Clinical decision support algorithm based on machine learning to assess the clinical response to anti-programmed death-1 therapy in patients with non-small-cell lung cancer

Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer

Immunotherapy is improving the survival of patients with metastatic non-small cell lung cancer (NSCLC), yet reliable biomarkers are needed to identify responders prospectively and optimize patient care. In this study, we explore the benefits of multimodal approaches to predict immunotherapy outcome using multiple machine learning algorithms and integration strategies. We analyze baseline multimodal data from a cohort of 317 metastatic NSCLC patients treated with first-line immunotherapy, including positron emission tomography images, digitized pathological slides, bulk transcriptomic profiles, and clinical information. Testing multiple integration strategies, most of them yield multimodal models surpassing both the best unimodal models and established univariate biomarkers, such as PD-L1 expression. Additionally, several multimodal combinations demonstrate improved patient risk stratification compared to models built with routine clinical features only. Our study thus provides evidence of the superiority of multimodal over unimodal approaches, advocating for the collection of large multimodal NSCLC datasets to develop and validate robust and powerful immunotherapy biomarkers.

Noninvasive early identification of durable clinical benefit from immune checkpoint inhibition: a prospective multicenter study (NCT04566432)

Immune checkpoint inhibitors (ICIs) have changed the treatment landscape for patients with non-small cell lung cancer (NSCLC). In spite of durable responses in some patients, many patients develop early disease progression during the ICI treatment. Thus, early identification of patients with no durable benefit would facilitate the clinical decision for these patients. In this prospective, multicenter study, 101 non-EGFR/ALK patients who received ICI treatment were enrolled after screening 328 stage III-IV NSCLC patients. At the date of cutoff, 83 patients were eligible for ICI efficacy evaluation, with 56 patients having progress-free survival (PFS) over 6 months, which was defined as durable clinical benefit (DCB). A multimodal model was established by integrating normalized bTMB, early dynamic of ctDNA and the first RECIST response. This model could robustly predict DCB with area under the curve (AUC) of 0.878, sensitivity of 79.2% at 86.4% specificity (accuracy = 80.0%). This model was further validated in the independent cohort of the DIREct-On study with AUC of 0.887, sensitivity of 94.7% at 85.3% specificity (accuracy = 90.3%). Patients with higher predict scores had substantially longer PFS than those with lower scores (training cohort: median PFS 13.6 vs 4.2 months, P < 0.001, HR = 0.24; validation cohort: median PFS 11.0 vs 2.2 months, P < 0.001, HR = 0.17). Taken together, these results demonstrate that integrating early changes of ctDNA, normalized bTMB, and the first RECIST response can provide accurate, noninvasive, and early prediction of durable benefits for NSCLC patients treated with ICIs. Further prospective studies are warranted to validate these findings and guide clinical decision-making for optimal immunotherapy in NSCLC patients.

Federated Learning Survival Model and Potential Radiotherapy Decision Support Impact Assessment for Non-small Cell Lung Cancer Using Real-World Data

AIMS

The objective of this study was to develop a two-year overall survival model for inoperable stage I-III non-small cell lung cancer (NSCLC) patients using routine radiation oncology data over a federated (distributed) learning network and evaluate the potential of decision support for curative versus palliative radiotherapy.

METHODS

A federated infrastructure of data extraction, de-identification, standardisation, image analysis, and modelling was installed for seven clinics to obtain clinical and imaging features and survival information for patients treated in 2011-2019. A logistic regression model was trained for the 2011-2016 curative patient cohort and validated for the 2017-2019 cohort. Features were selected with univariate and model-based analysis and optimised using bootstrapping. System performance was assessed by the receiver operating characteristic (ROC) and corresponding area under curve (AUC), C-index, calibration metrics and Kaplan-Meier survival curves, with risk groups defined by model probability quartiles. Decision support was evaluated using a case-control analysis using propensity matching between treatment groups.

RESULTS

1655 patient datasets were included. The overall model AUC was 0.68. Fifty-eight percent of patients treated with palliative radiotherapy had a low-to-moderate risk prediction according to the model, with survival times not significantly different (p = 0.87 and 0.061) from patients treated with curative radiotherapy classified as high-risk by the model. When survival was simulated by risk group and model-indicated treatment, there was an estimated 11% increase in survival rate at two years (p < 0.01).

CONCLUSION

Federated learning over multiple institution data can be used to develop and validate decision support systems for lung cancer while quantifying the potential impact of their use in practice. This paves the way for personalised medicine, where decisions can be based more closely on individual patient details from routine care.

Proteomic and metabolomic features in patients with HCC responding to lenvatinib and anti-PD1 therapy

Combination therapy (lenvatinib/programmed death-1 inhibitor) is effective for treating unresectable hepatocellular carcinoma (uHCC). We reveal that responders have better overall and progression-free survival, as well as high tumor mutation burden and special somatic variants. We analyze the proteome and metabolome of 82 plasma samples from patients with hepatocellular carcinoma (HCC; n = 51) and normal controls (n = 15), revealing that individual differences outweigh treatment differences. Responders exhibit enhanced activity in the alternative/lectin complement pathway and higher levels of lysophosphatidylcholines (LysoPCs), predicting a favorable prognosis. Non-responders are enriched for immunoglobulins, predicting worse outcomes. Compared to normal controls, HCC plasma proteins show acute inflammatory response and platelet activation, while LysoPCs decrease. Combination therapy increases LysoPCs/phosphocholines in responders. Logistic regression/random forest models using metabolomic features achieve good performance in the prediction of responders. Proteomic analysis of cancer tissues unveils molecular features that are associated with side effects in responders receiving combination therapy. In conclusion, our analysis identifies plasma features associated with uHCC responders to combination therapy.

Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review

BACKGROUND

The widespread use of immune checkpoint inhibitors (ICIs) has revolutionised treatment of multiple cancer types. However, selecting patients who may benefit from ICI remains challenging. Artificial intelligence (AI) approaches allow exploitation of high-dimension oncological data in research and development of precision immuno-oncology.

MATERIALS AND METHODS

We conducted a systematic literature review of peer-reviewed original articles studying the ICI efficacy prediction in cancer patients across five data modalities: genomics (including genomics, transcriptomics, and epigenomics), radiomics, digital pathology (pathomics), and real-world and multimodality data.

RESULTS

A total of 90 studies were included in this systematic review, with 80% published in 2021-2022. Among them, 37 studies included genomic, 20 radiomic, 8 pathomic, 20 real-world, and 5 multimodal data. Standard machine learning (ML) methods were used in 72% of studies, deep learning (DL) methods in 22%, and both in 6%. The most frequently studied cancer type was non-small-cell lung cancer (36%), followed by melanoma (16%), while 25% included pan-cancer studies. No prospective study design incorporated AI-based methodologies from the outset; rather, all implemented AI as a post hoc analysis. Novel biomarkers for ICI in radiomics and pathomics were identified using AI approaches, and molecular biomarkers have expanded past genomics into transcriptomics and epigenomics. Finally, complex algorithms and new types of AI-based markers, such as meta-biomarkers, are emerging by integrating multimodal/multi-omics data.

CONCLUSION

AI-based methods have expanded the horizon for biomarker discovery, demonstrating the power of integrating multimodal data from existing datasets to discover new meta-biomarkers. While most of the included studies showed promise for AI-based prediction of benefit from immunotherapy, none provided high-level evidence for immediate practice change. A priori planned prospective trial designs are needed to cover all lifecycle steps of these software biomarkers, from development and validation to integration into clinical practice.

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.

Bayesian network enables interpretable and state-of-the-art prediction of immunotherapy responses in cancer patients

Immune checkpoint inhibitors, especially PD-1/PD-L1 blockade, have revolutionized cancer treatment and brought tremendous benefits to patients who otherwise would have had a limited prognosis. Nonetheless, only a small fraction of patients respond to immunotherapy, and the costs and side effects of immune checkpoint inhibitors cannot be ignored. With the advent of machine and deep learning, clinical and genetic data have been used to stratify patient responses to immunotherapy. Unfortunately, these approaches have typically been "black-box" methods that are unable to explain their predictions, thereby hindering their responsible clinical application. Herein, we developed a "white-box" Bayesian network model that achieves accurate and interpretable predictions of immunotherapy responses against nonsmall cell lung cancer (NSCLC). This tree-augmented naïve Bayes (TAN) model accurately predicted durable clinical benefits and distinguished two clinically significant subgroups with distinct prognoses. Furthermore, our state-of-the-art white-box TAN approach achieved greater accuracy than previous methods. We hope that our model will guide clinicians in selecting NSCLC patients who truly require immunotherapy and expect our approach to be easily applied to other types of cancer.

Subtyping of advanced lung cancer based on PD-L1 expression, tumor histopathology and mutation burden (EGFR and KRAS): a study from North India

Immune checkpoint inhibitor (PD-L1) therapy of advanced non-small-cell lung cancer (NSCLC) has variable outcomes. Tumor subtypes based on PD-L1 expression, histopathology, mutation burden is required for patient stratification and formulation of treatment guidelines. Lung cancers (n=57) diagnosed at Pathology department, VPCI (2018-2021) were retrospectively analyzed. PD-L1(SP263) expressed by tumor cells [low (<1%), medium (1-49%), high (≥50%)] was correlated with histopathology, microenvironment, EGFR, KRAS expression. Patients were categorized into high and low risk based on their: i) gender: males (n=47, 30-89 years), females (n=10, 45-80 years); ii) smoking history: males 26/47 (45.61%), females 1/10 (10%); iii) tumor subtyping: squamous cell carcinoma 15/57 (26.32%), adenocarcinoma 6/57 (17.54%), NSCLC-undifferentiated 24/57 (42.10%), adenosquamous carcinoma 5/57 (8.77 %), carcinosarcoma 4/57 (7.02%), small cell carcinoma 1/57 (1.75%); iv) inflammatory tumor microenvironment/TILs 44/57 (77.1%); iv) PD-L1 positivity-31/57 (54.3%); v) concomitant EGFR/KRAS positivity. PD-L1positive cases showed squamous/undifferentiated histopathology, concomitant EGFR+ (9/20, 45%) and KRAS+ (8/15, 53.3%), smoking+ (21/31,67.74%).PD-L1 negative cases (26/57, 45.6%), were EGFR+ (2/14, 14.28%) and KRAS+ (6/19, 31.5%). The high-risk lung cancer subtypes show squamous/undifferentiated histopathology, inflammatory microenvironment, male preponderance, smoking history, higher concomitant PD-L1, KRAS and EGFR positivity. Lung cancer subtyping can predict clinical response/resistance of patients prior to initiation of PD-L1 inhibitor therapies and can be used to guide therapy.

Application of machine learning in the prediction of deficient mismatch repair in patients with colorectal cancer based on routine preoperative characterization

Simple summary

Detecting deficient mismatch repair (dMMR) in patients with colorectal cancer is essential for clinical decision-making, including evaluation of prognosis, guidance of adjuvant chemotherapy and immunotherapy, and primary screening for Lynch syndrome. However, outside of tertiary care centers, existing detection methods are not widely disseminated and highly depend on the experienced pathologist. Therefore, it is of great clinical significance to develop a broadly accessible and low-cost tool for dMMR prediction, particularly prior to surgery. In this study, we developed a convenient and reliable model for predicting dMMR status in CRC patients on routine preoperative characterization utilizing multiple machine learning algorithms. This model will work as an automated screening tool for identifying patients suitable for mismatch repair testing and consequently for improving the detection rate of dMMR, while reducing unnecessary labor and cost in patients with proficient mismatch repair.

Background

Deficient mismatch repair (dMMR) indicates a sustained anti-tumor immune response and has a favorable prognosis in patients with colorectal cancer (CRC). Although all CRC patients are recommended to undergo dMMR testing after surgery, current diagnostic approaches are not available for all country hospitals and patients. Therefore, efficient and low-cost predictive models for dMMR, especially for preoperative evaluations, are warranted.

Methods

A large scale of 5596 CRC patients who underwent surgical resection and mismatch repair testing were enrolled and randomly divided into training and validation cohorts. The clinical features exploited for predicting dMMR comprised the demographic characteristics, preoperative laboratory data, and tumor burden information. Machine learning (ML) methods involving eight basic algorithms, ensemble learning methods, and fusion algorithms were adopted with 10-fold cross-validation, and their performance was evaluated based on the area under the receiver operating characteristic curve (AUC) and calibration curves. The clinical net benefits were assessed using a decision curve analysis (DCA), and a nomogram was developed to facilitate model clinical practicality.

Results

All models achieved an AUC of nearly 0.80 in the validation cohort, with the stacking model exhibiting the best performance (AUC = 0.832). Logistical DCA revealed that the stacking model yielded more clinical net benefits than the conventional regression models. In the subgroup analysis, the stacking model also predicted dMMR regardless of the clinical stage. The nomogram showed a favorable consistence with the actual outcome in the calibration curve.

Conclusion

With the aid of ML algorithms, we developed a novel and robust model for predicting dMMR in CRC patients with satisfactory discriminative performance and designed a user-friendly and convenient nomogram.

A Transfer Learning Approach with a Convolutional Neural Network for the Classification of Lung Carcinoma

Lung cancer is among the most hazardous types of cancer in humans. The correct diagnosis of pathogenic lung disease is critical for medication. Traditionally, determining the pathological form of lung cancer involves an expensive and time-consuming process investigation. Lung cancer is a leading cause of mortality worldwide, with lung tissue nodules being the most prevalent way for doctors to identify it. The proposed model is based on robust deep-learning-based lung cancer detection and recognition. This study uses a deep neural network as an extraction of features approach in a computer-aided diagnosing (CAD) system to assist in detecting lung illnesses at high definition. The proposed model is categorized into three phases: first, data augmentation is performed, classification is then performed using the pretrained CNN model, and lastly, localization is completed. The amount of obtained data in medical image assessment is occasionally inadequate to train the learning network. We train the classifier using a technique known as transfer learning (TL) to solve the issue introduced into the process. The proposed methodology offers a non-invasive diagnostic tool for use in the clinical assessment that is effective. The proposed model has a lower number of parameters that are much smaller compared to the state-of-the-art models. We also examined the desired dataset's robustness depending on its size. The standard performance metrics are used to assess the effectiveness of the proposed architecture. In this dataset, all TL techniques perform well, and VGG 16, VGG 19, and Xception for 20 epoch structure are compared. Preprocessing functions as a wonderful bridge to build a dependable model and eventually helps to forecast future scenarios by including the interface at a faster phase for any model. At the 20th epoch, the accuracy of VGG 16, VGG 19, and Xception is 98.83 percent, 98.05 percent, and 97.4 percent.

Effect of Family Participatory Nursing Model Based on WeChat Platform on Psychological Elasticity and Quality of Life of Patients with Lung Cancer

Objective

To explore the effect of family participatory nursing model based on WeChat platform on psychological elasticity and life quality of patients with lung cancer.

Methods

One hundred patients with lung cancer treated in our hospital from February 2019 to April 2021 were enrolled. The patients were randomly assigned into control group and study group. The control group received routine nursing and the study group received family participatory nursing model based on WeChat platform. The scores of nursing satisfaction, self-feeling burden, symptom group assessment scale, family care index, and compliance and life quality were compared.

Results

First of all, we compared the nursing satisfaction: the study group was very satisfied in 25 cases, satisfactory in 20 cases, general in 5 cases, the satisfaction rate was 100.00%; the control group was very satisfied in 14 cases, satisfactory in 17 cases, general in 13 cases, dissatisfied in 6 cases, and the satisfaction rate was 88.00%. Compared between the two groups, the nursing satisfaction in the study group was higher compared to the control group (P < 0.05). Secondly, we compared the self-perceived burden, the emotional burden, physical burden, and economic burden and total scores of the study group were lower compared to the control group (P < 0.05). Comparing the scores of symptom group evaluation scale, the scores of respiratory symptoms, fatigue symptoms, psychological and emotional symptoms, digestive tract symptoms, and nervous system symptoms in the study group were lower compared to the control group (P < 0.05). In terms of the family care index of the two groups, the scores of fitness, cooperation, length, emotion, and intimacy in the study group were higher compared to the control group (P < 0.05). Comparison of compliance, the study group was very compliant in 42 cases, compliant in 7 cases, noncompliant in 1 case, the compliance rate was 98.00%; the control group was very compliant in 24 cases, compliant in 20 cases, noncompliant in 6 cases, the compliance rate was 88.00%. The compliance rate in the study group was higher compared to the control group (P < 0.05). Finally, we compared the scores of qualities of life. Before nursing, there exhibited no significant difference (P > 0.05). The scores of physiological function, psychological function, social function, and health self-cognition in the study group were lower compared to the control group (P < 0.05).

Conclusion

The family participatory nursing model based on WeChat platform helps to facilitate the psychological elasticity and quality of life of patients with lung cancer and further promote patients' self-care ability and compliance with lung cancer. It can also effectively enhance family care and nursing satisfaction; the nursing model is worth popularizing and applying in clinic.

The value of AI in the Diagnosis, Treatment, and Prognosis of Malignant Lung Cancer

Malignant tumors is a serious public health threat. Among them, lung cancer, which has the highest fatality rate globally, has significantly endangered human health. With the development of artificial intelligence (AI) and its integration with medicine, AI research in malignant lung tumors has become critical. This article reviews the value of CAD, computer neural network deep learning, radiomics, molecular biomarkers, and digital pathology for the diagnosis, treatment, and prognosis of malignant lung tumors.

Application of machine learning approaches to predict the 5-year survival status of patients with esophageal cancer

Background

Accurate prognostic estimation for esophageal cancer (EC) patients plays an important role in the process of clinical decision-making. The objective of this study was to develop an effective model to predict the 5-year survival status of EC patients using machine learning (ML) algorithms.

Methods

We retrieved the information of patients diagnosed with EC between 2010 and 2015 from the Surveillance, Epidemiology, and End Results (SEER) Program, including 24 features. A total of 8 ML models were applied to the selected dataset to classify the EC patients in terms of 5-year survival status, including 3 newly developed gradient boosting models (GBM), XGBoost, CatBoost, and LightGBM, 2 commonly used tree-based models, gradient boosting decision trees (GBDT) and random forest (RF), and 3 other ML models, artificial neural networks (ANN), naive Bayes (NB), and support vector machines (SVM). A 5-fold cross-validation was used in model performance measurement.

Results

After excluding records with missing data, the final study population comprised 10,588 patients. Feature selection was conducted based on the χ² test, however, the experiment results showed that the complete dataset provided better prediction of outcomes than the dataset with removal of non-significant features. Among the 8 models, XGBoost had the best performance [area under the receiver operating characteristic (ROC) curve (AUC): 0.852 for XGBoost, 0.849 for CatBoost, 0.850 for LightGBM, 0.846 for GBDT, 0.838 for RF, 0.844 for ANN, 0.833 for NB, and 0.789 for SVM]. The accuracy and logistic loss of XGBoost were 0.875 and 0.301, respectively, which were also the best performances. In the XGBoost model, the SHapley Additive exPlanations (SHAP) value was calculated and the result indicated that the four features: reason no cancer-directed surgery, Surg Prim Site, age, and stage group had the greatest impact on predicting the outcomes.

Conclusions

The XGBoost model and the complete dataset can be used to construct an accurate prognostic model for patients diagnosed with EC which may be applicable in clinical practice in the future.

Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data

BACKGROUND

Immune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs.

METHODS

Patients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response.

RESULTS

Overall, 298 patients were enrolled. The overall response rate and DCR were 15.3% and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58, p < 0.0001; OR 1.8, p < 0.001). These variables were also associated with PFS and OS and ranked top in random forest-based feature importance. Neutrophil-to-lymphocyte ratio was also associated with DCR, PFS and OS. The best ML algorithm was a random forest. It could predict DCR with satisfactory efficacy based on these three variables. Ten-fold cross-validated performances were: accuracy 0.68 ± 0.04, sensitivity 0.58 ± 0.08; specificity 0.78 ± 0.06; positive predictive value 0.70 ± 0.08; negative predictive value 0.68 ± 0.06; AUC 0.74 ± 0.03.

CONCLUSION

Combination of simple clinical and biological data could accurately predict disease control rate at the individual level.