Machine learning applications in cancer prognosis and prediction

Optimizing cardiovascular disease mortality prediction: a super learner approach in the tehran lipid and glucose study

BACKGROUND & AIM

Cardiovascular disease (CVD) is the most important cause of death in the world and has a potential impact on health care costs, this study aimed to evaluate the performance of machine learning survival models and determine the optimum model for predicting CVD-related mortality.

METHOD

In this study, the research population was all participants in Tehran Lipid and Glucose Study (TLGS) aged over 30 years. We used the Gradient Boosting model (GBM), Support Vector Machine (SVM), Super Learner (SL), and Cox proportional hazard (Cox-PH) models to predict the CVD-related mortality using 26 features. The dataset was randomly divided into training (80%) and testing (20%). To evaluate the performance of the methods, we used the Brier Score (BS), Prediction Error (PE), Concordance Index (C-index), and time-dependent Area Under the Curve (TD-AUC) criteria. Four different clinical models were also performed to improve the performance of the methods.

RESULTS

Out of 9258 participants with a mean age of (SD; range) 43.74 (15.51; 20-91), 56.60% were female. The CVD death proportion was 2.5% (228 participants). The death proportion was significantly higher in men (67.98% M, 32.02% F). Based on predefined selection criteria, the SL method has the best performance in predicting CVD-related mortality (TD-AUC > 93.50%). Among the machine learning (ML) methods, The SVM has the worst performance (TD-AUC = 90.13%). According to the relative effect, age, fasting blood sugar, systolic blood pressure, smoking, taking aspirin, diastolic blood pressure, Type 2 diabetes mellitus, hip circumference, body mss index (BMI), and triglyceride were identified as the most influential variables in predicting CVD-related mortality.

CONCLUSION

According to the results of our study, compared to the Cox-PH model, Machine Learning models showed promising and sometimes better performance in predicting CVD-related mortality. This finding is based on the analysis of a large and diverse urban population from Tehran, Iran.

Application of machine learning for lung cancer survival prognostication-A systematic review and meta-analysis

Introduction

Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer.

Methods

We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models.

Results

The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models.

Conclusion

Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.

Laboratory blood parameters and machine learning for the prognosis of esophageal squamous cell carcinoma

Background

In contemporary study, the death of esophageal squamous cell carcinoma (ESCC) patients need precise and expedient prognostic methodologies.

Objective

To develop and validate a prognostic model tailored to ESCC patients, leveraging the power of machine learning (ML) techniques and drawing insights from comprehensive datasets of laboratory-derived blood parameters.

Methods

Three ML approaches, including Gradient Boosting Machine (GBM), Random Survival Forest (RSF), and the classical Cox method, were employed to develop models on a dataset of 2521 ESCC patients with 27 features. The models were evaluated by concordance index (C-index) and time receiver operating characteristics (Time ROC) curves. We used the optimal model to evaluate the correlation between features and prognosis and divide patients into low- and high-risk groups by risk stratification. Its performance was analyzed by Kaplan-Meier curve and the comparison with AJCC8 stage. We further evaluate the comprehensive effectiveness of the model in ESCC subgroup by risk score and KDE (kernel density estimation) plotting.

Results

RSF's C-index (0.746) and AUC (three-year AUC 0.761, five-year AUC 0.771) had slight advantage over GBM and the classical Cox method. Subsequently, 14 features such as N stage, T stage, surgical margin, tumor length, age, Dissected LN number, MCH, Na, FIB, DBIL, CL, treatment, vascular invasion, and tumor grade were selected to build the model. Based on these, we found significant difference for survival rate between low-(3-year OS 81.8%, 5-year OS 69.8%) and high-risk (3-year OS 25.1%, 5-year OS 11.5%) patients in training set, which was also verified in test set (all P < 0.0001). Compared with the AJCC8th stage system, it showed a greater discriminative ability which is also in good agreement with its staging ability.

Conclusion

We developed an ESCC prognostic model with good performance by clinical features and laboratory blood parameters.

Feasibility, accuracy, and usability analysis of MapAML, a first-in-class app for integrated diagnosis in acute myeloid leukemia

Performing a comprehensive diagnosis of acute myeloid leukemia (AML) is complex and involves the integration of clinical information, bone marrow morphology, immunophenotyping, cytogenetic, and molecular analysis, which can be challenging to the general hematologist. The aim of this study was to evaluate the usability and accuracy of MapAML, a smartphone app for integrated diagnosis in AML, created to aid the hematologist in its clinical practice. App performance was evaluated in dedicated sessions, in which 21 hematologists or fellows in hematology performed an integrated diagnosis of deidentified real-world clinical AML cases, first without and posteriorly with MapAML use. Diagnosis accuracy increased after MapAML utilization, with the average score going from 7.08 without app to 8.88 with app use (on a scale from 0 to 10), representing a significant accuracy improvement (p = .002). Usability evaluation was very favorable, with 81% of users considering the app very or extremely simple to use. There was also a significant increase in confidence to perform a complete and accurate diagnosis in AML after app use, with 61.9% of the participants willing to use the app in their clinical practice. In this study, MapAML increased accuracy with excellent usability for integrated diagnosis in AML.

A novel mitochondria-related core gene signature to predict the prognosis and evaluate tumour microenvironment in CESC single-cell validation

Mitochondria and their related genes (MTRGs) are pivotal in the tumour microenvironment (TME) of cervical cancer, influencing prognosis and treatment response. This study developed a prognostic model using MTRGs to predict overall survival (OS) in cervical squamous cell carcinoma and endocervical adenocarcinoma (CESC), aiming for personalized therapy. Analysing 14 MTRGs like ISCU and NDUFA11 through techniques such as univariate Cox regression, we found that a low mitochondrial (MT) score is associated with better survival, while a high MT score predicts poorer outcomes. The TME score, particularly influenced by CD8 T cells, also correlates with prognosis, with a high score indicating favourable outcomes. The interplay between MT and TME subtypes revealed that the best prognosis is seen in patients with a low MT and high TME score. Our findings highlight the role of MTRGs as potential biomarkers and therapeutic targets in cervical cancer, offering a novel approach to improving patient outcomes through a more nuanced understanding of mitochondrial function and immune interactions within the TME. This model presents a promising avenue for enhancing the precision of prognostic assessments in CESC.

Unveiling the best predictive models for early‑onset metastatic cancer: Insights and innovations (Review)

Cancer metastasis is the primary cause of cancer deaths. Metastasis involves the spread of cancer cells from the primary tumors to other body parts, commonly through lymphatic and vascular pathways. Key aspects include the high mutation rate and the capability of metastatic cells to form invasive tumors even without a large initial tumor mass. Particular emphasis is given to early metastasis, occurring in initial cancer stages and often leading to misdiagnosis, which adversely affects survival and prognosis. The present review highlighted the need for improved understanding and detection methods for early metastasis, which has not been effectively identified clinically. The present review demonstrated the clinicopathological and molecular characteristics of early‑onset metastatic types of cancer, noting factors such as age, race, tumor size and location as well as the histological and pathological grade as significant predictors. In conclusion, the present review underscored the importance of early detection and management of metastatic types of cancer and called for improved predictive models, including advanced techniques such as nomograms and machine learning, so as to enhance patient outcomes, acknowledging the challenges and limitations of the current research as well as the necessity for further studies.

Comparison of machine learning algorithms for the classification of spinal cord tumor

Spinal cord Tumor has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into Bening or malignant has led many re- search teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, Logistic regression, Support Vector Machines (SVMs), Decision Trees (DTs), Random forest classifier(RFs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we have discussed a predictive model based on various supervised ML techniques.

A comprehensive review of dose limits, triage systems and measurement tools for consequence management of nuclear and radiological emergencies

During a radiological or nuclear emergency, occupational workers, members of the public, and emergency responders may be exposed to radionuclides, whether external or internal, through inhalation, ingestion, or wounds. In the case of internalized radiation exposure, prompt assessment of contamination is necessary to inform subsequent medical interventions. This review assembles the constituent considerations for managing nuclear and radiological incidents, focused on a parallel analysis of the evolution of radiation dose limits - notably in the emergency preparedness and response realm - alongside a discussion of triage systems and in vivo radionuclide detection tools. The review maps the development of international and national standards and regulations concerning radiation dose limits, illuminating how past incidents and accumulated knowledge have informed present emergency preparedness and response practices, specifically for internalized radiation. Additionally, the objectives and levels of radiation triage systems are explored in-depth, along with a global survey of practices and protocols. Finally, this review also focuses on in vivo detection systems and their capacities for radionuclide identification, prioritizing internalized gamma-emitting isotopes due to their broader relevance. Collectively, this study comprehensively addresses the intricacies of triage management following radiation emergencies, emphasizing the imperative for enhanced standardization and continued research in this critical domain.

A super SDM (species distribution model) 'in the cloud' for better habitat-association inference with a 'big data' application of the Great Gray Owl for Alaska

The currently available distribution and range maps for the Great Grey Owl (GGOW; Strix nebulosa) are ambiguous, contradictory, imprecise, outdated, often hand-drawn and thus not quantified, not based on data or scientific. In this study, we present a proof of concept with a biological application for technical and biological workflow progress on latest global open access 'Big Data' sharing, Open-source methods of R and geographic information systems (OGIS and QGIS) assessed with six recent multi-evidence citizen-science sightings of the GGOW. This proposed workflow can be applied for quantified inference for any species-habitat model such as typically applied with species distribution models (SDMs). Using Random Forest-an ensemble-type model of Machine Learning following Leo Breiman's approach of inference from predictions-we present a Super SDM for GGOWs in Alaska running on Oracle Cloud Infrastructure (OCI). These Super SDMs were based on best publicly available data (410 occurrences + 1% new assessment sightings) and over 100 environmental GIS habitat predictors ('Big Data'). The compiled global open access data and the associated workflow overcome for the first time the limitations of traditionally used PC and laptops. It breaks new ground and has real-world implications for conservation and land management for GGOW, for Alaska, and for other species worldwide as a 'new' baseline. As this research field remains dynamic, Super SDMs can have limits, are not the ultimate and final statement on species-habitat associations yet, but they summarize all publicly available data and information on a topic in a quantified and testable fashion allowing fine-tuning and improvements as needed. At minimum, they allow for low-cost rapid assessment and a great leap forward to be more ecological and inclusive of all information at-hand. Using GGOWs, here we aim to correct the perception of this species towards a more inclusive, holistic, and scientifically correct assessment of this urban-adapted owl in the Anthropocene, rather than a mysterious wilderness-inhabiting species (aka 'Phantom of the North'). Such a Super SDM was never created for any bird species before and opens new perspectives for impact assessment policy and global sustainability.

Enhancement of Classifier Performance with Adam and RanAdam Hyper-Parameter Tuning for Lung Cancer Detection from Microarray Data-In Pursuit of Precision

Microarray gene expression analysis is a powerful technique used in cancer classification and research to identify and understand gene expression patterns that can differentiate between different cancer types, subtypes, and stages. However, microarray databases are highly redundant, inherently nonlinear, and noisy. Therefore, extracting meaningful information from such a huge database is a challenging one. The paper adopts the Fast Fourier Transform (FFT) and Mixture Model (MM) for dimensionality reduction and utilises the Dragonfly optimisation algorithm as the feature selection technique. The classifiers employed in this research are Nonlinear Regression, Naïve Bayes, Decision Tree, Random Forest and SVM (RBF). The classifiers' performances are analysed with and without feature selection methods. Finally, Adaptive Moment Estimation (Adam) and Random Adaptive Moment Estimation (RanAdam) hyper-parameter tuning techniques are used as improvisation techniques for classifiers. The SVM (RBF) classifier with the Fast Fourier Transform Dimensionality Reduction method and Dragonfly feature selection achieved the highest accuracy of 98.343% with RanAdam hyper-parameter tuning compared to other classifiers.

Informing immunotherapy with multi-omics driven machine learning

Progress in sequencing technologies and clinical experiments has revolutionized immunotherapy on solid and hematologic malignancies. However, the benefits of immunotherapy are limited to specific patient subsets, posing challenges for broader application. To improve its effectiveness, identifying biomarkers that can predict patient response is crucial. Machine learning (ML) play a pivotal role in harnessing multi-omic cancer datasets and unlocking new insights into immunotherapy. This review provides an overview of cutting-edge ML models applied in omics data for immunotherapy analysis, including immunotherapy response prediction and immunotherapy-relevant tumor microenvironment identification. We elucidate how ML leverages diverse data types to identify significant biomarkers, enhance our understanding of immunotherapy mechanisms, and optimize decision-making process. Additionally, we discuss current limitations and challenges of ML in this rapidly evolving field. Finally, we outline future directions aimed at overcoming these barriers and improving the efficiency of ML in immunotherapy research.

Deep learning-based predictive classification of functional subpopulations of hematopoietic stem cells and multipotent progenitors

BACKGROUND

Hematopoietic stem cells (HSCs) and multipotent progenitors (MPPs) play a pivotal role in maintaining lifelong hematopoiesis. The distinction between stem cells and other progenitors, as well as the assessment of their functions, has long been a central focus in stem cell research. In recent years, deep learning has emerged as a powerful tool for cell image analysis and classification/prediction.

METHODS

In this study, we explored the feasibility of employing deep learning techniques to differentiate murine HSCs and MPPs based solely on their morphology, as observed through light microscopy (DIC) images.

RESULTS

After rigorous training and validation using extensive image datasets, we successfully developed a three-class classifier, referred to as the LSM model, capable of reliably distinguishing long-term HSCs, short-term HSCs, and MPPs. The LSM model extracts intrinsic morphological features unique to different cell types, irrespective of the methods used for cell identification and isolation, such as surface markers or intracellular GFP markers. Furthermore, employing the same deep learning framework, we created a two-class classifier that effectively discriminates between aged HSCs and young HSCs. This discovery is particularly significant as both cell types share identical surface markers yet serve distinct functions. This classifier holds the potential to offer a novel, rapid, and efficient means of assessing the functional states of HSCs, thus obviating the need for time-consuming transplantation experiments.

CONCLUSION

Our study represents the pioneering use of deep learning to differentiate HSCs and MPPs under steady-state conditions. This novel and robust deep learning-based platform will provide a basis for the future development of a new generation stem cell identification and separation system. It may also provide new insight into the molecular mechanisms underlying stem cell self-renewal.

Development and validation of a deep learning model for predicting postoperative survival of patients with gastric cancer

BACKGROUND

Deep learning (DL), a specialized form of machine learning (ML), is valuable for forecasting survival in various diseases. Its clinical applicability in real-world patients with gastric cancer (GC) has yet to be extensively validated.

METHODS

A combined cohort of 11,414 GC patients from the Surveillance, Epidemiology and End Results (SEER) database and 2,846 patients from a Chinese dataset were utilized. The internal validation of different algorithms, including DL model, traditional ML models, and American Joint Committee on Cancer (AJCC) stage model, was conducted by training and testing sets on the SEER database, followed by external validation on the Chinese dataset. The performance of the algorithms was assessed using the area under the receiver operating characteristic curve, decision curve, and calibration curve.

RESULTS

DL model demonstrated superior performance in terms of the area under the curve (AUC) at 1, 3, and, 5 years post-surgery across both datasets, surpassing other ML models and AJCC stage model, with AUCs of 0.77, 0.80, and 0.82 in the SEER dataset and 0.77, 0.76, and 0.75 in the Chinese dataset, respectively. Furthermore, decision curve analysis revealed that the DL model yielded greater net gains at 3 years than other ML models and AJCC stage model, and calibration plots at 3 years indicated a favorable level of consistency between the ML and actual observations during external validation.

CONCLUSIONS

DL-based model was established to accurately predict the survival rate of postoperative patients with GC.

Modeling Epidemiology Data with Machine Learning Technique to Detect Risk Factors for Gastric Cancer

PURPOSE

Gastric cancer (GC) ranks as the 7th most common cancer worldwide and a leading cause of cancer mortality. In Iran, stomach malignancies are the most common fatal cancers with higher than world average incidence. In recent years, methods like machine learning that provide the opportunity of merging health issues with computational power and learning capacity have caught considerable attention for prediction and diagnosis of diseases. In this study, we aimed to model GC data to find risk factors and identify GC cases in Golestan Cohort Study (GCS), using gradient boosting as a machine learning technique.

METHODS

Since the GC class (280) was smaller than not-GC (49,467), "Synthetic Minority Oversampling Technique" was used to balance the dataset. Seventy percent of the data was used to train the gradient boosting algorithm and find effective factors on gastric cancer, and the remaining 30% was used for accuracy assessment.

RESULTS

Our results indicated that out of 19 factors, age, social economical status, tea temperature, body mass index, gender, and education were the top six effective factors with impact rates of 0.24, 0.16, 0.13, 0.13, and 0.07, respectively. The trained model classified 70 out of 72 GC patients in the test set, correctly.

CONCLUSION

The results indicate that this model can effectively detect gastric cancer (GC) by utilizing important risk factors, thus avoiding the need for invasive procedures. The model's performance is reliable when provided with an adequate amount of input data, and as the dataset expands, its accuracy and generalization improve significantly. Overall, the trained system's success stems from its ability to identify risk factors and identify cancer patients.

Few-shot genes selection: subset of PAM50 genes for breast cancer subtypes classification

BACKGROUND

In recent years, researchers have made significant strides in understanding the heterogeneity of breast cancer and its various subtypes. However, the wealth of genomic and proteomic data available today necessitates efficient frameworks, instruments, and computational tools for meaningful analysis. Despite its success as a prognostic tool, the PAM50 gene signature's reliance on many genes presents challenges in terms of cost and complexity. Consequently, there is a need for more efficient methods to classify breast cancer subtypes using a reduced gene set accurately.

RESULTS

This study explores the potential of achieving precise breast cancer subtype categorization using a reduced gene set derived from the PAM50 gene signature. By employing a "Few-Shot Genes Selection" method, we randomly select smaller subsets from PAM50 and evaluate their performance using metrics and a linear model, specifically the Support Vector Machine (SVM) classifier. In addition, we aim to assess whether a more compact gene set can maintain performance while simplifying the classification process. Our findings demonstrate that certain reduced gene subsets can perform comparable or superior to the full PAM50 gene signature.

CONCLUSIONS

The identified gene subsets, with 36 genes, have the potential to contribute to the development of more cost-effective and streamlined diagnostic tools in breast cancer research and clinical settings.

Optimizing Fecal Occult Blood Test (FOBT) Colorectal Cancer Screening Using Gut Bacteriome as a Biomarker

BACKGROUND

Colorectal cancer (CRC) is a major cause of cancer mortality in the world. One of the most widely used screening tests for CRC is the immunochemical fecal occult blood test (iFOBT), which detects human hemoglobin from patient's stool sample. Although it is highly efficient in detecting blood from patients with gastro-intestinal lesions, such as polyps and cancers, the iFOBT has a high rate of false positive discovery. Recent studies suggested gut bacteria as a promising noninvasive biomarker for improving the diagnosis of CRC. In this study, we examined the composition of gut bacteria using iFOBT leftover from patients undergoing screening test along with a colonoscopy.

METHODS

After collecting data from more than 800 patients, we considered 4 groups for this study. The first and second groups were respectively "healthy" in which the patients had either no blood in their stool or had blood but no lesions. The third and fourth groups of patients had both blood in their stools with precancerous and cancerous lesions and considered either as low-grade and high-grade lesion groups, respectively. An amplification of 16S rRNA (V4 region) gene was performed, followed by sequencing along with various statistical and bioinformatic analysis.

RESULTS

We analyzed the composition of the gut bacteriome at phylum, class, genus, and species levels. Although members of the Firmicute phylum increased in the 3 groups compared to healthy patients, the phylum Actinobacteriota was found to decrease. Moreover, Blautia obeum and Anaerostipes hadrus from the phylum Firmicutes were increased and Collinsella aerofaciens from phylum Actinobacteriota was found decreased when healthy group is compared to the patients with high-grade lesions. Finally, among the 5 machine learning algorithms used to perform our analysis, both elastic net (AUC > 0.7) and random forest (AUC > 0.8) performs well in differentiating healthy patients from 3 other patient groups having blood in their stool.

CONCLUSION

Our study integrates the iFOBT screening tool with gut bacterial composition to improve the prediction of CRC lesions.

Ultrasound-Based Radiomics for the Classification of Henoch-Schönlein Purpura Nephritis in Children

Henoch-Schönlein purpura nephritis (HSPN) is one of the most common kidney diseases in children. The current diagnosis and classification of HSPN depend on pathological biopsy, which is seriously limited by its invasive and high-risk nature. The aim of the study was to explore the potential of radiomics model for evaluating the histopathological classification of HSPN based on the ultrasound (US) images. A total of 440 patients with Henoch-Schönlein purpura nephritis proved by biopsy were analyzed retrospectively. They were grouped according to two histopathological categories: those without glomerular crescent formation (ISKDC grades I-II) and those with glomerular crescent formation (ISKDC grades III-V). The patients were randomly assigned to either a training cohort (n = 308) or a validation cohort (n = 132) with a ratio of 7:3. The sonologist manually drew the regions of interest (ROI) on the ultrasound images of the right kidney including the cortex and medulla. Then, the ultrasound radiomics features were extracted using the Pyradiomics package. The dimensions of radiomics features were reduced by Spearman correlation coefficients and least absolute shrinkage and selection operator (LASSO) method. Finally, three radiomics models using k-nearest neighbor (KNN), logistic regression (LR), and support vector machine (SVM) were established, respectively. The predictive performance of such classifiers was assessed with receiver operating characteristic (ROC) curve. 105 radiomics features were extracted from derived US images of each patient and 14 features were ultimately selected for the machine learning analysis. Three machine learning models including k-nearest neighbor (KNN), logistic regression (LR), and support vector machine (SVM) were established for HSPN classification. Of the three classifiers, the SVM classifier performed the best in the validation cohort [area under the curve (AUC) =0.870 (95% CI, 0.795-0.944), sensitivity = 0.706, specificity = 0.950]. The US-based radiomics had good predictive value for HSPN classification, which can be served as a noninvasive tool to evaluate the severity of renal pathology and crescentic formation in children with HSPN.

Performance analysis of data resampling on class imbalance and classification techniques on multi-omics data for cancer classification

Cancer, in any of its forms, remains a significant public health concern worldwide. Advances in early detection and treatment could lead to a decline in the overall death rate from cancer in recent decades. Therefore, tumor prediction and classification play an important role in fighting cancer. This study built computational models for a joint analysis of RNA seq, copy number variation (CNV), and DNA methylation to classify normal and tumor samples across liver cancer, breast cancer, and colon adenocarcinoma from The Cancer Genome Atlas (TCGA) dataset. Total of 18 machine learning methods were evaluated based on the AUC, precision, recall, and F-measure. Besides, five techniques were compared to ameliorate problems of class imbalance in the cancer datasets. Synthetic Minority Oversampling Technique (SMOTE) demonstrated the best performance. The results indicate that the model applying Stochastic Gradient Descent (SGD) for learning binary class SVM with hinge loss has the highest classification results on liver cancer and breast cancer datasets, with accuracy over 99% and AUC greater than or equal to 0.999. For colon adenocarcinoma dataset, both SGD and Sequential Minimal Optimization (SMO) that implements John Platt's sequential minimal optimization algorithm for training a support vector machine shows an outstanding classification performance with accuracy of 100%, AUC, precision, recall, and F-measure all at 1.000.

Developing an intelligent prediction system for successful aging based on artificial neural networks

Background

Due to the growing number of disabilities in elderly, Attention to this period of life is essential to be considered. Few studies focused on the physical, mental, disabilities, and disorders affecting the quality of life in elderly people. SA1 is related to various factors influencing the elderly's life. So, the objective of the current study is to build an intelligent system for SA prediction through ANN2 algorithms to investigate better all factors affecting the elderly life and promote them.

Methods

This study was performed on 1156 SA and non-SA cases. We applied statistical feature reduction method to obtain the best factors predicting the SA. Two models of ANNs with 5, 10, 15, and 20 neurons in hidden layers were used for model construction. Finally, the best ANN configuration was obtained for predicting the SA using sensitivity, specificity, accuracy, and cross-entropy loss function.

Results

The study showed that 25 factors correlated with SA at the statistical level of P < 0.05. Assessing all ANN structures resulted in FF-BP3 algorithm having the configuration of 25-15-1 with accuracy-train of 0.92, accuracy-test of 0.86, and accuracy-validation of 0.87 gaining the best performance over other ANN algorithms.

Conclusions

Developing the CDSS for predicting SA has crucial role to effectively inform geriatrics and health care policymakers decision making.

An uncertainty-based interpretable deep learning framework for predicting breast cancer outcome

BACKGROUND

Predicting outcome of breast cancer is important for selecting appropriate treatments and prolonging the survival periods of patients. Recently, different deep learning-based methods have been carefully designed for cancer outcome prediction. However, the application of these methods is still challenged by interpretability. In this study, we proposed a novel multitask deep neural network called UISNet to predict the outcome of breast cancer. The UISNet is able to interpret the importance of features for the prediction model via an uncertainty-based integrated gradients algorithm. UISNet improved the prediction by introducing prior biological pathway knowledge and utilizing patient heterogeneity information.

RESULTS

The model was tested in seven public datasets of breast cancer, and showed better performance (average C-index = 0.691) than the state-of-the-art methods (average C-index = 0.650, ranged from 0.619 to 0.677). Importantly, the UISNet identified 20 genes as associated with breast cancer, among which 11 have been proven to be associated with breast cancer by previous studies, and others are novel findings of this study.

CONCLUSIONS

Our proposed method is accurate and robust in predicting breast cancer outcomes, and it is an effective way to identify breast cancer-associated genes. The method codes are available at: https://github.com/chh171/UISNet .

Prognostic Implication of Lymphovascular Invasion in Early Gastric Cancer Meeting Endoscopic Submucosal Dissection Criteria: Insights from Radical Surgery Outcomes

BACKGROUND

The management of early gastric cancer (EGC) has witnessed a rise in the utilization of endoscopic submucosal dissection (ESD) as a treatment modality, although prognostic markers are needed to guide management strategies. This study investigates the prognostic implications of lymphovascular invasion (LVI) in ESD-eligible EGC patients, specifically its implications for subsequent radical surgery.

MATERIAL AND METHODS

A retrospective, multicenter study from two primary hospitals analyzed clinicopathological data from 1369 EGC patients eligible for ESD, who underwent gastrectomy at Shanghai Cancer Center and Huashan Hospital between 2009 and 2018. We evaluated the relationship between LVI and lymph node metastasis (LNM), as well as the influence of LVI on recurrence-free survival (RFS) and overall survival (OS).

RESULTS

We found a strong association between LVI and LNM (p < 0.001). Advanced machine learning approaches, including Random Forest, Gradient Boosting Machine, and eXtreme Gradient Boosting, confirmed the pivotal role of LVI in forecasting LNM from both centers. Multivariate analysis identified LVI as an independent negative prognostic factor for both RFS and OS, with hazard ratios of 4.5 (95% CI: 2.4-8.5, p < 0.001) and 4.4 (95% CI: 2.1-8.9, p < 0.001), respectively.

CONCLUSIONS

LVI is crucial for risk stratification in ESD-eligible EGC patients, underscoring the necessity for radical gastrectomy. Future research should explore the potential incorporation of LVI status into existing TNM staging systems and novel therapeutic strategies.

A Deep Learning Model Combining Multimodal Factors to Predict the Overall Survival of Transarterial Chemoembolization

Background

To develop and validate an overall survival (OS) prediction model for transarterial chemoembolization (TACE).

Methods

In this retrospective study, 301 patients with hepatocellular carcinoma (HCC) who received TACE from 2012 to 2015 were collected. The residual network was used to extract prognostic information from CT images, which was then combined with the clinical factors adjusted by COX regression to predict survival using a modified deep learning model (DLOPCombin). The DLOPCombin model was compared with the residual network model (DLOPCTR), multiple COX regression model (DLOPCox), Radiomic model (Radiomic), and clinical model.

Results

In the validation cohort, DLOPCombin shows the highest TD AUC of all cohorts, which compared with Radiomic (TD AUC: 0.96vs 0.63) and clinical model (TD AUC: 0.96 vs 0.62) model. DLOPCombin showed significant difference in C index compared with DLOPCTR and DLOPCox models (P < 0.05). Moreover, the DLOPCombin showed good calibration and overall net benefit. Patients with DLOPCombin model score ≤ 0.902 had better OS (33 months vs 15.5 months, P < 0.0001).

Conclusion

The deep learning model can effectively predict the patients' overall survival of TACE.

[Screening of immune related gene and survival prediction of lung adenocarcinoma patients based on LightGBM model]

Lung cancer is one of the malignant tumors with the greatest threat to human health, and studies have shown that some genes play an important regulatory role in the occurrence and development of lung cancer. In this paper, a LightGBM ensemble learning method is proposed to construct a prognostic model based on immune relate gene (IRG) profile data and clinical data to predict the prognostic survival rate of lung adenocarcinoma patients. First, this method used the Limma package for differential gene expression, used CoxPH regression analysis to screen the IRG to prognosis, and then used XGBoost algorithm to score the importance of the IRG features. Finally, the LASSO regression analysis was used to select IRG that could be used to construct a prognostic model, and a total of 17 IRG features were obtained that could be used to construct model. LightGBM was trained according to the IRG screened. The K-means algorithm was used to divide the patients into three groups, and the area under curve (AUC) of receiver operating characteristic (ROC) of the model output showed that the accuracy of the model in predicting the survival rates of the three groups of patients was 96%, 98% and 96%, respectively. The experimental results show that the model proposed in this paper can divide patients with lung adenocarcinoma into three groups [5-year survival rate higher than 65% (group 1), lower than 65% but higher than 30% (group 2) and lower than 30% (group 3)] and can accurately predict the 5-year survival rate of lung adenocarcinoma patients.

Machine learning predicts the risk of osteoporosis in patients with breast cancer and healthy women

OBJECTIVE

In this study, we investigated the effects of endocrine therapy and related drugs on the body composition and bone metabolism of patients with breast cancer. Additionally, using body composition-related indicators in machine learning algorithms, the risks of osteoporosis in patients with breast cancer and healthy women were predicted.

METHODS

We enrolled postmenopausal patients with breast cancer who were hospitalized in a tertiary hospital and postmenopausal women undergoing health checkups in our hospital between 2019 and 2021. The basic information, body composition, bone density-related indicators, and bone metabolism-related indicators of all the study subjects were recorded. Machine learning models were constructed using cross-validation.

RESULTS

Compared with a healthy population, the body composition of patients with breast cancer was low in bone mass, protein, body fat percentage, muscle, and basal metabolism, whereas total water, intracellular fluid, extracellular fluid, and waist-to-hip ratio were high. In patients with breast cancer, the bone mineral density (BMD), Z value, and T value were low and the proportion of bone loss and osteoporosis was high. BMD in patients with breast cancer was negatively correlated with age, endocrine therapy status, duration of medication, and duration of menopause, and it was positively correlated with body mass index (BMI) and basal metabolism. The parameters including body composition, age, hormone receptor status, and medication type were used for developing the machine learning model to predict osteoporosis risk in patients with breast cancer and healthy populations. The model showed a high accuracy in predicting osteoporosis, reflecting the predictive value of the model.

CONCLUSIONS

Patients with breast cancer may have changed body composition and BMD. Compared with the healthy population, the main indicators of osteoporosis in patients with breast cancer were reduced nonadipose tissue, increased risk of edema, altered fat distribution, and reduced BMD. In addition to age, duration of treatment, and duration of menopause, body composition-related indicators such as BMI and basal metabolism may be considerably associated with BMD of patients with breast cancer, suggesting that BMD status can be monitored in clinical practice by focusing on changes in the aforementioned indexes, which may provide a way to prevent preclinical osteoporosis.

A journey from omics to clinicomics in solid cancers: Success stories and challenges

The word 'cancer' encompasses a heterogenous group of distinct disease types characterized by a spectrum of pathological features, genetic alterations and response to therapies. According to the World Health Organization, cancer is the second leading cause of death worldwide, responsible for one in six deaths and hence imposes a significant burden on global healthcare systems. High-throughput omics technologies combined with advanced imaging tools, have revolutionized our ability to interrogate the molecular landscape of tumors and has provided unprecedented understanding of the disease. Yet, there is a gap between basic research discoveries and their translation into clinically meaningful therapies for improving patient care. To bridge this gap, there is a need to analyse the vast amounts of high dimensional datasets from multi-omics platforms. The integration of multi-omics data with clinical information like patient history, histological examination and imaging has led to the novel concept of clinicomics and may expedite the bench-to-bedside transition in cancer. The journey from omics to clinicomics has gained momentum with development of radiomics which involves extracting quantitative features from medical imaging data with the help of deep learning and artificial intelligence (AI) tools. These features capture detailed information about the tumor's shape, texture, intensity, and spatial distribution. Together, the related fields of multiomics, translational bioinformatics, radiomics and clinicomics may provide evidence-based recommendations tailored to the individual cancer patient's molecular profile and clinical characteristics. In this chapter, we summarize multiomics studies in solid cancers with a specific focus on breast cancer. We also review machine learning and AI based algorithms and their use in cancer diagnosis, subtyping, prognosis and predicting treatment resistance and relapse.

Prognostic Factors for Mortality in Hepatocellular Carcinoma at Diagnosis: Development of a Predictive Model Using Artificial Intelligence

BACKGROUND

Hepatocellular carcinoma (HCC) accounts for 75% of primary liver tumors. Controlling risk factors associated with its development and implementing screenings in risk populations does not seem sufficient to improve the prognosis of these patients at diagnosis. The development of a predictive prognostic model for mortality at the diagnosis of HCC is proposed.

METHODS

In this retrospective multicenter study, the analysis of data from 191 HCC patients was conducted using machine learning (ML) techniques to analyze the prognostic factors of mortality that are significant at the time of diagnosis. Clinical and analytical data of interest in patients with HCC were gathered.

RESULTS

Meeting Milan criteria, Barcelona Clinic Liver Cancer (BCLC) classification and albumin levels were the variables with the greatest impact on the prognosis of HCC patients. The ML algorithm that achieved the best results was random forest (RF).

CONCLUSIONS

The development of a predictive prognostic model at the diagnosis is a valuable tool for patients with HCC and for application in clinical practice. RF is useful and reliable in the analysis of prognostic factors in the diagnosis of HCC. The search for new prognostic factors is still necessary in patients with HCC.

Predictive analytics and early intervention in healthcare social work: a scoping review

This scoping review investigates the untapped potential of predictive analytics in healthcare social work, specifically targeting early intervention frameworks. Despite the escalating attention predictive analytics has garnered across multiple disciplines, its tailored application in social work remains notably sparse. This study endeavors to fill this lacuna by meticulously reviewing the extant literature and delineating the prospective advantages and inherent constraints of integrating predictive analytics into healthcare social work. The outcomes of this inquiry enrich the prevailing dialogue on the utility of predictive analytics in healthcare, offering indispensable perspectives for practitioners and policymakers in the social work domain.

Applications of Machine Learning (ML) and Mathematical Modeling (MM) in Healthcare with Special Focus on Cancer Prognosis and Anticancer Therapy: Current Status and Challenges

The use of data-driven high-throughput analytical techniques, which has given rise to computational oncology, is undisputed. The widespread use of machine learning (ML) and mathematical modeling (MM)-based techniques is widely acknowledged. These two approaches have fueled the advancement in cancer research and eventually led to the uptake of telemedicine in cancer care. For diagnostic, prognostic, and treatment purposes concerning different types of cancer research, vast databases of varied information with manifold dimensions are required, and indeed, all this information can only be managed by an automated system developed utilizing ML and MM. In addition, MM is being used to probe the relationship between the pharmacokinetics and pharmacodynamics (PK/PD interactions) of anti-cancer substances to improve cancer treatment, and also to refine the quality of existing treatment models by being incorporated at all steps of research and development related to cancer and in routine patient care. This review will serve as a consolidation of the advancement and benefits of ML and MM techniques with a special focus on the area of cancer prognosis and anticancer therapy, leading to the identification of challenges (data quantity, ethical consideration, and data privacy) which are yet to be fully addressed in current studies.

Understand how machine learning impact lung cancer research from 2010 to 2021: A bibliometric analysis

Advances in lung cancer research applying machine learning (ML) technology have generated many relevant literature. However, there is absence of bibliometric analysis review that aids a comprehensive understanding of this field and its progress. Present article for the first time performed a bibliometric analysis to clarify research status and focus from 2010 to 2021. In the analysis, a total of 2,312 relevant literature were searched and retrieved from the Web of Science Core Collection database. We conducted a bibliometric analysis and further visualization. During that time, exponentially growing annual publication and our model have shown a flourishing research prospect. Annual citation reached the peak in 2017. Researchers from United States and China have produced most of the relevant literature and strongest partnership between them. Medical image analysis and Nature appeared to bring more attention to the public. The computer-aided diagnosis, precision medicine, and survival prediction were the focus of research, reflecting the development trend at that period. ML did make a big difference in lung cancer research in the past decade.

Remote Diagnosis on Upper Respiratory Tract Infections Based on a Neural Network with Few Symptom Words-A Feasibility Study

This study aims explore the feasibility of using neural network (NNs) and deep learning to diagnose three common respiratory diseases with few symptom words. These three diseases are nasopharyngitis, upper respiratory infection, and bronchitis/bronchiolitis. Through natural language processing, the symptom word vectors are encoded by GPT-2 and classified by the last linear layer of the NN. The experimental results are promising, showing that this model achieves a high performance in predicting all three diseases. They revealed 90% accuracy, which suggests the implications of the developed model, highlighting its potential use in assisting patients' understanding of their conditions via a remote diagnosis. Unlike previous studies that have focused on extracting various categories of information from medical records, this study directly extracts sequential features from unstructured text data, reducing the effort required for data pre-processing.

Novel ensemble feature selection techniques applied to high-grade gastroenteropancreatic neuroendocrine neoplasms for the prediction of survival

BACKGROUND AND OBJECTIVE

Determining the most informative features for predicting the overall survival of patients diagnosed with high-grade gastroenteropancreatic neuroendocrine neoplasms is crucial to improve individual treatment plans for patients, as well as the biological understanding of the disease. The main objective of this study is to evaluate the use of modern ensemble feature selection techniques for this purpose with respect to (a) quantitative performance measures such as predictive performance, (b) clinical interpretability, and (c) the effect of integrating prior expert knowledge.

METHODS

The Repeated Elastic Net Technique for Feature Selection (RENT) and the User-Guided Bayesian Framework for Feature Selection (UBayFS) are recently developed ensemble feature selectors investigated in this work. Both allow the user to identify informative features in datasets with low sample sizes and focus on model interpretability. While RENT is purely data-driven, UBayFS can integrate expert knowledge a priori in the feature selection process. In this work, we compare both feature selectors on a dataset comprising 63 patients and 110 features from multiple sources, including baseline patient characteristics, baseline blood values, tumor histology, imaging, and treatment information.

RESULTS

Our experiments involve data-driven and expert-driven setups, as well as combinations of both. In a five-fold cross-validated experiment without expert knowledge, our results demonstrate that both feature selectors allow accurate predictions: A reduction from 110 to approximately 20 features (around 82%) delivers near-optimal predictive performances with minor variations according to the choice of the feature selector, the predictive model, and the fold. Thereafter, we use findings from clinical literature as a source of expert knowledge. In addition, expert knowledge has a stabilizing effect on the feature set (an increase in stability of approximately 40%), while the impact on predictive performance is limited.

CONCLUSIONS

The features WHO Performance Status, Albumin, Platelets, Ki-67, Tumor Morphology, Total MTV, Total TLG, and SUVmax are the most stable and predictive features in our study. Overall, this study demonstrated the practical value of feature selection in medical applications not only to improve quantitative performance but also to deliver potentially new insights to experts.

Improving Cancer Survival Prediction via Graph Convolutional Neural Network Learning on Protein-Protein Interaction Networks

Cancer is one of the most challenging health problems worldwide. Accurate cancer survival prediction is vital for clinical decision making. Many deep learning methods have been proposed to understand the association between patients' genomic features and survival time. In most cases, the gene expression matrix is fed directly to the deep learning model. However, this approach completely ignores the interactions between biomolecules, and the resulting models can only learn the expression levels of genes to predict patient survival. In essence, the interaction between biomolecules is the key to determining the direction and function of biological processes. Proteins are the building blocks and principal undertakings of life activities, and as such, their complex interaction network is potentially informative for deep learning methods. Therefore, a more reliable approach is to have the neural network learn both gene expression data and protein interaction networks. We propose a new computational approach, termed CRESCENT, which is a protein-protein interaction (PPI) prior knowledge graph-based convolutional neural network (GCN) to improve cancer survival prediction. CRESCENT relies on the gene expression networks rather than gene expression levels to predict patient survival. The performance of CRESCENT is evaluated on a large-scale pan-cancer dataset consisting of 5991 patients from 16 different types of cancers. Extensive benchmarking experiments demonstrate that our proposed method is competitive in terms of the evaluation metric of the time-dependent concordance index( Ctd) when compared with several existing state-of-the-art approaches. Experiments also show that incorporating the network structure between genomic features effectively improves cancer survival prediction.

Enhancing Bone Cancer Diagnosis Through Image Extraction and Machine Learning: A State-of-the-Art Approach

Background: Bone cancer is a severe condition often leading to patient mortality. Diagnosis relies on X-rays, MRIs, or CT scans, which require time-consuming manual review by experts. Thus, developing an automated system is crucial for accurate classification of malignant and healthy bone.Methods: Differentiating between them poses a challenge as they may exhibit similar physical characteristics. The initial step is selecting the optimal edge detection method. Two feature sets are then generated: one with the histogram of oriented gradients (HOG) and one without. Performance evaluation involves two machine learning models: Support Vector Machine (SVM) and Random Forest.Results: Including HOG consistently yields superior results. The SVM model with HOG achieves an F-1 score of 0.92, outperforming the Random Forest model's .77. This study aims to develop reliable methods for bone cancer classification. The proposed automated method assists surgeons in accurately detecting malignant bone regions using modern image analysis techniques and machine learning models. Incorporating HOG significantly enhances performance, improving differentiation between malignant and healthy bone.Conclusion: Ultimately, this approach supports precise diagnoses and informed treatment decisions for bone cancer patients.

Ancient dormant virus remnant ERVW-1 drives ferroptosis via degradation of GPX4 and SLC3A2 in schizophrenia

Human endogenous retroviruses (HERVs) are remnants of retroviral infections in human germline cells from millions of years ago. Among these, ERVW-1 (also known as HERV-W-ENV, ERVWE1, or ENVW) encodes the envelope protein of the HERV-W family, which contributes to the pathophysiology of schizophrenia. Additionally, neuropathological studies have revealed cell death and disruption of iron homeostasis in the brains of individuals with schizophrenia. Here, our bioinformatics analysis showed that differentially expressed genes in the human prefrontal cortex RNA microarray dataset (GSE53987) were mainly related to ferroptosis and its associated pathways. Clinical data demonstrated significantly lower expression levels of ferroptosis-related genes, particularly Glutathione peroxidase 4 (GPX4) and solute carrier family 3 member 2 (SLC3A2), in schizophrenia patients compared to normal controls. Further in-depth analyses revealed a significant negative correlation between ERVW-1 expression and the levels of GPX4/SLC3A2 in schizophrenia. Studies indicated that ERVW-1 increased iron levels, malondialdehyde (MDA), and transferrin receptor protein 1 (TFR1) expression while decreasing glutathione (GSH) levels and triggering the loss of mitochondrial membrane potential, suggesting that ERVW-1 can induce ferroptosis. Ongoing research has shown that ERVW-1 reduced the expression of GPX4 and SLC3A2 by inhibiting their promoter activities. Moreover, Ferrostatin-1 (Fer-1), the ferroptosis inhibitor, reversed the iron accumulation and mitochondrial membrane potential loss, as well as restored the expressions of ferroptosis markers GSH, MDA, and TFR1 induced by ERVW-1. In conclusion, ERVW-1 could promote ferroptosis by downregulating the expression of GPX4 and SLC3A2, revealing a novel mechanism by which ERVW-1 contributes to neuronal cell death in schizophrenia.

Machine learning algorithms being an auxiliary tool to predict the overall survival of patients with renal cell carcinoma using the SEER database

Background

The clinical prognosis assessment of renal cell carcinoma (RCC) still relies on nuclear grading and nuclear score by naked eye with microscope, which has defects long time, low efficiency, and uneven evaluation level criteria. There are few machine learning (ML) studies investigating the prognosis in the RCC literature which could also quantify the risk of postoperative recurrence of RCC patients and guide cancer patients to conduct individualized postoperative clinical management. This study evaluated the suitability of ML algorithms for survival prediction in patients with RCC.

Methods

A total of 192,912 RCC patients from the Surveillance, Epidemiology, and End Results (SEER) were obtained from 2004 to 2015. Six ML algorithms including support vector machine (SVM), Bayesian method, decision tree, random forest, neural network, and Extreme Gradient Boosting (XGBoost) were applied to predict overall survival (OS) of RCC.

Results

Patients from the SEER with a median age of 62 years and the pathological types were clear cell RCC (47.6%), papillary RCC (9.5%), chromophobe RCC (4.0%) and others (4.1%) were collected. In the deleting patients with missing data, the highest accurate model was XGBoost [area under the curve (AUC) 67.0%]. In the deleting patients with missing data and survival time <5 years, the accuracy of random forest, neural network and XGBoost were high, with AUC of 80.8%, 81.5% and 81.8%, respectively. In the only deleting the missing tumor diameter and filling the missing dataset with missForest, the highest accurate model was random forest (AUC: 71.9%). In this study, the overall accuracy of the SVM model was not high, apart from in the population of patients with deleting the missing tumor diameter and survival time <5 years, and filling the missing data with missForest. Random forest, neural network and XGBoost had high accuracy, with AUC of 84.1%, 84.7% and 84.8%, respectively.

Conclusions

ML algorithms could be used to predict the prognosis of RCC. It could quantify the recurrence possibility of patients and help more individualized postoperative clinical management. Given the limitations and complexity of datasets, ML may be used as an auxiliary tool to analyze and process larger datasets and complex data.

Clinical decision support tool for breast cancer recurrence prediction using SHAP value in cooperative game theory

Background

Recurrence remains the primary cause of death in patients with breast cancer. Although machine learning can efficiently predict the prognosis of breast cancer patients, the black-box nature of the model may result in a lack of evidence for clinicians when making critical decisions.

Methods

In this study, our main objective was twofold: (1) to develop a clinical decision support tool for predicting the prognosis of breast cancer and (2) to identify and explore the key factors that influence breast cancer recurrence. To achieve this, we employed an explainable ensemble learning method called Shapley additive explanation (SHAP), which leverages cooperative game theory. Using real-world data from 1629 breast cancer patients, we analyzed and uncovered the key factors associated with breast cancer recurrence. Subsequently, we used these identified factors to create a recurrence prediction model and establish a decision mechanism for the tool. The proposed method not only provides accurate recurrence predictions but also offers transparent explanations for these predictions.

Results

By utilizing four key factors, namely, tumor size, clinical stage III, number of lymph node metastases, and age, our decision support tool for predicting breast cancer recurrence achieved significant improvements. The extra-tree model exhibited an increased area under the receiver operating characteristic curve (AUC) of 0.97, while the Random Forest model demonstrated an improved AUC of 0.96. We also offer a decision mechanism for a recurrence prediction model based on the identified key factors. This transparent and interpretable decision-making process facilitated by our explainable ensemble learning model enhances trust and promotes its applicability in clinical settings.

Conclusions

The proposed explainable ensemble learning method shows promising results in predicting breast cancer recurrence, outperforming existing methods with high accuracy and transparency. This advancement has the potential to significantly improve clinical decision-making and patient outcomes in breast cancer treatment.

Combined measurement of serum zinc with PSA ameliorates prostate cancer screening efficiency via support vector machine algorithms

Background

Early screening of prostate cancer (PCa) is pivotal but challenging in the clinical scenario due to the phenomena of false positivity or false negativity of some serological evaluations, e.g. PSA testing. Decline of serum Zn2+ levels in PCa patients reportedly plays a crucial role in early screening of PCa. Accordingly, we combined 4 indices comprising the serum levels of total PSA (tPSA), free PSA (fPSA), Zn2+ and demographic information (especially age) in order to ameliorate the efficacies of PCa screening with support vector machine (SVM) algorithms.

Methods

A total of 858 male patients with prostate disorders and 345 healthy male controls were enrolled. Patients' data included 4 variables and serum Zn2+ was quantified via a self-invented Zn2+ responsive AIE-based fluorescent probe as previously published. tPSA and fPSA were routinely determined by a chemiluminescent method. Mathematical simulations were conducted to establish a SVM model for the combined diagnostics with the four variables. Moreover, ROC and its characteristic AUC were also employed to evaluate the classification efficacy of the model. Sigmoid function was utilized to estimate corresponding probabilities of classifying the clinical subjects as per 5 grades, which were incorporated into our established prostate index (PI) stratification system.

Results

In SVM model, the mean AUC of the ROC with the quartet of variables was approximately 84% for PCa diagnosis, whereas the mean AUC of the ROCs with tPSA, fPSA, [Zn2+] or age alone was 64%, 62%, 55% and 59%, respectively. We further established an integrated prostate index (PI) stratification system with 5 grades and a software package to support clinicians in predicting PCa, with the accuracy of our risk stratification system being 83.3%, 91.6% and 83.3% in predicting normal, benign and PCa cases in corresponding groups. Follow-up findings especially MRI results and PI-RADS scores supported the reliability of this stratification platform as well.

Conclusion

Findings from our present study demonstrated that index combination via SVM algorithms may well facilitate clinicians in early differential screening of PCa. Meanwhile, our established PI stratification system based on SVM model and Sigmoid function provided substantial accuracy in preclinical risk prediction of developing prostate cancer.

Survival prediction of glioblastoma patients using modern deep learning and machine learning techniques

In this study, we utilized data from the Surveillance, Epidemiology, and End Results (SEER) database to predict the glioblastoma patients' survival outcomes. To assess dataset skewness and detect feature importance, we applied Pearson's second coefficient test of skewness and the Ordinary Least Squares method, respectively. Using two sampling strategies, holdout and five-fold cross-validation, we developed five machine learning (ML) models alongside a feed-forward deep neural network (DNN) for the multiclass classification and regression prediction of glioblastoma patient survival. After balancing the classification and regression datasets, we obtained 46,340 and 28,573 samples, respectively. Shapley additive explanations (SHAP) were then used to explain the decision-making process of the best model. In both classification and regression tasks, as well as across holdout and cross-validation sampling strategies, the DNN consistently outperformed the ML models. Notably, the accuracy were 90.25% and 90.22% for holdout and five-fold cross-validation, respectively, while the corresponding R2 values were 0.6565 and 0.6622. SHAP analysis revealed the importance of age at diagnosis as the most influential feature in the DNN's survival predictions. These findings suggest that the DNN holds promise as a practical auxiliary tool for clinicians, aiding them in optimal decision-making concerning the treatment and care trajectories for glioblastoma patients.

Construction and validation of a progression prediction model for locally advanced rectal cancer patients received neoadjuvant chemoradiotherapy followed by total mesorectal excision based on machine learning

Background

We attempted to develop a progression prediction model for local advanced rectal cancer(LARC) patients who received preoperative neoadjuvant chemoradiotherapy(NCRT) and operative treatment to identify high-risk patients in advance.

Methods

Data from 272 LARC patients who received NCRT and total mesorectal excision(TME) from 2011 to 2018 at the Fourth Hospital of Hebei Medical University were collected. Data from 161 patients with rectal cancer (each sample with one target variable (progression) and 145 characteristic variables) were included. One Hot Encoding was applied to numerically represent some characteristics. The K-Nearest Neighbor (KNN) filling method was used to determine the missing values, and SmoteTomek comprehensive sampling was used to solve the data imbalance. Eventually, data from 135 patients with 45 characteristic clinical variables were obtained. Random forest, decision tree, support vector machine (SVM), and XGBoost were used to predict whether patients with rectal cancer will exhibit progression. LASSO regression was used to further filter the variables and narrow down the list of variables using a Venn diagram. Eventually, the prediction model was constructed by multivariate logistic regression, and the performance of the model was confirmed in the validation set.

Results

Eventually, data from 135 patients including 45 clinical characteristic variables were included in the study. Data were randomly divided in an 8:2 ratio into a data set and a validation set, respectively. Area Under Curve (AUC) values of 0.72 for the decision tree, 0.97 for the random forest, 0.89 for SVM, and 0.94 for XGBoost were obtained from the data set. Similar results were obtained from the validation set. Twenty-three variables were obtained from LASSO regression, and eight variables were obtained by considering the intersection of the variables obtained using the previous four machine learning methods. Furthermore, a multivariate logistic regression model was constructed using the data set; the ROC indicated its good performance. The ROC curve also verified the good predictive performance in the validation set.

Conclusions

We constructed a logistic regression model with good predictive performance, which allowed us to accurately predict whether patients who received NCRT and TME will exhibit disease progression.

Machine learning-based classifiers to predict metastasis in colorectal cancer patients

Background

The increasing prevalence of colorectal cancer (CRC) in Iran over the past three decades has made it a key public health burden. This study aimed to predict metastasis in CRC patients using machine learning (ML) approaches in terms of demographic and clinical factors.

Methods

This study focuses on 1,127 CRC patients who underwent appropriate treatments at Taleghani Hospital, a tertiary care facility. The patients were divided into training and test datasets in an 80:20 ratio. Various ML methods, including Naive Bayes (NB), random rorest (RF), support vector machine (SVM), neural network (NN), decision tree (DT), and logistic regression (LR), were used for predicting metastasis in CRC patients. Model performance was evaluated using 5-fold cross-validation, reporting sensitivity, specificity, the area under the curve (AUC), and other indexes.

Results

Among the 1,127 patients, 183 (16%) had experienced metastasis. In the predictionof metastasis, both the NN and RF algorithms had the highest AUC, while SVM ranked third in both the original and balanced datasets. The NN and RF algorithms achieved the highest AUC (100%), sensitivity (100% and 100%, respectively), and accuracy (99.2% and 99.3%, respectively) on the balanced dataset, followed by the SVM with an AUC of 98.8%, a sensitivity of 97.5%, and an accuracy of 97%. Moreover, lower false negative rate (FNR), false positive rate (FPR), and higher negative predictive value (NPV) can be confirmed by these two methods. The results also showed that all methods exhibited good performance in the test datasets, and the balanced dataset improved the performance of most ML methods. The most important variables for predicting metastasis were the tumor stage, the number of involved lymph nodes, and the treatment type. In a separate analysis of patients with tumor stages I-III, it was identified that tumor grade, tumor size, and tumor stage are the most important features.

Conclusion

This study indicated that NN and RF were the best among ML-based approaches for predicting metastasis in CRC patients. Both the tumor stage and the number of involved lymph nodes were considered the most important features.

A Machine Learning Model to Predict Risk for Hepatocellular Carcinoma in Patients With Metabolic Dysfunction-Associated Steatotic Liver Disease

Background and Aims

Hepatocellular carcinoma (HCC) incidence is increasing and correlated with metabolic dysfunction-associated steatotic liver disease (MASLD; formerly nonalcoholic fatty liver disease), even in patients without advanced liver fibrosis who are more likely to be diagnosed with advanced disease stages and shorter survival time, and less likely to receive a liver transplant. Machine learning (ML) tools can characterize large datasets and help develop predictive models that can calculate individual HCC risk and guide selective screening and risk mitigation strategies.

Methods

Tableau and KNIME Analytics were used for descriptive analytics and ML tasks. ML models were developed using standard laboratory and clinical parameters. Sci-kit learn algorithms were used for model development. Data from University of California (UC), Davis, were used to develop and train a pilot predictive model, which was subsequently validated in an independent dataset from UC San Francisco. MASLD and HCC patients were identified by International Classification of Diseases-9/10 codes.

Results

Of the patients diagnosed with MASLD (n = 1561 training; n = 686 validation), HCC developed in 14% (n = 227) of the UC Davis training cohort and 25% (n = 176) of the UC San Francisco validation cohort. Liver fibrosis determined by the noninvasive Fibrosis-4 score was the strongest single predictor for HCC in the model. Using the validation cohort, the model predicted HCC development at 92.06% accuracy with an area under the curve of 0.97, F1-score of 0.84, 98.34% specificity, and 74.41% sensitivity.

Conclusion

ML models can aid physicians in providing early HCC risk assessment in patients with MASLD. Further validation will translate to cost-effective, personalized care of at-risk patients.

Should we really use graph neural networks for transcriptomic prediction?

The recent development of deep learning methods have undoubtedly led to great improvement in various machine learning tasks, especially in prediction tasks. This type of methods have also been adapted to answer various problems in bioinformatics, including automatic genome annotation, artificial genome generation or phenotype prediction. In particular, a specific type of deep learning method, called graph neural network (GNN) has repeatedly been reported as a good candidate to predict phenotypes from gene expression because its ability to embed information on gene regulation or co-expression through the use of a gene network. However, up to date, no complete and reproducible benchmark has ever been performed to analyze the trade-off between cost and benefit of this approach compared to more standard (and simpler) machine learning methods. In this article, we provide such a benchmark, based on clear and comparable policies to evaluate the different methods on several datasets. Our conclusion is that GNN rarely provides a real improvement in prediction performance, especially when compared to the computation effort required by the methods. Our findings on a limited but controlled simulated dataset shows that this could be explained by the limited quality or predictive power of the input biological gene network itself.

Artificial intelligence for classification and detection of oral mucosa lesions on photographs: a systematic review and meta-analysis

OBJECTIVE

This study aimed to review and synthesize studies using artificial intelligence (AI) for classifying, detecting, or segmenting oral mucosal lesions on photographs.

MATERIALS AND METHOD

Inclusion criteria were (1) studies employing AI to (2) classify, detect, or segment oral mucosa lesions, (3) on oral photographs of human subjects. Included studies were assessed for risk of bias using Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). A PubMed, Scopus, Embase, Web of Science, IEEE, arXiv, medRxiv, and grey literature (Google Scholar) search was conducted until June 2023, without language limitation.

RESULTS

After initial searching, 36 eligible studies (from 8734 identified records) were included. Based on QUADAS-2, only 7% of studies were at low risk of bias for all domains. Studies employed different AI models and reported a wide range of outcomes and metrics. The accuracy of AI for detecting oral mucosal lesions ranged from 74 to 100%, while that for clinicians un-aided by AI ranged from 61 to 98%. Pooled diagnostic odds ratio for studies which evaluated AI for diagnosing or discriminating potentially malignant lesions was 155 (95% confidence interval 23-1019), while that for cancerous lesions was 114 (59-221).

CONCLUSIONS

AI may assist in oral mucosa lesion screening while the expected accuracy gains or further health benefits remain unclear so far.

CLINICAL RELEVANCE

Artificial intelligence assists oral mucosa lesion screening and may foster more targeted testing and referral in the hands of non-specialist providers, for example. So far, it remains unclear if accuracy gains compared with specialized can be realized.

An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies

The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

Predicting delayed remission in Cushing's disease using radiomics models: a multi-center study

Purpose

No multi-center radiomics models have been built to predict delayed remission (DR) after transsphenoidal surgery (TSS) in Cushing's disease (CD). The present study aims to build clinical and radiomics models based on data from three centers to predict DR after TSS in CD.

Methods

A total of 122 CD patients from Peking Union Medical College Hospital, Xuanwu Hospital, and Fuzhou General Hospital were enrolled between January 2000 and January 2019. The T1-weighted gadolinium-enhanced MRI images and clinical data were used as inputs to build clinical and radiomics models. The regions of interest (ROI) of MRI images were automatically defined by a deep learning algorithm developed by our team. The area under the curve (AUC) of receiver operating characteristic (ROC) curves was used to evaluate the performance of the models. In total, 10 machine learning algorithms were used to construct models.

Results

The overall DR rate is 44.3% (54/122). According to multivariate Logistic regression analysis, patients with higher BMI and lower postoperative cortisol levels are more likely to achieve a higher rate of delayed remission. Among the 10 models, XGBoost achieved the best performance among all models in both clinical and radiomics models with AUC values of 0.767 and 0.819 respectively. The results from SHAP value and LIME algorithms revealed that postoperative cortisol level (PoC) and BMI were the most important features associated with DR.

Conclusion

Radiomics models can be built as an effective noninvasive method to predict DR and might be useful in assisting neurosurgeons in making therapeutic plans after TSS for CD patients. These results are preliminary and further validation in a larger patient sample is needed.

Optimizing Gene Selection and Cancer Classification with Hybrid Sine Cosine and Cuckoo Search Algorithm

Gene expression datasets offer a wide range of information about various biological processes. However, it is difficult to find the important genes among the high-dimensional biological data due to the existence of redundant and unimportant ones. Numerous Feature Selection (FS) techniques have been created to get beyond this obstacle. Improving the efficacy and precision of FS methodologies is crucial in order to identify significant genes amongst complicated complex biological data. In this work, we present a novel approach to gene selection called the Sine Cosine and Cuckoo Search Algorithm (SCACSA). This hybrid method is designed to work with well-known machine learning classifiers Support Vector Machine (SVM). Using a dataset on breast cancer, the hybrid gene selection algorithm's performance is carefully assessed and compared to other feature selection methods. To improve the quality of the feature set, we use minimum Redundancy Maximum Relevance (mRMR) as a filtering strategy in the first step. The hybrid SCACSA method is then used to enhance and optimize the gene selection procedure. Lastly, we classify the dataset according to the chosen genes by using the SVM classifier. Given the pivotal role gene selection plays in unraveling complex biological datasets, SCACSA stands out as an invaluable tool for the classification of cancer datasets. The findings help medical practitioners make well-informed decisions about cancer diagnosis and provide them with a valuable tool for navigating the complex world of gene expression data.

Autosurv: interpretable deep learning framework for cancer survival analysis incorporating clinical and multi-omics data

Accurate prognosis for cancer patients can provide critical information for optimizing treatment plans and improving life quality. Combining omics data and demographic/clinical information can offer a more comprehensive view of cancer prognosis than using omics or clinical data alone and can also reveal the underlying disease mechanisms at the molecular level. In this study, we developed and validated a deep learning framework to extract information from high-dimensional gene expression and miRNA expression data and conduct prognosis prediction for breast cancer and ovarian-cancer patients using multiple independent multi-omics datasets. Our model achieved significantly better prognosis prediction than the current machine learning and deep learning approaches in various settings. Moreover, an interpretation method was applied to tackle the "black-box" nature of deep neural networks and we identified features (i.e., genes, miRNA, demographic/clinical variables) that were important to distinguish predicted high- and low-risk patients. The significance of the identified features was partially supported by previous studies.

Identification and validation of prognostic signature genes of bladder cancer by integrating methylation and transcriptomic analysis

Being a frequent malignant tumor of the genitourinary system, Bladder Urothelial Carcinoma (BLCA) has a poor prognosis. This study focused on identifying and validating prognostic biomarkers utilizing methylation, transcriptomics, and clinical data from The Cancer Genome Atlas Bladder Urothelial Carcinoma (TCGA BLCA) cohort. The impact of altered differentially methylated hallmark pathway genes was subjected to clustering analysis to observe changes in the transcriptional landscape on BLCA patients and identify two subtypes of patients from the TCGA BLCA population where Subtype 2 was associated with the worst prognosis with a p-value of 0.00032. Differential expression and enrichment analysis showed that subtype 2 was enriched in immune-responsive and cancer-progressive pathways, whereas subtype 1 was enriched in biosynthetic pathways. Following, regression and network analyses revealed Epidermal Growth Factor Receptor (EGFR), Fos-related antigen 1 (FOSL1), Nuclear Factor Erythroid 2 (NFE2), ADP-ribosylation factor-like protein 4D (ARL4D), SH3 domain containing ring finger 2 (SH3RF2), and Cadherin 3 (CDH3) genes to be the most significant prognostic gene markers. These genes were used to construct a risk model that separated the BLCA patients into high and low-risk groups. The risk model was also validated in an external dataset by performing survival analysis between high and low-risk groups with a p-value < 0.001 and the result showed the high group was significantly associated with poor prognosis compared to the low group. Single-cell analyses revealed the elevated level of these genes in the tumor microenvironment and associated with immune response. High-grade patients also tend to have a high expression of these genes compared to low-grade patients. In conclusion, this research developed a six-gene signature that is pertinent to the prediction of overall survival (OS) and might contribute to the advancement of precision medicine in the management of bladder cancer.

Machine learning-based radiomics strategy for prediction of acquired EGFR T790M mutation following treatment with EGFR-TKI in NSCLC

The epidermal growth factor receptor (EGFR) Thr790 Met (T790M) mutation is responsible for approximately half of the acquired resistance to EGFR-tyrosine kinase inhibitor (TKI) in non-small-cell lung cancer (NSCLC) patients. Identifying patients at diagnosis who are likely to develop this mutation after first- or second-generation EGFR-TKI treatment is crucial for better treatment outcomes. This study aims to develop and validate a radiomics-based machine learning (ML) approach to predict the T790M mutation in NSCLC patients at diagnosis. We collected retrospective data from 210 positive EGFR mutation NSCLC patients, extracting 1316 radiomics features from CT images. Using the LASSO algorithm, we selected 10 radiomics features and 2 clinical features most relevant to the mutations. We built models with 7 ML approaches and assessed their performance through the receiver operating characteristic (ROC) curve. The radiomics model and combined model, which integrated radiomics features and relevant clinical factors, achieved an area under the curve (AUC) of 0.80 (95% confidence interval [CI] 0.79-0.81) and 0.86 (0.87-0.88), respectively, in predicting the T790M mutation. Our study presents a convenient and noninvasive radiomics-based ML model for predicting this mutation at the time of diagnosis, aiding in targeted treatment planning for NSCLC patients with EGFR mutations.