A comparison of machine learning methods for predicting recurrence and death after curative-intent radiotherapy for non-small cell lung cancer: Development and validation of multivariable clinical prediction models

Machine learning-based prognostic prediction and surgical guidance for intrahepatic cholangiocarcinoma

The prognosis following radical surgery for intrahepatic cholangiocarcinoma (ICC) is poor, and optimal follow-up strategies remain unclear, with ongoing debates regarding anatomic resection (AR) versus non-anatomic resection (NAR). This study included 680 patients from five hospitals, comparing a combination of eight feature screening methods and 11 machine learning algorithms to predict prognosis and construct integrated models. These models were assessed using nested cross-validation and various datasets, benchmarked against TNM stage and performance status. Evaluation metrics such as area under the curve (AUC) were applied. Prognostic models incorporating screened features showed superior performance compared to unselected models, with AR emerging as a key variable. Treatment recommendation models for surgical approaches, including DeepSurv, neural network multitask logistic regression (N-MTLR), and Kernel support vector machine (SVM), indicated that N-MTLR's recommendations were associated with survival benefits. Additionally, some patients identified as suitable for NAR were within groups previously considered for AR. In conclusion, three robust clinical models were developed to predict ICC prognosis and optimize surgical decisions, improving patient outcomes and supporting shared decision-making for patients and surgeons.

Time-dependent interpretable survival prediction model for second primary NSCLC patients

OBJECTIVE

Accurate predictive models for second primary non-small cell lung cancer (SP-NSCLC) are limited. This study aimed to develop and validate overall survival (OS) prediction models for SP-NSCLC patients using time-dependent interpretable survival machine learning algorithms.

METHODS

This study utilized data from the Surveillance, Epidemiology, and End Results (SEER) database, encompassing 8 and 12 registries, to extract data on patients aged 20-89 diagnosed with SP-NSCLC between 1988 and 2020. The dataset was divided into development, external temporal and spatial validation cohorts. Predictors included demographic, clinical, pathological and initial primary cancer-related features. Multiple survival machine learning algorithms were developed and validated, assessing model performance using C-index, time-dependent area under the receiver operating characteristic curve (time-AUC), and time-dependent Brier Score. The time-dependent interpretability analysis was employed to explore the time-dependent feature importance of key predictors.

RESULTS

The Blackboost model demonstrated excellent performance (C-index: 0.7517, and time-AUC: 0.8438), and good calibration (time-Brier Score of 0.0754). External validations and subgroup analyses demonstrated the robustness, generalizability, and fairness. Utilizing the optimal cutoff threshold, high-risk groups could be effectively identified. Surgery was the most critical predictor across the entire survival period. Combined stage (distant) and chemotherapy were the second most important predictors within 0 to 5 years, while age replaced from 5 to 20 years. Additionally, we developed an online visualization tool.

CONCLUSIONS

The Blackboost survival model achieved accurate, fair, and robust survival prediction for SP-NSCLC patients. Surgery, combined stage (distant), chemotherapy, and age contributed differently across various survival periods. The online visualization tool facilitated personalized survival predictions.

Predicting early stage lung cancer recurrence and survival from combined tumor motion amplitude and radiomics on free-breathing 4D-CT

BACKGROUND

Cancer control outcomes of lung cancer are hypothesized to be affected by several confounding factors, including tumor heterogeneity and patient history, which have been hypothesized to mitigate the dose delivery effectiveness when treated with radiation therapy. Providing an accurate predictive model to identify patients at risk would enable tailored follow-up strategies during treatment.

PURPOSE

Our goal is to demonstrate the added prognostic value of including tumor displacement amplitude in a predictive model that combines clinical features and computed tomography (CT) radiomics for 2-year recurrence and survival in non-small-cell lung cancer (NSCLC) patients treated with curative-intent stereotactic body radiation therapy.

METHODS

A cohort of 381 patients treated for primary lung cancer with radiotherapy was collected, each including a planning CT with a dosimetry plan, 4D-CT, and clinical information. From this cohort, 101 patients (26.5%) experienced cancer progression (locoregional/distant metastasis) or death within 2 years of the end of treatment. Imaging data was analyzed for radiomics features from the tumor segmented image, as well as tumor motion amplitude measured on 4D-CT. A random forest (RF) model was developed to predict the overall outcomes, which was compared to three other approaches - logistic regression, support vector machine, and convolutional neural networks.

RESULTS

A 6-fold cross-validation study yielded an area under the receiver operating characteristic curve of 72% for progression-free survival when combining clinical data with radiomics features and tumor motion using a RF model (72% sensitivity and 81% specificity). The combined model showed significant improvement compared to standard clinical data. Model performances for loco-regional recurrence and overall survival sub-outcomes were established at 73% and 70%, respectively. No comparative methods reached statistical significance in any data configuration.

CONCLUSIONS

Combined tumor respiratory motion and radiomics features from planning CT showed promising predictive value for 2-year tumor control and survival, indicating the potential need for improving motion management strategies in future studies using machine learning-based prognosis models.

Mime: A flexible machine-learning framework to construct and visualize models for clinical characteristics prediction and feature selection

The widespread use of high-throughput sequencing technologies has revolutionized the understanding of biology and cancer heterogeneity. Recently, several machine-learning models based on transcriptional data have been developed to accurately predict patients' outcome and clinical response. However, an open-source R package covering state-of-the-art machine-learning algorithms for user-friendly access has yet to be developed. Thus, we proposed a flexible computational framework to construct a machine learning-based integration model with elegant performance (Mime). Mime streamlines the process of developing predictive models with high accuracy, leveraging complex datasets to identify critical genes associated with prognosis. An in silico combined model based on de novo PIEZO1-associated signatures constructed by Mime demonstrated high accuracy in predicting the outcomes of patients compared with other published models. Furthermore, the PIEZO1-associated signatures could also precisely infer immunotherapy response by applying different algorithms in Mime. Finally, SDC1 selected from the PIEZO1-associated signatures demonstrated high potential as a glioma target. Taken together, our package provides a user-friendly solution for constructing machine learning-based integration models and will be greatly expanded to provide valuable insights into current fields. The Mime package is available on GitHub (https://github.com/l-magnificence/Mime).

Improved prognostication of overall survival after radiotherapy in lung cancer patients by an interpretable machine learning model integrating lung and tumor radiomics and clinical parameters

BACKGROUND

Accurate prognostication of overall survival (OS) for non-small cell lung cancer (NSCLC) patients receiving definitive radiotherapy (RT) is crucial for developing personalized treatment strategies. This study aims to construct an interpretable prognostic model that combines radiomic features extracted from normal lung and from primary tumor with clinical parameters. Our model aimed to clarify the complex, nonlinear interactions between these variables and enhance prognostic accuracy.

METHODS

We included 661 stage III NSCLC patients from three multi-national datasets: a training set (N = 349), test-set-1 (N = 229), and test-set-2 (N = 83), all undergoing definitive RT. A total of 104 distinct radiomic features were separately extracted from the regions of interest in the lung and the tumor. We developed four predictive models using eXtreme gradient boosting and selected the top 10 features based on the Shapley additive explanations (SHAP) values. These models were the tumor radiomic model (Model-T), lung radiomic model (Model-L), a combined radiomic model (Model-LT), and an integrated model incorporating clinical parameters (Model-LTC). Model performance was evaluated through Harrell's concordance index, Kaplan-Meier survival curves, time-dependent area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Interpretability was assessed using the SHAP framework.

RESULTS

Model-LTC exhibited superior performance, with notable predictive accuracy (C-index: training set, 0.87; test-set-2, 0.76) and time-dependent AUC above 0.75. Complex nonlinear relationships and interactions were evident among the model's variables.

CONCLUSION

The integration of radiomic and clinical factors within an interpretable framework significantly improved OS prediction. The SHAP analysis provided insightful interpretability, enhancing the model's clinical applicability and potential for aiding personalized treatment decisions.

Impact of the number of dissected lymph nodes on machine learning-based prediction of postoperative lung cancer recurrence: a single-hospital retrospective cohort study

BACKGROUND

The optimal number of lymph nodes to be dissected during lung cancer surgery to minimise the postoperative recurrence risk remains undetermined. This study aimed to elucidate the impact of the number of dissected lymph nodes on the risk of postoperative recurrence of non-small cell lung cancer (NSCLC) using machine learning algorithms and statistical analyses.

METHODS

We retrospectively analysed 650 patients with NSCLC who underwent complete resection. Five machine learning models were trained using clinicopathological variables to predict postoperative recurrence. The relationship between the number of dissected lymph nodes and postoperative recurrence was investigated in the best-performing model using Shapley additive explanations values and partial dependence plots. Multivariable Cox proportional hazard analysis was performed to estimate the HR for postoperative recurrence based on the number of dissected nodes.

RESULTS

The random forest model demonstrated superior predictive performance (area under the receiver operating characteristic curve: 0.92, accuracy: 0.83, F1 score: 0.64). The partial dependence plot of this model revealed a non-linear dependence of the number of dissected lymph nodes on recurrence prediction within the range of 0-20 nodes, with the weakest dependence at 10 nodes. A linear increase in the dependence was observed for ≥20 dissected nodes. A multivariable analysis revealed a significantly elevated risk of recurrence in the group with ≥20 dissected nodes in comparison to those with <20 nodes (adjusted HR, 1.45; 95% CI 1.003 to 2.087).

CONCLUSIONS

The number of dissected lymph nodes was significantly associated with the risk of postoperative recurrence of NSCLC. The risk of recurrence is minimised when approximately 10 nodes are dissected but may increase when >20 nodes are removed. Limiting lymph node dissection to approximately 20 nodes may help to preserve a favourable antitumour immune environment. These findings provide novel insights into the optimisation of lymph node dissection during lung cancer surgery.

A deep learning approach for overall survival prediction in lung cancer with missing values

BACKGROUND AND OBJECTIVE

In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges.

METHODS

We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time.

RESULTS

We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used.

CONCLUSIONS

The results show that our model not only outperforms the state-of-the-art's performance but also simplifies the analysis in the presence of missing data, by effectively eliminating the need to identify the most appropriate imputation strategy for predicting OS in NSCLC patients.

Estimated incidence of disruptions to event-free survival from non-metastatic cancers in New South Wales, Australia - a population-wide epidemiological study of linked cancer registry and treatment data

Introduction

Population cancer registries record primary cancer incidence, mortality and survival for whole populations, but not more timely outcomes such as cancer recurrence, secondary cancers or other complications that disrupt event-free survival. Nonetheless, indirect evidence may be inferred from treatment data to provide indicators of recurrence and like events, which can facilitate earlier assessment of care outcomes. The present study aims to infer such evidence by applying algorithms to linked cancer registry and treatment data obtained from hospitals and universal health insurance claims applicable to the New South Wales (NSW) population of Australia.

Materials and methods

Primary invasive cancers from the NSW Cancer Registry (NSWCR), diagnosed in 2001-2018 with localized or regionalized summary stage, were linked to treatment data for five common Australian cancers: breast, colon/rectum, lung, prostate, and skin (melanomas). Clinicians specializing in each cancer type provided guidance on expected treatment pathways and departures to indicate remission and subsequent recurrence or other disruptive events. A sample survey of patients and clinicians served to test initial population-wide results. Following consequent refinement of the algorithms, estimates of recurrence and like events were generated. Their plausibility was assessed by their correspondence with expected outcomes by tumor type and summary stage at diagnosis and by their associations with cancer survival.

Results

Kaplan-Meier product limit estimates indicated that 5-year cumulative probabilities of recurrence and other disruptive events were lower, and median times to these events longer, for those staged as localized rather than regionalized. For localized and regionalized cancers respectively, these were: breast - 7% (866 days) and 34% (570 days); colon/rectum - 15% (732 days) and 25% (641 days); lung - 46% (552 days) and 66% (404 days); melanoma - 11% (893 days) and 38% (611 days); and prostate - 14% (742 days) and 39% (478 days). Cases with markers for these events had poorer longer-term survival.

Conclusions

These population-wide estimates of recurrence and like events are approximations only. Absent more direct measures, they nonetheless may inform service planning by indicating population or treatment sub-groups at increased risk of recurrence and like events sooner than waiting for deaths to occur.

Machine learning model predicts airway stenosis requiring clinical intervention in patients after lung transplantation: a retrospective case-controlled study

BACKGROUND

Patients with airway stenosis (AS) are associated with considerable morbidity and mortality after lung transplantation (LTx). This study aims to develop and validate machine learning (ML) models to predict AS requiring clinical intervention in patients after LTx.

METHODS

Patients who underwent LTx between January 2017 and December 2019 were reviewed. The conventional logistic regression (LR) model was fitted by the independent risk factors which were determined by multivariate LR. The optimal ML model was determined based on 7 feature selection methods and 8 ML algorithms. Model performance was assessed by the area under the curve (AUC) and brier score, which were internally validated by the bootstrap method.

RESULTS

A total of 381 LTx patients were included, and 40 (10.5%) patients developed AS. Multivariate analysis indicated that male, pulmonary arterial hypertension, and postoperative 6-min walking test were significantly associated with AS (all P < 0.001). The conventional LR model showed performance with an AUC of 0.689 and brier score of 0.091. In total, 56 ML models were developed and the optimal ML model was the model fitted using a random forest algorithm with a determination coefficient feature selection method. The optimal model exhibited the highest AUC and brier score values of 0.760 (95% confidence interval [CI], 0.666-0.864) and 0.085 (95% CI, 0.058-0.117) among all ML models, which was superior to the conventional LR model.

CONCLUSIONS

The optimal ML model, which was developed by clinical characteristics, allows for the satisfactory prediction of AS in patients after LTx.

The Overlooked Cornerstone in Precise Medicine: Personalized Postoperative Surveillance Plan for NSCLC

Non-small cell lung cancer recurrence after curative-intent surgery remains a challenge despite advancements in treatment. We review postoperative surveillance strategies and their impact on overall survival, highlighting recommendations from clinical guidelines and controversies. Studies suggest no clear benefit from more intensive imaging, whereas computed tomography scans reveal promise in detecting recurrence. For early-stage disease, including ground-glass opacities and adenocarcinoma in situ or minimally invasive adenocarcinoma, less frequent surveillance may suffice owing to favorable prognosis. Liquid biopsy, especially circulating tumor deoxyribonucleic acid, holds potential for detecting minimal residual disease. Clinicopathologic factors and genomic profiles can also provide information about site-specific metastases. Machine learning may enable personalized surveillance plans on the basis of multi-omics data. Although precision medicine transforms non-small cell lung cancer treatment, optimizing surveillance strategies remains essential. Tailored surveillance strategies and emerging technologies may enhance early detection and improve patients' survival, necessitating further research for evidence-based protocols.

Exploring and clinical validation of prognostic significance and therapeutic implications of copper homeostasis-related gene dysregulation in acute myeloid leukemia

The patterns and biological functions of copper homeostasis-related genes (CHRGs) in acute myeloid leukemia (AML) remain unclear. We explored the patterns and biological functions of CHRGs in AML. Using independent cohorts, including TCGA-GTEx, GSE114868, GSE37642, and clinical samples, we identified 826 common differentially expressed genes. Specifically, 12 cuproptosis-related genes (e.g., ATP7A, ATP7B) were upregulated, while 17 cuproplasia-associated genes (e.g., ATOX1, ATP7A) were downregulated in AML. We used LASSO-Cox, Kaplan-Meier, and Nomogram analyses to establish prognostic risk models, effectively stratifying patients with AML into high- and low-risk groups. Subgroup analysis revealed that high-risk patients exhibited poorer overall survival and involvement in fatty acid metabolism, apoptosis, and glycolysis. Immune infiltration analysis indicated differences in immune cell composition, with notable increases in B cells, cytotoxic T cells, and memory T cells in the low-risk group, and increased monocytes and neutrophils in the high-risk group. Single-cell sequencing analysis corroborated the expression characteristics of critical CHRGs, such as MAPK1 and ATOX1, associated with the function of T, B, and NK cells. Drug sensitivity analysis suggested potential therapeutic agents targeting copper homeostasis, including Bicalutamide and Sorafenib. PCR validation confirmed the differential expression of 4 cuproptosis-related genes (LIPT1, SLC31A1, GCSH, and PDHA1) and 9 cuproplasia-associated genes (ATOX1, CCS, CP, MAPK1, SOD1, COA6, PDK1, DBH, and PDE3B) in AML cell line. Importantly, these genes serve as potential biomarkers for patient stratification and treatment. In conclusion, we shed light on the expression patterns and biological functions of CHRGs in AML. The developed risk models provided prognostic implications for patient survival, offering valuable information on the regulatory characteristics of CHRGs and potential avenues for personalized treatment in AML.

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.

Machine learning methods predict recurrence of pN3b gastric cancer after radical resection

Background

The incidence of stage pN3b gastric cancer (GC) is low, and the clinical prognosis is poor, with a high rate of postoperative recurrence. Machine learning (ML) methods can predict the recurrence of GC after surgery. However, the prognostic significance for pN3b remains unclear. Therefore, we aimed to predict the recurrence of pN3b through ML models.

Methods

This retrospective study included 336 patients with pN3b GC who underwent radical surgery. A 3-fold cross-validation was used to partition the participants into training and test cohorts. Linear combinations of new variable features were constructed using principal component analysis (PCA). Various ML algorithms, including random forest, support vector machine (SVM), logistic regression, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), and Gaussian naive Bayes (GNB), were utilized to establish a recurrence prediction model. Model performance was evaluated using the receiver operating characteristic (ROC) curve and the area under the curve (AUC). Python was used for the analysis of ML algorithms.

Results

Nine principal components with a cumulative variance interpretation rate of 90.71% were identified. The output results of the test set showed that random forests had the highest AUC (0.927) for predicting overall recurrence with an accuracy rate of 80.5%. Random forests had the highest AUC (0.940) for predicting regional recurrence with an accuracy of 89.7%. For predicting distant recurrence, random forests had the highest AUC (0.896) with an accuracy of 84.3%. For peritoneal recurrence, random forests had the highest AUC (0.923) with an accuracy of 83.3%.

Conclusions

ML can personalize the prediction of postoperative recurrence in patients with GC with stage pN3b.

Preliminary Evidence of the Use of Generative AI in Health Care Clinical Services: Systematic Narrative Review

BACKGROUND

Generative artificial intelligence tools and applications (GenAI) are being increasingly used in health care. Physicians, specialists, and other providers have started primarily using GenAI as an aid or tool to gather knowledge, provide information, train, or generate suggestive dialogue between physicians and patients or between physicians and patients' families or friends. However, unless the use of GenAI is oriented to be helpful in clinical service encounters that can improve the accuracy of diagnosis, treatment, and patient outcomes, the expected potential will not be achieved. As adoption continues, it is essential to validate the effectiveness of the infusion of GenAI as an intelligent technology in service encounters to understand the gap in actual clinical service use of GenAI.

OBJECTIVE

This study synthesizes preliminary evidence on how GenAI assists, guides, and automates clinical service rendering and encounters in health care The review scope was limited to articles published in peer-reviewed medical journals.

METHODS

We screened and selected 0.38% (161/42,459) of articles published between January 1, 2020, and May 31, 2023, identified from PubMed. We followed the protocols outlined in the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to select highly relevant studies with at least 1 element on clinical use, evaluation, and validation to provide evidence of GenAI use in clinical services. The articles were classified based on their relevance to clinical service functions or activities using the descriptive and analytical information presented in the articles.

RESULTS

Of 161 articles, 141 (87.6%) reported using GenAI to assist services through knowledge access, collation, and filtering. GenAI was used for disease detection (19/161, 11.8%), diagnosis (14/161, 8.7%), and screening processes (12/161, 7.5%) in the areas of radiology (17/161, 10.6%), cardiology (12/161, 7.5%), gastrointestinal medicine (4/161, 2.5%), and diabetes (6/161, 3.7%). The literature synthesis in this study suggests that GenAI is mainly used for diagnostic processes, improvement of diagnosis accuracy, and screening and diagnostic purposes using knowledge access. Although this solves the problem of knowledge access and may improve diagnostic accuracy, it is oriented toward higher value creation in health care.

CONCLUSIONS

GenAI informs rather than assisting or automating clinical service functions in health care. There is potential in clinical service, but it has yet to be actualized for GenAI. More clinical service-level evidence that GenAI is used to streamline some functions or provides more automated help than only information retrieval is needed. To transform health care as purported, more studies related to GenAI applications must automate and guide human-performed services and keep up with the optimism that forward-thinking health care organizations will take advantage of GenAI.

AI/ML advances in non-small cell lung cancer biomarker discovery

Lung cancer is the leading cause of cancer deaths among both men and women, representing approximately 25% of cancer fatalities each year. The treatment landscape for non-small cell lung cancer (NSCLC) is rapidly evolving due to the progress made in biomarker-driven targeted therapies. While advancements in targeted treatments have improved survival rates for NSCLC patients with actionable biomarkers, long-term survival remains low, with an overall 5-year relative survival rate below 20%. Artificial intelligence/machine learning (AI/ML) algorithms have shown promise in biomarker discovery, yet NSCLC-specific studies capturing the clinical challenges targeted and emerging patterns identified using AI/ML approaches are lacking. Here, we employed a text-mining approach and identified 215 studies that reported potential biomarkers of NSCLC using AI/ML algorithms. We catalogued these studies with respect to BEST (Biomarkers, EndpointS, and other Tools) biomarker sub-types and summarized emerging patterns and trends in AI/ML-driven NSCLC biomarker discovery. We anticipate that our comprehensive review will contribute to the current understanding of AI/ML advances in NSCLC biomarker research and provide an important catalogue that may facilitate clinical adoption of AI/ML-derived biomarkers.

Artificial intelligence-based recurrence prediction outperforms classical histopathological methods in pulmonary adenocarcinoma biopsies

INTRODUCTION

Between 10 and 50% of early-stage lung adenocarcinoma patients experience local or distant recurrence. Histological parameters such as a solid or micropapillary growth pattern are well-described risk factors for recurrence. However, not every patient presenting with such a pattern will develop recurrence. Designing a model which can more accurately predict recurrence on small biopsy samples can aid the stratification of patients for surgery, (neo-)adjuvant therapy, and follow-up.

MATERIAL AND METHODS

In this study, a statistical model on biopsies fed with histological data from early and advanced-stage lung adenocarcinomas was developed to predict recurrence after surgical resection. Additionally, a convolutional neural network (CNN)-based artificial intelligence (AI) classification model, named AI-based Lung Adenocarcinoma Recurrence Predictor (AILARP), was trained to predict recurrence, with an ImageNet pre-trained EfficientNet that was fine-tuned on lung adenocarcinoma biopsies using transfer learning. Both models were validated using the same biopsy dataset to ensure that an accurate comparison was demonstrated.

RESULTS

The statistical model had an accuracy of 0.49 for all patients when using histology data only. The AI classification model yielded a test accuracy of 0.70 and 0.82 and an area under the curve (AUC) of 0.74 and 0.87 on patch-wise and patient-wise hematoxylin and eosin (H&E) stained whole slide images (WSIs), respectively.

CONCLUSION

AI classification outperformed the traditional clinical approach for recurrence prediction on biopsies by a fair margin. The AI classifier may stratify patients according to their recurrence risk, based only on small biopsies. This model warrants validation in a larger lung biopsy cohort.

Exploring the efficacy of artificial neural networks in predicting lung cancer recurrence: a retrospective study based on patient records

Background

Lung cancer remains a significant public health concern, accounting for a considerable number of cancer-related deaths worldwide. Neural networks have emerged as a promising tool that can aid in the diagnosis and treatment of various cancers. Consequently, there has been a growing interest in exploring the potential of artificial intelligence (AI) methods in medicine. The present study aimed to evaluate the effectiveness of a neural network in predicting lung cancer recurrence.

Methods

The study employed retrospective data from 2,296 medical records of patients diagnosed with lung cancer and admitted to the Warmińsko-Mazurskie Center for Lung Diseases in Olsztyn, Poland. The statistical software STATISTICA 7.1, equipped with the Neural Networks module (StatSoft Inc., Tulsa, USA), was utilized to analyze the data. The neural network model was trained using patient information regarding gender, treatment, smoking status, family history, and symptoms of cancer.

Results

The study employed a multilayer perceptron neural network with a two-phase learning process. The network demonstrated high predictive ability, as indicated by the percentage of correct classifications, which amounted to 87.5%, 89.1%, and 89.9% for the training, validation, and test sets, respectively.

Conclusions

The findings of this study support the potential usefulness of a neural network-based predictive model in assessing the risk of lung cancer recurrence. Further research is warranted to validate these findings and to explore AI's broader implications in cancer diagnosis and treatment.

A life-threatening bleeding prediction model for immune thrombocytopenia based on personalized machine learning: a nationwide prospective cohort study

Rare but critical bleeding events in primary immune thrombocytopenia (ITP) present life-threatening complications in patients with ITP, which severely affect their prognosis, quality of life, and treatment decisions. Although several studies have investigated the risk factors related to critical bleeding in ITP, large sample size data, consistent definitions, large-scale multicenter findings, and prediction models for critical bleeding events in patients with ITP are unavailable. For the first time, in this study, we applied the newly proposed critical ITP bleeding criteria by the International Society on Thrombosis and Hemostasis for large sample size data and developed the first machine learning (ML)-based online application for predict critical ITP bleeding. In this research, we developed and externally tested an ML-based model for determining the risk of critical bleeding events in patients with ITP using large multicenter data across China. Retrospective data from 8 medical centers across the country were obtained for model development and prospectively tested in 39 medical centers across the country over a year. This system exhibited good predictive capabilities for training, validation, and test datasets. This convenient web-based tool based on a novel algorithm can rapidly identify the bleeding risk profile of patients with ITP and facilitate clinical decision-making and reduce the occurrence of adversities.

Immunodiagnosis - the promise of personalized immunotherapy

Immunotherapy showed remarkable efficacy in several cancer types. However, the majority of patients do not benefit from immunotherapy. Evaluating tumor heterogeneity and immune status before treatment is key to identifying patients that are more likely to respond to immunotherapy. Demographic characteristics (such as sex, age, and race), immune status, and specific biomarkers all contribute to response to immunotherapy. A comprehensive immunodiagnostic model integrating all these three dimensions by artificial intelligence would provide valuable information for predicting treatment response. Here, we coined the term "immunodiagnosis" to describe the blueprint of the immunodiagnostic model. We illustrated the features that should be included in immunodiagnostic model and the strategy of constructing the immunodiagnostic model. Lastly, we discussed the incorporation of this immunodiagnosis model in clinical practice in hopes of improving the prognosis of tumor immunotherapy.

The role of artificial intelligence based on PET/CT radiomics in NSCLC: Disease management, opportunities, and challenges

Objectives

Lung cancer has been widely characterized through radiomics and artificial intelligence (AI). This review aims to summarize the published studies of AI based on positron emission tomography/computed tomography (PET/CT) radiomics in non-small-cell lung cancer (NSCLC).

Materials and methods

A comprehensive search of literature published between 2012 and 2022 was conducted on the PubMed database. There were no language or publication status restrictions on the search. About 127 articles in the search results were screened and gradually excluded according to the exclusion criteria. Finally, this review included 39 articles for analysis.

Results

Classification is conducted according to purposes and several studies were identified at each stage of disease:1) Cancer detection (n=8), 2) histology and stage of cancer (n=11), 3) metastases (n=6), 4) genotype (n=6), 5) treatment outcome and survival (n=8). There is a wide range of heterogeneity among studies due to differences in patient sources, evaluation criteria and workflow of radiomics. On the whole, most models show diagnostic performance comparable to or even better than experts, and the common problems are repeatability and clinical transformability.

Conclusion

AI-based PET/CT Radiomics play potential roles in NSCLC clinical management. However, there is still a long way to go before being translated into clinical application. Large-scale, multi-center, prospective research is the direction of future efforts, while we need to face the risk of repeatability of radiomics features and the limitation of access to large databases.

A CT-based transfer learning approach to predict NSCLC recurrence: The added-value of peritumoral region

Non-small cell lung cancer (NSCLC) represents 85% of all new lung cancer diagnoses and presents a high recurrence rate after surgery. Thus, an accurate prediction of recurrence risk in NSCLC patients at diagnosis could be essential to designate risk patients to more aggressive medical treatments. In this manuscript, we apply a transfer learning approach to predict recurrence in NSCLC patients, exploiting only data acquired during its screening phase. Particularly, we used a public radiogenomic dataset of NSCLC patients having a primary tumor CT image and clinical information. Starting from the CT slice containing the tumor with maximum area, we considered three different dilatation sizes to identify three Regions of Interest (ROIs): CROP (without dilation), CROP 10 and CROP 20. Then, from each ROI, we extracted radiomic features by means of different pre-trained CNNs. The latter have been combined with clinical information; thus, we trained a Support Vector Machine classifier to predict the NSCLC recurrence. The classification performances of the devised models were finally evaluated on both the hold-out training and hold-out test sets, in which the original sample has been previously divided. The experimental results showed that the model obtained analyzing CROP 20 images, which are the ROIs containing more peritumoral area, achieved the best performances on both the hold-out training set, with an AUC of 0.73, an Accuracy of 0.61, a Sensitivity of 0.63, and a Specificity of 0.60, and on the hold-out test set, with an AUC value of 0.83, an Accuracy value of 0.79, a Sensitivity value of 0.80, and a Specificity value of 0.78. The proposed model represents a promising procedure for early predicting recurrence risk in NSCLC patients.

Application of several machine learning algorithms for the prediction of afatinib treatment outcome in advanced-stage EGFR-mutated non-small-cell lung cancer

BACKGROUND

The present study aimed to evaluate the performance of several machine learning (ML) algorithms in predicting 1-year afatinib continuation and 2-year survival after afatinib initiation and to identify the differences in survival outcomes between ML-classified strata.

METHODS

Data that were also used in the RESET study were retrospectively collected from 16 hospitals in South Korea. A stratified random sampling method was applied to split the data into training and test sets (70:30 split ratio). Clinical information, such as age, sex, tumor stage, smoking, performance status, metastasis, type of metastasis, dose adjustment, and pathologic information on EGFR mutations were inputted. Training was performed using eight ML algorithms: logistic regression, decision tree, deep neural network, random forest, support vector machine, boosting, bagging, and the naïve Bayes classifier. The model performance was assessed based on sensitivity, specificity, and accuracy. Area under the receiver operator characteristic curve (AUC) was calculated and compared between the ML models using DeLong's test. A Kaplan-Meier (KM) curve was used to visualize the identified strata obtained from the ML models.

RESULTS

No significant differences in the input variables were observed between the training and test datasets. The best-performing models were support vector machine in predicting 1-year afatinib continuation (AUC 0.626) and decision tree in 2-year survival after afatinib start (AUC 0.644), although the performances of the ML models were comparable and did not display any predictive roles. KM analysis and log-rank test revealed significant differences between the strata identified from the ML model (p < 0.001) in terms of both time-on-treatment (TOT) and overall survival (OS).

CONCLUSION

The performances of ML models in our study found no discernible roles in predicting afatinib-related outcomes, although the identified strata revealed different TOT and OS in the KM analysis. This implies the strength of ML in predicting the survival outcome, as well as the limitation of electronic medical record-based variables in ML algorithms. Careful consideration of variable inclusion is likely to improve the general model performance.

Current status and future developments in predicting outcomes in radiation oncology

Advancements in data-driven technologies and the inclusion of information-rich multiomics features have significantly improved the performance of outcomes modeling in radiation oncology. For this current trend to be sustainable, challenges related to robust data modeling such as small sample size, low size to feature ratio, noisy data, as well as issues related to algorithmic modeling such as complexity, uncertainty, and interpretability, need to be mitigated if not resolved. Emerging computational technologies and new paradigms such as federated learning, human-in-the-loop, quantum computing, and novel interpretability methods show great potential in overcoming these challenges and bridging the gap towards precision outcome modeling in radiotherapy. Examples of these promising technologies will be presented and their potential role in improving outcome modeling will be discussed.

Prediction of early-stage melanoma recurrence using clinical and histopathologic features

Prognostic analysis for early-stage (stage I/II) melanomas is of paramount importance for customized surveillance and treatment plans. Since immune checkpoint inhibitors have recently been approved for stage IIB and IIC melanomas, prognostic tools to identify patients at high risk of recurrence have become even more critical. This study aims to assess the effectiveness of machine-learning algorithms in predicting melanoma recurrence using clinical and histopathologic features from Electronic Health Records (EHRs). We collected 1720 early-stage melanomas: 1172 from the Mass General Brigham healthcare system (MGB) and 548 from the Dana-Farber Cancer Institute (DFCI). We extracted 36 clinicopathologic features and used them to predict the recurrence risk with supervised machine-learning algorithms. Models were evaluated internally and externally: (1) five-fold cross-validation of the MGB cohort; (2) the MGB cohort for training and the DFCI cohort for testing independently. In the internal and external validations, respectively, we achieved a recurrence classification performance of AUC: 0.845 and 0.812, and a time-to-event prediction performance of time-dependent AUC: 0.853 and 0.820. Breslow tumor thickness and mitotic rate were identified as the most predictive features. Our results suggest that machine-learning algorithms can extract predictive signals from clinicopathologic features for early-stage melanoma recurrence prediction, which will enable the identification of patients that may benefit from adjuvant immunotherapy.

Gross tumour volume radiomics for prognostication of recurrence & death following radical radiotherapy for NSCLC

Recurrence occurs in up to 36% of patients treated with curative-intent radiotherapy for NSCLC. Identifying patients at higher risk of recurrence for more intensive surveillance may facilitate the earlier introduction of the next line of treatment. We aimed to use radiotherapy planning CT scans to develop radiomic classification models that predict overall survival (OS), recurrence-free survival (RFS) and recurrence two years post-treatment for risk-stratification. A retrospective multi-centre study of >900 patients receiving curative-intent radiotherapy for stage I-III NSCLC was undertaken. Models using radiomic and/or clinical features were developed, compared with 10-fold cross-validation and an external test set, and benchmarked against TNM-stage. Respective validation and test set AUCs (with 95% confidence intervals) for the radiomic-only models were: (1) OS: 0.712 (0.592–0.832) and 0.685 (0.585–0.784), (2) RFS: 0.825 (0.733–0.916) and 0.750 (0.665–0.835), (3) Recurrence: 0.678 (0.554–0.801) and 0.673 (0.577–0.77). For the combined models: (1) OS: 0.702 (0.583–0.822) and 0.683 (0.586–0.78), (2) RFS: 0.805 (0.707–0.903) and 0·755 (0.672–0.838), (3) Recurrence: 0·637 (0.51–0.·765) and 0·738 (0.649–0.826). Kaplan-Meier analyses demonstrate OS and RFS difference of >300 and >400 days respectively between low and high-risk groups. We have developed validated and externally tested radiomic-based prediction models. Such models could be integrated into the routine radiotherapy workflow, thus informing a personalised surveillance strategy at the point of treatment. Our work lays the foundations for future prospective clinical trials for quantitative personalised risk-stratification for surveillance following curative-intent radiotherapy for NSCLC.

Machine learning models predict lymph node metastasis in patients with stage T1-T2 esophageal squamous cell carcinoma

Background

For patients with stage T1-T2 esophageal squamous cell carcinoma (ESCC), accurately predicting lymph node metastasis (LNM) remains challenging. We aimed to investigate the performance of machine learning (ML) models for predicting LNM in patients with stage T1-T2 ESCC.

Methods

Patients with T1-T2 ESCC at three centers between January 2014 and December 2019 were included in this retrospective study and divided into training and external test sets. All patients underwent esophagectomy and were pathologically examined to determine the LNM status. Thirty-six ML models were developed using six modeling algorithms and six feature selection techniques. The optimal model was determined by the bootstrap method. An external test set was used to further assess the model’s generalizability and effectiveness. To evaluate prediction performance, the area under the receiver operating characteristic curve (AUC) was applied.

Results

Of the 1097 included patients, 294 (26.8%) had LNM. The ML models based on clinical features showed good predictive performance for LNM status, with a median bootstrapped AUC of 0.659 (range: 0.592, 0.715). The optimal model using the naive Bayes algorithm with feature selection by determination coefficient had the highest AUC of 0.715 (95% CI: 0.671, 0.763). In the external test set, the optimal ML model achieved an AUC of 0.752 (95% CI: 0.674, 0.829), which was superior to that of T stage (0.624, 95% CI: 0.547, 0.701).

Conclusions

ML models provide good LNM prediction value for stage T1-T2 ESCC patients, and the naive Bayes algorithm with feature selection by determination coefficient performed best.