost), Random Forest (RF), Naive Bayes Classifier (NB), Support Vector Machine (SVM), Logistic Regression (LR), and Decision Tree (DT)-were trained on a 70/30 train-test split, with missing data imputed and sample imbalance addressed via SMOTE. Model performance was evaluated using AUROC, accuracy, sensitivity, specificity, precision, recall, and F1 score. SHAP analysis was used to identify key features. In addition, to further enhance the interpretability of the model, we applied SHAP analysis to identify the features that have a significant impact on PAD prediction. This approach allowed us to determine the contribution of different variables to the model's output, providing deeper insights into how each feature influences the prediction of PAD outcomes.

RESULTS

Of 31,126 participants, 4,520 met inclusion criteria (mean age 61.2 ± 13.5 years; 48.8% male), and 441 (9.7%) had ABI <0.9. XGBoost outperformed other models, achieving an AUROC of 0.913 (95% CI, 0.891-0.936) and F1 score of 0.932. With SMOTE, its AUROC improved to 0.926 (95% CI, 0.889-0.936) and F1 score to 0.937. SHAP analysis identified Vitamin C, saturated fatty acids, selenium, phosphorus, and protein intake as key predictors of PAD.

CONCLUSIONS

This is the first study to apply ML algorithms to examine nutrient intake and PAD in a general population. Vitamin C and phosphorus showed negative correlations with PAD, while saturated fatty acids, protein, and selenium exhibited positive associations.

Intelligent Design of Lipid Nanoparticles for Enhanced Gene Therapeutics

Lipid nanoparticles (LNPs) are an effective delivery system for gene therapeutics. By optimizing their formulation, the physiochemical properties of LNPs can be tailored to improve tissue penetration, cellular uptake, and precise targeting. The application of these targeted delivery strategies within the LNP framework ensures efficient delivery of therapeutic agents to specific organs or cell types, thereby maximizing therapeutic efficacy. In the realm of genome editing, LNPs have emerged as a potent vehicle for delivering CRISPR/Cas components, offering significant advantages such as high in vivo efficacy. The incorporation of machine learning into the optimization of LNP platforms for gene therapeutics represents a significant advancement, harnessing its predictive capabilities to substantially accelerate the research and development process. This review highlights the dynamic evolution of LNP technology, which is expected to drive transformative progress in the field of gene therapy.

Laboratory measurement and machine learning-based analysis of driving factors for brake wear particle emissions from light-duty electric vehicles and heavy-duty vehicles

This study investigates brake wear particle (BWP) emissions from light-duty electric vehicles (EVs) and heavy-duty vehicles (HDVs) using a self-developed whole-vehicle testing system and a modified brake dynamometer. The results show that regenerative braking significantly reduces emissions: weak and strong regenerative braking modes reduce brake wear PM2.5 by 75 % and 87 %, and brake wear PM10 by 90 % and 95 %, respectively. HDVs with drum brakes produce lower emissions and higher PM2.5/PM10 ratios than those with disc brakes. A machine learning model (XGBoost) was developed to analyze the relationship between BWP emissions and factors (11 for light-duty EVs and 8 for HDVs, based on kinematic, vehicle, and braking parameters). SHapley Additive exPlanations (SHAP) were used for model interpretation. For light-duty EVs, reducing high kinetic energy losses (Ike > 6500 J) and initial speeds (V > 45 km/h) braking events significantly lowers emissions. Additionally, the emission reduction effect of regenerative braking intensity (BI) stabilizes when BI exceeds 900 J. For HDVs, controlling braking temperature (Avg.T < 200°C) and initial speed (V < 50 km/h) effectively reduces emissions. Our findings provide new insights into the emission characteristics and control strategies for BWPs. SYNOPSIS: The construction and interpretation of a machine learning based model of brake wear emissions provides new insights into the refined assessment and control of non-exhaust emissions.

Marigold: a machine learning-based web app for zebrafish pose tracking

BACKGROUND

High-throughput behavioral analysis is important for drug discovery, toxicological studies, and the modeling of neurological disorders such as autism and epilepsy. Zebrafish embryos and larvae are ideal for such applications because they are spawned in large clutches, develop rapidly, feature a relatively simple nervous system, and have orthologs to many human disease genes. However, existing software for video-based behavioral analysis can be incompatible with recordings that contain dynamic backgrounds or foreign objects, lack support for multiwell formats, require expensive hardware, and/or demand considerable programming expertise. Here, we introduce Marigold, a free and open source web app for high-throughput behavioral analysis of embryonic and larval zebrafish.

RESULTS

Marigold features an intuitive graphical user interface, tracks up to 10 user-defined keypoints, supports both single- and multiwell formats, and exports a range of kinematic parameters in addition to publication-quality data visualizations. By leveraging a highly efficient, custom-designed neural network architecture, Marigold achieves reasonable training and inference speeds even on modestly powered computers lacking a discrete graphics processing unit. Notably, as a web app, Marigold does not require any installation and runs within popular web browsers on ChromeOS, Linux, macOS, and Windows. To demonstrate Marigold's utility, we used two sets of biological experiments. First, we examined novel aspects of the touch-evoked escape response in techno trousers (tnt) mutant embryos, which contain a previously described loss-of-function mutation in the gene encoding Eaat2b, a glial glutamate transporter. We identified differences and interactions between touch location (head vs. tail) and genotype. Second, we investigated the effects of feeding on larval visuomotor behavior at 5 and 7 days post-fertilization (dpf). We found differences in the number and vigor of swimming bouts between fed and unfed fish at both time points, as well as interactions between developmental stage and feeding regimen.

CONCLUSIONS

In both biological experiments presented here, the use of Marigold facilitated novel behavioral findings. Marigold's ease of use, robust pose tracking, amenability to diverse experimental paradigms, and flexibility regarding hardware requirements make it a powerful tool for analyzing zebrafish behavior, especially in low-resource settings such as course-based undergraduate research experiences. Marigold is available at: https://downeslab.github.io/marigold/ .

Identification of WDR74 and TNFRSF12A as biomarkers for early osteoarthritis using machine learning and immunohistochemistry

Background

Osteoarthritis (OA) is a chronic joint condition that causes pain, limited mobility, and reduced quality of life, posing a threat to healthy aging. Early detection is crucial for improving prognosis. Recent research has focused on the role of ubiquitination-related genes (URGs) in early OA prediction. This study aims to integrate URG expression data with machine learning (ML) to identify biomarkers that improve diagnosis and prognosis in the early stages of OA.

Methods

OA single-cell RNA sequencing datasets were collected from the GEO database. Single-cell analysis was performed to investigate the composition and relationships of chondrocytes in OA. The potential intercellular communication mechanisms were explored using the CellChat R package. URGs were retrieved from GeneCards, and ubiquitination scores were calculated using the AUCell package. Gene module analysis based on co-expression network analysis was conducted to identify core genes. Additionally, ML analysis was performed to identify core URGs and construct a diagnostic model. We employed XGBoost, a gradient-boosting ML algorithm, to identify core URGs and construct a diagnostic model. The model's performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. In addition, we explored the relationship between core URGs and immune processes. The ChEA3 database was utilized to predict the transcription factors regulated by core ubiquitination-related genes. The expression of select URGs was validated using qRT-PCR and immunohistochemistry (IHC).

Results

We identified WDR74 and TNFRSF12A as pivotal ubiquitination-related genes associated with OA, exhibiting considerable differential expression. The diagnostic model constructed with URGs exhibited remarkable accuracy, with area under the curve (AUC) values consistently exceeding 0.9. The expression levels of WDR74 and TNFRSF12A were significantly higher in the IL-1β-induced group in an in vitro qPCR experiment. The IHC validation on human knee joint specimens confirmed the upregulation of WDR74 and TNFRSF12A in OA tissues, corroborating their potential as diagnostic biomarkers.

Conclusions

WDR74 and TNFRSF12A as principal biomarkers highlighted their attractiveness as therapeutic targets. The identification of core biomarkers might facilitate early intervention options, potentially modifying the illness trajectory and enhancing patient outcomes.

Establishing a preoperative predictive model for gallbladder adenoma and cholesterol polyps based on machine learning: a multicentre retrospective study

BACKGROUND

With the rising diagnostic rate of gallbladder polypoid lesions (GPLs), differentiating benign cholesterol polyps from gallbladder adenomas with a higher preoperative malignancy risk is crucial. This study aimed to establish a preoperative prediction model capable of accurately distinguishing between gallbladder adenomas and cholesterol polyps using machine learning algorithms.

MATERIALS AND METHODS

We retrospectively analysed the patients' clinical baseline data, serological indicators, and ultrasound imaging data. Using 12 machine learning algorithms, 110 combination predictive models were constructed. The models were evaluated using internal and external cohort validation, receiver operating characteristic curves, area under the curve (AUC) values, calibration curves, and clinical decision curves to determine the best predictive model.

RESULTS

Among the 110 combination predictive models, the Support Vector Machine + Random Forest (SVM + RF) model demonstrated the highest AUC values of 0.972 and 0.922 in the training and internal validation sets, respectively, indicating an optimal predictive performance. The model-selected features included gallbladder wall thickness, polyp size, polyp echo, and pedicle. Evaluation through external cohort validation, calibration curves, and clinical decision curves further confirmed its excellent predictive ability for distinguishing gallbladder adenomas from cholesterol polyps. Additionally, this study identified age, adenosine deaminase level, and metabolic syndrome as potential predictive factors for gallbladder adenomas.

CONCLUSION

This study employed the machine learning combination algorithms and preoperative ultrasound imaging data to construct an SVM + RF predictive model, enabling effective preoperative differentiation of gallbladder adenomas and cholesterol polyps. These findings will assist clinicians in accurately assessing the risk of GPLs and providing personalised treatment strategies.

Machine learning for synthetic gene circuit engineering

Synthetic biology leverages engineering principles to program biology with new functions for applications in medicine, energy, food, and the environment. A central aspect of synthetic biology is the creation of synthetic gene circuits - engineered biological circuits capable of performing operations, detecting signals, and regulating cellular functions. Their development involves large design spaces with intricate interactions among circuit components and the host cellular machinery. Here, we discuss the emerging role of machine learning in addressing these challenges. We articulate how machine learning may enhance synthetic gene circuit engineering, from individual components to circuit-level aspects, while highlighting associated challenges. We discuss potential hybrid approaches that combine machine learning with mechanistic modeling to leverage the advantages of data-driven models with the prescriptive ability of mechanism-based models. Machine learning and its integration with mechanistic modeling are poised to advance synthetic biology, but challenges need to be overcome for such efforts to realize their potential.

The clinical application of artificial intelligence in cancer precision treatment

BACKGROUND

Artificial intelligence has made significant contributions to oncology through the availability of high-dimensional datasets and advances in computing and deep learning. Cancer precision medicine aims to optimize therapeutic outcomes and reduce side effects for individual cancer patients. However, a comprehensive review describing the impact of artificial intelligence on cancer precision medicine is lacking.

OBSERVATIONS

By collecting and integrating large volumes of data and applying it to clinical tasks across various algorithms and models, artificial intelligence plays a significant role in cancer precision medicine. Here, we describe the general principles of artificial intelligence, including machine learning and deep learning. We further summarize the latest developments in artificial intelligence applications in cancer precision medicine. In tumor precision treatment, artificial intelligence plays a crucial role in individualizing both conventional and emerging therapies. In specific fields, including target prediction, targeted drug generation, immunotherapy response prediction, neoantigen prediction, and identification of long non-coding RNA, artificial intelligence offers promising perspectives. Finally, we outline the current challenges and ethical issues in the field.

CONCLUSIONS

Recent clinical studies demonstrate that artificial intelligence is involved in cancer precision medicine and has the potential to benefit cancer healthcare, particularly by optimizing conventional therapies, emerging targeted therapies, and individual immunotherapies. This review aims to provide valuable resources to clinicians and researchers and encourage further investigation in this field.

Simulation of adaptive immune receptors and repertoires with complex immune information to guide the development and benchmarking of AIRR machine learning

Machine learning (ML) has shown great potential in the adaptive immune receptor repertoire (AIRR) field. However, there is a lack of large-scale ground-truth experimental AIRR data suitable for AIRR-ML-based disease diagnostics and therapeutics discovery. Simulated ground-truth AIRR data are required to complement the development and benchmarking of robust and interpretable AIRR-ML methods where experimental data is currently inaccessible or insufficient. The challenge for simulated data to be useful is incorporating key features observed in experimental repertoires. These features, such as antigen or disease-associated immune information, cause AIRR-ML problems to be challenging. Here, we introduce LIgO, a software suite, which simulates AIRR data for the development and benchmarking of AIRR-ML methods. LIgO incorporates different types of immune information both on the receptor and the repertoire level and preserves native-like generation probability distribution. Additionally, LIgO assists users in determining the computational feasibility of their simulations. We show two examples where LIgO supports the development and validation of AIRR-ML methods: (i) how individuals carrying out-of-distribution immune information impacts receptor-level prediction performance and (ii) how immune information co-occurring in the same AIRs impacts the performance of conventional receptor-level encoding and repertoire-level classification approaches. LIgO guides the advancement and assessment of interpretable AIRR-ML methods.

Spatial deconvolution from bulk DNA methylation profiles determines intratumoral epigenetic heterogeneity

BACKGROUND

Intratumoral heterogeneity emerges from accumulating genetic and epigenetic changes during tumorigenesis, which may contribute to therapeutic failure and drug resistance. However, the lack of a quick and convenient approach to determine the intratumoral epigenetic heterogeneity (eITH) limit the application of eITH in clinical settings. Here, we aimed to develop a tool that can evaluate the eITH using the DNA methylation profiles from bulk tumors.

METHODS

Genomic DNA of three laser micro-dissected tumor regions, including digestive tract surface, central bulk, and invasive front, was extracted from formalin-fixed paraffin-embedded sections of colorectal cancer patients. The genome-wide methylation profiles were generated with methylation array. The most variable methylated probes were selected to construct a DNA methylation-based heterogeneity (MeHEG) estimation tool that can deconvolve the proportion of each reference tumor region with the support vector machine model-based method. A PCR-based assay for quantitative analysis of DNA methylation (QASM) was developed to specifically determine the methylation status of each CpG in MeHEG assay at single-base resolution to realize fast evaluation of epigenetic heterogeneity.

RESULTS

In the discovery set with 79 patients, the differentially methylated CpGs among the three tumor regions were found. The 7 most representative CpGs were identified and subsequently selected to develop the MeHEG algorithm. We validated its performance of deconvolution of tumor regions in an independent cohort. In addition, we showed the significant association of MeHEG-based epigenetic heterogeneity with the genomic heterogeneity in mutation and copy number variation in our in-house and TCGA cohorts. Besides, we found that the patients with higher MeHEG score had worse disease-free and overall survival outcomes. Finally, we found dynamic change of epigenetic heterogeneity based on MeHEG score in cancer cells under the treatment of therapeutic drugs.

CONCLUSION

By developing a 7-loci panel using a machine learning approach combined with the QASM assay for PCR-based application, we present a valuable method for evaluating intratumoral heterogeneity. The MeHEG algorithm offers novel insights into tumor heterogeneity from an epigenetic perspective, potentially enriching current knowledge of tumor complexity and providing a new tool for clinical and research applications in cancer biology.

Prognosis modelling of adverse events for post-PCI treated AMI patients based on inflammation and nutrition indexes

OBJECTIVE

This study aimed to evaluate the predictive performance of inflammatory and nutritional indices for adverse cardiovascular events (ACE) in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI) using a machine learning (ML) algorithm.

METHODS

AMI patients who underwent PCI were recruited and randomly divided into non/ACE groups. Inflammatory and nutritional indices were graded according to the laboratory examination reports. Logistic Regression was used to screen for factors that were significant for ML model establishment. The performances of the algorithms were evaluated in terms of accuracy, kappa, F1, receiver operating characteristic, precision recall curve, etc. RESULTS: Age, LVEF%, Killip Grade, heart rate, creatinine, albumin, neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), and prognostic nutritional index (PNI) were significantly correlated with ACE by Logistic regression analysis (P < 0.05). These nine factors were employed to establish stepwise regression (SR), random forest (RF), naïve Bayes (NB), decision trees (DT), and artificial neutron network (ANN), whose performances were evaluated in terms of accuracy, kappa, F1, receiver operating characteristic, precision recall curve, etc. The accuracy of the decision tree was greater than that of other trees. The area under the curves was the highest in the ANN model compared with the other models.

CONCLUSION

ANN predictive performance had an advantage over other ML algorithms based on age, LVEF%, Killip Grade, heart rate, creatinine, albumin, NLR, PLR, and PNI.

Artificial intelligence and machine learning in cell-free-DNA-based diagnostics

The discovery of circulating fetal and tumor cell-free DNA (cfDNA) molecules in plasma has opened up tremendous opportunities in noninvasive diagnostics such as the detection of fetal chromosomal aneuploidies and cancers and in posttransplantation monitoring. The advent of high-throughput sequencing technologies makes it possible to scrutinize the characteristics of cfDNA molecules, opening up the fields of cfDNA genetics, epigenetics, transcriptomics, and fragmentomics, providing a plethora of biomarkers. Machine learning (ML) and/or artificial intelligence (AI) technologies that are known for their ability to integrate high-dimensional features have recently been applied to the field of liquid biopsy. In this review, we highlight various AI and ML approaches in cfDNA-based diagnostics. We first introduce the biology of cell-free DNA and basic concepts of ML and AI technologies. We then discuss selected examples of ML- or AI-based applications in noninvasive prenatal testing and cancer liquid biopsy. These applications include the deduction of fetal DNA fraction, plasma DNA tissue mapping, and cancer detection and localization. Finally, we offer perspectives on the future direction of using ML and AI technologies to leverage cfDNA fragmentation patterns in terms of methylomic and transcriptional investigations.

Development and validation of a machine learning-based prediction model for hepatorenal syndrome in liver cirrhosis patients using MIMIC-IV and eICU databases

Hepatorenal syndrome (HRS) is a key contributor to poor prognosis in liver cirrhosis. This study aims to leverage the database to build a predictive model for early identification of high-risk patients. From two sizable public databases, we retrieved pertinent information about the cirrhosis patients' therapies, comorbidities, laboratory results, and demographics. Patients from the eICU database served as a test set for external validation, while patients from the MIMIC database were divided into training and validation groups. Variables were screened using LASSO regression, Extreme Gradient Boosting (XG Boost), and Random Forest (RF). Core risk factors were determined from the intersection of the three methods. A predictive model was constructed using multivariable logistic regression and visualized via a nomogram. Model performance was assessed using ROC curves, decision curve analysis (DCA), clinical impact curves (CIC), and calibration curves. Eight critical variables associated with HRS were identified using machine learning methods. The final predictive model, based on five key variables-spontaneous bacterial peritonitis, red blood cell count, creatinine, activated partial thromboplastin time, and total bilirubin-showed excellent discrimination, with AUCs of 0.832 (95% CI 0.8069-0.8563) in the training set and 0.8415 (95% CI 0.8042-0.8789) in the validation set. The AUC in the external test set was 0.8212 (95% CI 0.7784-0.864). By integrating the MIMIC-IV database and machine learning algorithms, we developed an effective predictive model for HRS in liver cirrhosis patients, providing a robust tool for early clinical intervention.

Closing the loop: establishing an autonomous test-learn cycle to optimize induction of bacterial systems using a robotic platform

One goal of synthetic biology is to provide well-characterised biological parts that behave predictably in genetic assemblies. To achieve this, each part must be characterised in a time-resolved manner under relevant conditions. Robotic platforms can be used to automate this task and provide sufficiently large and reproducible data sets including provenance. Although robotics can significantly speed up the data collection process, the collation and analysis of the resulting data, needed to reprogram and refine workflows for future iterations, is often a manual process. As a result, even in times of rapidly advancing artificial intelligence, the common design-build-test-learn (DBTL) cycle is still not circular without human intervention. To move towards fully automated DBTL cycles, we developed a software framework to enable a robotic platform to autonomously adjust test parameters. This interdisciplinary work between computer science and biology thus transforms a static robotic platform into a dynamic one. The software framework includes software components such as an importer that retrieves measurement data from the platform's devices and writes it to a database. This is followed by an optimizer that selects the next measurement points based on a balance between exploration and exploitation. The platform is shown to be able to automatically and autonomously optimize the inducer concentration for a Bacillus subtilis system and the combination of inducer and feed release for a Escherichia coli system. As a target product the readily measurable green fluorescent reporter protein (GFP) is produced over multiple, consecutive iterations of testing. An evaluation of chosen (learning) algorithms for single and dual factor optimization was performed. In this article, we share the lessons learned from the development, implementation and execution of this automated design-build-test-learn cycles on a robotic platform.

Construction of exosome non-coding RNA feature for non-invasive, early detection of gastric cancer patients by machine learning: a multi-cohort study

BACKGROUND AND OBJECTIVE

Gastric cancer (GC) remains a prevalent and preventable disease, yet accurate early diagnostic methods are lacking. Exosome non-coding RNAs (ncRNAs), a type of liquid biopsy, have emerged as promising diagnostic biomarkers for various tumours. This study aimed to identify a serum exosome ncRNA feature for enhancing GC diagnosis.

DESIGNS

Serum exosomes from patients with GC (n=37) and healthy donors (n=20) were characterised using RNA sequencing, and potential biomarkers for GC were validated through quantitative reverse transcription PCR (qRT-PCR) in both serum exosomes and tissues. A combined diagnostic model was developed using LASSO-logistic regression based on a cohort of 518 GC patients and 460 healthy donors, and its diagnostic performance was evaluated via receiver operating characteristic curves.

RESULTS

RNA sequencing identified 182 candidate biomarkers for GC, of which 31 were validated as potential biomarkers by qRT-PCR. The combined diagnostic score (cd-score), derived from the expression levels of four long ncRNAs (RP11.443C10.1, CTD-2339L15.3, LINC00567 and DiGeorge syndrome critical region gene (DGCR9)), was found to surpass commonly used biomarkers, such as carcinoembryonic antigen, carbohydrate antigen 19-9 (CA19-9) and CA72-4, in distinguishing GC patients from healthy donors across training, testing and external validation cohorts, with AUC values of 0.959, 0.942 and 0.949, respectively. Additionally, the cd-score could effectively identify GC patients with negative gastrointestinal tumour biomarkers and those in early-stage. Furthermore, molecular biological assays revealed that knockdown of DGCR9 inhibited GC tumour growth.

CONCLUSIONS

Our proposed serum exosome ncRNA feature provides a promising liquid biopsy approach for enhancing the early diagnosis of GC.

Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199

BACKGROUND

Immunotherapy and radiotherapy play crucial roles in the transformation therapy of locally advanced pancreatic cancer; however, the exploration of effective predictive biomarkers has been unsatisfactory. With the rapid development of radiomics, next-generation sequencing, and machine learning, there is hope to identify biomarkers that can predict the efficacy of transformative treatment for locally advanced pancreatic cancer through simple and non-invasive clinical methods. Our study focuses on using computed tomography (CT), positron emission tomography/computed tomography (PET/CT), gene mutations, and baseline carbohydrate antigen 199 (CA199) to identify biomarkers for predicting the efficacy of transformative treatment.

METHODS

We retrospectively collected data from 70 patients with locally advanced pancreatic cancer who had undergone a biopsy for pathological diagnosis. These patients had complete baseline enhanced CT images and baseline CA199 results. Among them, 65 patients had efficacy evaluation results after 4 treatment cycles, 54 patients had complete baseline PET/CT images, 51 patients had complete DNA mutation detection results, and 34 patients had both complete PET/CT images and DNA mutation detection results. Additionally, 47 patients had complete available CT images at baseline, after 2 treatment cycles, and after 4 treatment cycles. We extracted radiomic features from the original lesion-enhanced CT images (including baseline and subsequent follow-up CT scans), radiomic features from baseline 18F-fluoro-2-deoxy-2-D-glucose (18F-FDG) PET, and patient-specific features related to abdominal and visceral fat. We used short-term and long-term treatment efficacy as the prediction outcomes and performed statistical and machine learning-based feature selection and COX regression analysis to identify potentially predictive features. Subsequently, we separately or in combination modeled the CT features, PET features, baseline CA199, and gene mutation data to construct efficacy prediction models. Finally, we investigated the mixed effects model of the dynamic changes in CT features at baseline, after 2 treatment cycles, and after 4 treatment cycles on the prediction of short-term treatment efficacy.

RESULTS

We found that a combination of CT radiomic features, including F1_ gray level co-occurrence matrix (GLCM), F2_gray level run length matrix (GLRLM), F5_neighboring gray tone difference matrix (NGTDM), and F6_Shape, PET radiomic features such as visceral adipose tissue (VAT), tumor-to-liver ratio (T/L), standardized uptake value mean (SUVmean), and GLCM, as well as baseline CA199, can be used to predict short-term treatment efficacy. Baseline CA199, GLCM, IntensityDirect, Shape, and PET/CT features are independent factors for long-term treatment efficacy. In constructing the short-term treatment efficacy prediction model, ensemble learning methods such as adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and RandomForest performed the best. However, in terms of model interpretability, decision tree methods provide the most intuitive display of the predictive details of the model. For the time series data of patients' baseline CT, CT after 2 treatment cycles, and CT after 4 treatment cycles, long short-term memory (LSTM) modeling yielded better predictive models.

CONCLUSION

A multimodal combination of radiomics, DNA mutations, and baseline CA199 can predict the efficacy of transformative treatment in locally advanced pancreatic cancer. Various feature selection methods and multimodal fusion approaches contribute to guiding personalized and precise treatment for pancreatic cancer.

Metallomic Classification of Pulmonary Nodules Using Blood by Deep-Learning-Boosted Synchrotron Radiation X-ray Fluorescence

Ambient air pollution is an important contributor to increasing cases of lung cancer, which is a malignant cancer with the highest mortality among all cancers. It primarily manifests in the form of pulmonary nodules, but not all will develop into lung cancer. Therefore, it is highly desired to distinguish between benign and malignant pulmonary nodules for the early prevention and treatment of lung cancer. Currently, histopathological examination is the gold standard for classifying pulmonary nodules, which is invasive, time-consuming, and labor-intensive. This study proposes a metallomics approach through synchrotron radiation X-ray fluorescence (SRXRF) with a simplified one-dimensional convolutional neural network (1DCNN) to distinguish pulmonary nodules by using serum samples. SRXRF spectra of serum samples were obtained and preliminarily analyzed using principal component analysis (PCA). Subsequently, machine learning algorithms (MLs) and 1DCNN were applied to develop classification models. Both MLs and 1DCNN based on full-channel spectra could distinguish patients with benign and malignant pulmonary nodules, but the highest accuracy rate of 96.7% was achieved when using 1DCNN. In addition, it was found that characteristic elements in serum from patients with malignant nodules were different from those in benign nodules, which can serve as the fingerprint metallome profile. The simplified model based on characteristic elements resulted in good performance of sensitivity and F1-score > 91.30%, G-mean, MCC and Kappa > 85.59%, and accuracy = 94.34%. In summary, metallomic classification of benign and malignant pulmonary nodules using serum samples can be achieved through 1DCNN-boosted SRXRF, which is easy to handle and much less invasive compared to histopathological examination.

Cellular Senescence in Hepatocellular Carcinoma: Immune Microenvironment Insights via Machine Learning and In Vitro Experiments

Hepatocellular carcinoma (HCC), a leading liver tumor globally, is influenced by diverse risk factors. Cellular senescence, marked by permanent cell cycle arrest, plays a crucial role in cancer biology, but its markers and roles in the HCC immune microenvironment remain unclear. Three machine learning methods, namely k nearest neighbor (KNN), support vector machine (SVM), and random forest (RF), are utilized to identify eight key HCC cell senescence markers (HCC-CSMs). Consensus clustering revealed molecular subtypes. The single-cell analysis explored the tumor microenvironment, immune checkpoints, and immunotherapy responses. In vitro, RNA interference mediated BIRC5 knockdown, and co-culture experiments assessed its impact. Cellular senescence-related genes predicted HCC survival information better than differential expression genes (DEGs). Eight key HCC-CSMs were identified, which revealed two distinct clusters with different clinical characteristics and mutation patterns. By single-cell RNA-seq data, we investigated the immunological microenvironment and observed that increasing immune cells allow hepatocytes to regain population dominance. This phenomenon may be associated with the HCC-CSMs identified in our study. By combining bulk RNA sequencing and single-cell RNA sequencing data, we identified the key gene BIRC5 and the natural killer (NK) cells that express BIRC5 at the highest levels. BIRC5 knockdown increased NK cell proliferation but reduced function, potentially aiding tumor survival. These findings provide insights into senescence-driven HCC progression and potential therapeutic targets.

Automatic etiological classification of stroke thrombus digital photographs using a deep learning model

Background

Etiological classification of ischemic stroke is fundamental for secondary prevention, but frequently results in undetermined cause. We aimed to develop a Deep Learning (DL)-based model for automatic etiological classification of ischemic stroke using digital images of thrombi retrieved by mechanical thrombectomy.

Methods

Patients with large vessel occlusion stroke subjected to mechanical thrombectomy between April 2016 and January 2023 at La Fe University and Polytechnic Hospital in Valencia were included. Thrombus digital images were obtained and clinical characteristics, including TOAST etiological classification as reference standard, were retrieved. Statistical analysis was performed to compare clinical characteristics between atherothrombotic and cardioembolic strokes. A DL method was designed based on two deep neural networks for: (1) image segmentation and (2) image classification including clinical characteristics. The metrics used were DICE coefficient for the segmentation network, and accuracy, precision, sensitivity, specificity and area under the curve (AUC) for the predictions of the classification network.

Results

A total of 166 patients (mean age 69 [SD, 13], 67 female) were included. TOAST classification was: 31 atherothrombotic, 87 cardioembolic, and 48 cryptogenic. The segmentation network achieved an average DICE coefficient of 0.96 [SD, 0.13]. The optimal fused imaging and clinical classification network had a 0.968 accuracy [95% CI, 0.935-0.994], and AUC of 0.947 [95% CI, 0.870-1]. Cryptogenic thrombi were classified as cardioembolic (96%) or atherothrombotic (4%).

Conclusion

Two convolutional neural networks perform the automatic segmentation of thrombus images and, combined with selected clinical characteristics, their accurate and precise classification into atherothrombotic or cardioembolic etiology in patients with acute ischemic stroke.

Development and validation of an interpretable machine learning model for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients

PURPOSE

Left atrial thrombus or spontaneous echo contrast (LAT/SEC) are widely recognized as significant contributors to cardiogenic embolism in non-valvular atrial fibrillation (NVAF). This study aimed to construct and validate an interpretable predictive model of LAT/SEC risk in NVAF patients using machine learning (ML) methods.

METHODS

Electronic medical records (EMR) data of consecutive NVAF patients scheduled for catheter ablation at the First Hospital of Jilin University from October 1, 2022, to February 1, 2024, were analyzed. A retrospective study of 1,222 NVAF patients was conducted. Nine ML algorithms combined with demographic, clinical, and laboratory data were applied to develop prediction models for LAT/SEC in NVAF patients. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression. Multiple ML classification models were integrated to identify the optimal model, and Shapley Additive exPlanations (SHAP) interpretation was utilized for personalized risk assessment. Diagnostic performances of the optimal model and the CHA2DS2-VASc scoring system for predicting LAT/SEC risk in NVAF were compared.

RESULTS

Among 1,078 patients included, the incidence of LAT/SEC was 10.02%. Six independent predictors, including age, non-paroxysmal AF, diabetes, ischemic stroke or thromboembolism (IS/TE), hyperuricemia, and left atrial diameter (LAD), were identified as the most valuable features. The logistic classification model exhibited the best performance with an area under the receiver operating characteristic curve (AUC) of 0.850, accuracy of 0.812, sensitivity of 0.818, and specificity of 0.780 in the test set. SHAP analysis revealed the contribution of explanatory variables to the model and their relationship with LAT/SEC occurrence. The logistic regression model significantly outperformed the CHA2DS2-VASc scoring system, with AUCs of 0.831 and 0.650, respectively (Z = 7.175, P < 0.001).

CONCLUSIONS

ML proves to be a reliable tool for predicting LAT/SEC risk in NVAF patients. The constructed logistic regression model, along with SHAP interpretation, may serve as a clinically useful tool for identifying high-risk NVAF patients. This enables targeted diagnostic evaluations and the development of personalized treatment strategies based on the findings.

MDFGNN-SMMA: prediction of potential small molecule-miRNA associations based on multi-source data fusion and graph neural networks

BACKGROUND

MicroRNAs (miRNAs) are pivotal in the initiation and progression of complex human diseases and have been identified as targets for small molecule (SM) drugs. However, the expensive and time-intensive characteristics of conventional experimental techniques for identifying SM-miRNA associations highlight the necessity for efficient computational methodologies in this field.

RESULTS

In this study, we proposed a deep learning method called Multi-source Data Fusion and Graph Neural Networks for Small Molecule-MiRNA Association (MDFGNN-SMMA) to predict potential SM-miRNA associations. Firstly, MDFGNN-SMMA extracted features of Atom Pairs fingerprints and Molecular ACCess System fingerprints to derive fusion feature vectors for small molecules (SMs). The K-mer features were employed to generate the initial feature vectors for miRNAs. Secondly, cosine similarity measures were computed to construct the adjacency matrices for SMs and miRNAs, respectively. Thirdly, these feature vectors and adjacency matrices were input into a model comprising GAT and GraphSAGE, which were utilized to generate the final feature vectors for SMs and miRNAs. Finally, the averaged final feature vectors were utilized as input for a multilayer perceptron to predict the associations between SMs and miRNAs.

CONCLUSIONS

The performance of MDFGNN-SMMA was assessed using 10-fold cross-validation, demonstrating superior compared to the four state-of-the-art models in terms of both AUC and AUPR. Moreover, the experimental results of an independent test set confirmed the model's generalization capability. Additionally, the efficacy of MDFGNN-SMMA was substantiated through three case studies. The findings indicated that among the top 50 predicted miRNAs associated with Cisplatin, 5-Fluorouracil, and Doxorubicin, 42, 36, and 36 miRNAs, respectively, were corroborated by existing literature and the RNAInter database.

A prediction study on the occurrence risk of heart disease in older hypertensive patients based on machine learning

OBJECTIVE

Constructing a predictive model for the occurrence of heart disease in elderly hypertensive individuals, aiming to provide early risk identification.

METHODS

A total of 934 participants aged 60 and above from the China Health and Retirement Longitudinal Study with a 7-year follow-up (2011-2018) were included. Machine learning methods (logistic regression, XGBoost, DNN) were employed to build a model predicting heart disease risk in hypertensive patients. Model performance was comprehensively assessed using discrimination, calibration, and clinical decision curves.

RESULTS

After a 7-year follow-up of 934 older hypertensive patients, 243 individuals (26.03%) developed heart disease. Older hypertensive patients with baseline comorbid dyslipidemia, chronic pulmonary diseases, arthritis or rheumatic diseases faced a higher risk of future heart disease. Feature selection significantly improved predictive performance compared to the original variable set. The ROC-AUC for logistic regression, XGBoost, and DNN were 0.60 (95% CI: 0.53-0.68), 0.64 (95% CI: 0.57-0.71), and 0.67 (95% CI: 0.60-0.73), respectively, with logistic regression achieving optimal calibration. XGBoost demonstrated the most noticeable clinical benefit as the threshold increased.

CONCLUSION

Machine learning effectively identifies the risk of heart disease in older hypertensive patients based on data from the CHARLS cohort. The results suggest that older hypertensive patients with comorbid dyslipidemia, chronic pulmonary diseases, and arthritis or rheumatic diseases have a higher risk of developing heart disease. This information could facilitate early risk identification for future heart disease in older hypertensive patients.

Development and Validation of a Diagnostic Model for Stanford Type B Aortic Dissection Based on Proteomic Profiling

Purpose

Stanford Type B Aortic Dissection (TBAD), a critical aortic disease, has exhibited stable mortality rates over the past decade. However, diagnostic approaches for TBAD during routine health check-ups are currently lacking. This study focused on developing a model to improve the diagnosis in a population.

Patients and Methods

Serum biomarkers were investigated in 88 participants using proteomic profiling combined with machine learning. The findings were validated using ELISA in other 80 participants. Subsequently, a diagnostic model for TBAD integrating biomarkers with clinical indicators was developed and assessed using machine learning.

Results

Six differentially expressed proteins (DEPs) were identified through proteomic profiling and machine learning in discovery and derivation cohorts. Five of these (GDF-15, IL6, CD58, LY9, and Siglec-7) were further verified through ELISA validation within the validation cohort. In addition, ten blood-related indicators were selected as clinical indicators. Combining biomarkers and clinical indicators, the machine learning-based models performed well (AUC of the biomarker model = 0.865, AUC of the clinical model = 0.904, and AUC of the combined model = 0.909) using relative quantitation. The performance of the three models was verified (AUC of biomarker model = 0.866, AUC of clinical model = 0.868, and AUC of combined model = 0.886) using absolute quantitation. Crucially, the combined models outperformed individual biomarkers and clinical models, demonstrating superior efficacy.

Conclusion

Using proteomic profiling, we identified serum IL-6, GDF-15, CD58, LY9, and Siglec-7 as TBAD biomarkers. The machine-learning-based diagnostic model exhibited significant potential for TBAD diagnosis using only blood samples within the population.

Demystifying the black box: A survey on explainable artificial intelligence (XAI) in bioinformatics

The widespread adoption of Artificial Intelligence (AI) and machine learning (ML) tools across various domains has showcased their remarkable capabilities and performance. Black-box AI models raise concerns about decision transparency and user confidence. Therefore, explainable AI (XAI) and explainability techniques have rapidly emerged in recent years. This paper aims to review existing works on explainability techniques in bioinformatics, with a particular focus on omics and imaging. We seek to analyze the growing demand for XAI in bioinformatics, identify current XAI approaches, and highlight their limitations. Our survey emphasizes the specific needs of both bioinformatics applications and users when developing XAI methods and we particularly focus on omics and imaging data. Our analysis reveals a significant demand for XAI in bioinformatics, driven by the need for transparency and user confidence in decision-making processes. At the end of the survey, we provided practical guidelines for system developers.

Combining machine learning and single-cell sequencing to identify key immune genes in sepsis

This research aimed to identify novel indicators for sepsis by analyzing RNA sequencing data from peripheral blood samples obtained from sepsis patients (n = 23) and healthy controls (n = 10). 5148 differentially expressed genes were identified using the DESeq2 technique and 5636 differentially expressed genes were identified by the limma method(|Log2 Fold Change|≥2, FDR < 0.05). A total of 1793 immune-related genes were identified from the ImmPort database, with 358 genes identified in both groups. Next, a Biological association network was constructed, and five key hub genes (CD4, HLA-DOB, HLA-DRB1, HLA-DRA, AHNAK) were identified using a combination of three topological analysis algorithms (MCC, Closeness, and MNC) and four machine learning algorithms (Random Forest, LASSO regression, SVM, and XGBoost). immune cell distribution showed that the key genes correlated with multiple immune cell infiltrations. Gene Set Enrichment Analysis (GSEA) revealed that the key genes involved multiple immune response and inflammation-related signaling pathways. Subsequently, diagnostic models were constructed using four machine learning algorithms (Logistic regression, AdaBoost, KNN, and XGBoost) based on the identified key genes. Models with the highest performance were then selected. Ultimately, single-cell sequencing data revealed that the identified key genes were expressed in various immune cells, while Quantitative PCR (qPCR) tests confirmed their reduced expression in the sepsis group.

Using XBGoost, an interpretable machine learning model, for diagnosing prostate cancer in patients with PSA < 20 ng/ml based on the PSAMR indicator

To create a diagnostic tool before biopsy for patients with prostate-specific antigen (PSA) levels < 20 ng/ml to minimize prostate biopsy-related discomfort and risks. Data from 655 patients who underwent transperineal prostate biopsy at the First Affiliated Hospital of Wannan Medical College from July 2021 to January 2023 were collected and analyzed. After applying the Synthetic Minority Over-sampling TEchnique class balancing on the training set, multiple machine learning models were constructed by using the Least Absolute Shrinkage and Selection Operator (LASSO) feature selection to identify the significant variables. The best-performing model was selected and evaluated through tenfold cross-validation to ensure interpretability. Finally, the performance was assessed using the test set data for validation. The age, prostate-specific antigen mass ratio (PSAMR), Prostate Imaging-Reporting and Data System, and prostate volume were selected as the variables for model construction based on the LASSO regression. The receiver operating characteristic (ROC) results for multiple models in the validation set were as follows: XGBoost: 0.93 (0.88-0.97); logistic: 0.89 (0.83-0.95); LightGBM: 0.87 (0.80-0.93); AdaBoost: 0.90 (0.85-0.96); GNB: 0.88 (0.82-0.95); CNB: 0.79 (0.71-0.87); MLP: 0.78 (0.69-0.86); and Support Vector Machine: 0.81 (0.73-0.89). XGBoost was selected as the best model and reconstructed with tenfold cross-validation on the training data, resulting in the following ROC scores: training set 0.995 (0.991-0.999), validation set 0.945 (0.885-0.997 ), and test set 0.920 (0.868-0.972). The Kolmogorov-Smirnov curve, calibration curve and learning curve yielded positive results; The decision curve demonstrates that patients with threshold probabilities ranging from 10 to 95% can benefit from this model. We developed an XGBoost machine learning model based on the PSAMR indicator and interpreted it using the SHapley Additive exPlanations method. The model offered a high-performance non-invasive technique to diagnose prostate cancer in patients with PSA levels < 20 ng/ml.