Using machine learning for mortality prediction and risk stratification in atezolizumab-treated cancer patients: Integrative analysis of eight clinical trials

Physical activity and idiopathic pulmonary fibrosis: A prospective cohort study in UK Biobank and Mendelian randomization analyses

INTRODUCTION

The impact of physical activity on the incidence of idiopathic pulmonary fibrosis (IPF) remains less well studied. This study aimed to investigate the relationship between moderate-to-vigorous physical activity (MVPA) and the risk of developing IPF.

METHODS

We analyzed data from a prospective cohort study within the UK Biobank involving 502,476 participants. Participants were categorized as meeting or not meeting the 2017 UK Physical Activity Guidelines (150 min of moderate activity or 75 min of vigorous activity per week). The cumulative incidence and hazard ratios (HRs) for IPF were analyzed using the Kaplan-Meier method, log-rank test, and Cox regression. Two-sample Mendelian randomization (MR) analyses were performed to identify potential causal links between physical activity and IPF risk.

RESULTS

Over a median of 12.2 y follow-up, we identified 1,639 incident IPF cases and 395,172 controls. Individuals who met the physical activity guidelines had a significantly lower risk of IPF than those who did not meet the guidelines (adjusted HR = 0.843, 95 % confidence interval [CI] = 0.765-0.930).The cumulative incidence of IPF was lower in the meeting guideline group than in the nonmeeting guideline group (Log-rank P = 0.0019). Two-sample MR analysis revealed that a 1-standard deviation increase in moderate-to-vigorous physical activity was linked to a reduced IPF risk (odds ratio [OR] = 0.17, 95 % CIs = 0.04 to 0.81, P = 0.026). Moreover, an increase in the number of days per week of moderate physical activity was genetically correlated with decreased IPF risk (OR = 0.32, 95 % CIs = 0.15-0.70, P = 0.003).

CONCLUSION

Higher levels of moderate-to-vigorous physical activity are causally associated with a significant reduction in the risk of developing IPF.

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.

Prognostic model development and clinical correlation of eight key genes in skin cutaneous melanoma

Cutaneous melanoma (SKCM) is a challenging and increasingly prevalent cancer with limited effective treatments. In our extensive study of 342 SKCM samples, we developed a prognostic model identifying eight key genes-CASPASE7CLEAVEDD198, FOXO3A, Melanoma gp100, CD171, 1433ZETA, SRC, P21, and CABL-linked to SKCM prognosis. Statistical analysis indicated significant differences in clinical outcomes between low and high-risk groups, corroborated by principal component analysis (PCA). Survival analysis and receiver operating characteristic (ROC) curve analysis confirmed the model's predictive accuracy for SKCM prognosis. Additionally, we observed notable correlations between the expression levels of genes related to prognosis and clinical characteristics. Our research offers crucial insights into SKCM prognosis, suggesting potential diagnostic markers and personalized treatment targets.

Just how transformative will AI/ML be for immuno-oncology?

Immuno-oncology involves the study of approaches which harness the patient's immune system to fight malignancies. Immuno-oncology, as with every other biomedical and clinical research field as well as clinical operations, is in the midst of technological revolutions, which vastly increase the amount of available data. Recent advances in artificial intelligence and machine learning (AI/ML) have received much attention in terms of their potential to harness available data to improve insights and outcomes in many areas including immuno-oncology. In this review, we discuss important aspects to consider when evaluating the potential impact of AI/ML applications in the clinic. We highlight four clinical/biomedical challenges relevant to immuno-oncology and how they may be able to be addressed by the latest advancements in AI/ML. These challenges include (1) efficiency in clinical workflows, (2) curation of high-quality image data, (3) finding, extracting and synthesizing text knowledge as well as addressing, and (4) small cohort size in immunotherapeutic evaluation cohorts. Finally, we outline how advancements in reinforcement and federated learning, as well as the development of best practices for ethical and unbiased data generation, are likely to drive future innovations.

Prediction of Effectiveness and Toxicities of Immune Checkpoint Inhibitors Using Real-World Patient Data

PURPOSE

Although immune checkpoint inhibitors (ICIs) have improved outcomes in certain patients with cancer, they can also cause life-threatening immunotoxicities. Predicting immunotoxicity risks alongside response could provide a personalized risk-benefit profile, inform therapeutic decision making, and improve clinical trial cohort selection. We aimed to build a machine learning (ML) framework using routine electronic health record (EHR) data to predict hepatitis, colitis, pneumonitis, and 1-year overall survival.

METHODS

Real-world EHR data of more than 2,200 patients treated with ICI through December 31, 2018, were used to develop predictive models. Using a prediction time point of ICI initiation, a 1-year prediction time window was applied to create binary labels for the four outcomes for each patient. Feature engineering involved aggregating laboratory measurements over appropriate time windows (60-365 days). Patients were randomly partitioned into training (80%) and test (20%) sets. Random forest classifiers were developed using a rigorous model development framework.

RESULTS

The patient cohort had a median age of 63 years and was 61.8% male. Patients predominantly had melanoma (37.8%), lung cancer (27.3%), or genitourinary cancer (16.4%). They were treated with PD-1 (60.4%), PD-L1 (9.0%), and CTLA-4 (19.7%) ICIs. Our models demonstrate reasonably strong performance, with AUCs of 0.739, 0.729, 0.755, and 0.752 for the pneumonitis, hepatitis, colitis, and 1-year overall survival models, respectively. Each model relies on an outcome-specific feature set, though some features are shared among models.

CONCLUSION

To our knowledge, this is the first ML solution that assesses individual ICI risk-benefit profiles based predominantly on routine structured EHR data. As such, use of our ML solution will not require additional data collection or documentation in the clinic.

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.

Routine perioperative blood tests predict survival of resectable lung cancer

There is growing evidence that inflammatory, immunologic, and metabolic status is associated with cancer patients survival. Here, we built a simple algorithm to predict lung cancer outcome. Perioperative routine blood tests (RBT) of a cohort of patients with resectable primary lung cancer (LC) were analysed. Inflammatory, immunologic, and metabolic profiles were used to create a single algorithm (RBT index) predicting LC survival. A concurrent cohort of patients with resectable lung metastases (LM) was used to validate the RBT index. Charts of 2088 consecutive LC and 1129 LM patients undergoing lung resection were evaluated. Among RBT parameters, C-reactive protein (CRP), lymphocytes, neutrophils, hemoglobin, albumin and glycemia independently correlated with survival, and were used to build the RBT index. Patients with a high RBT index had a higher 5-year mortality than low RBT patients (adjusted HR 1.93, 95% CI 1.62-2.31). High RBT patients also showed a fourfold higher risk of 30-day postoperative mortality (2.3% vs. 0.5%, p 0.0019). The LM analysis validated the results of the LC cohort. We developed a simple and easily available multifunctional tool predicting short-term and long-term survival of curatively resected LC and LM. Prospective external validation of RBT index is warranted.

Predicting breast cancer-specific survival in metaplastic breast cancer patients using machine learning algorithms

Metaplastic breast cancer (MpBC) is a rare and aggressive subtype of breast cancer, with data emerging on prognostic factors and survival prediction. This study aimed to develop machine learning models to predict breast cancer-specific survival (BCSS) in MpBC patients, utilizing a dataset of 160 patients with clinical, pathological, and biological variables. An in-depth variable selection process was carried out using gain ratio and correlation-based methods, resulting in 10 variables for model estimation. Five models (decision tree with bagging; logistic regression; multilayer perceptron; naïve Bayes; and, random forest algorithms) were evaluated using 10-fold cross-validation. Despite the constraints posed by the absence of therapeutic information, the random forest model exhibited the highest performance in predicting BCSS, with an ROC area of 0.808. This study emphasizes the potential of machine learning algorithms in predicting prognosis for complex and heterogeneous cancer subtypes using clinical datasets, and their potential to contribute to patient management. Further research that incorporates additional variables, such as treatment response, and more advanced machine learning techniques will likely enhance the predictive power of MpBC prognostic models.

Advances in efficacy prediction and monitoring of neoadjuvant immunotherapy for non-small cell lung cancer

The use of immune checkpoint inhibitors (ICIs) has become mainstream in the treatment of non-small cell lung cancer (NSCLC). The idea of harnessing the immune system to fight cancer is fast developing. Neoadjuvant treatment in NSCLC is undergoing unprecedented change. Chemo-immunotherapy combinations not only seem to achieve population-wide treating coverage irrespective of PD-L1 expression but also enable achieving a pathological complete response (pCR). Despite these recent advancements in neoadjuvant chemo-immunotherapy, not all patients respond favorably to treatment with ICIs plus chemo and may even suffer from severe immune-related adverse effects (irAEs). Similar to selection for target therapy, identifying patients most likely to benefit from chemo-immunotherapy may be valuable. Recently, several prognostic and predictive factors associated with the efficacy of neoadjuvant immunotherapy in NSCLC, such as tumor-intrinsic biomarkers, tumor microenvironment biomarkers, liquid biopsies, microbiota, metabolic profiles, and clinical characteristics, have been described. However, a specific and sensitive biomarker remains to be identified. Recently, the construction of prediction models for ICI therapy using novel tools, such as multi-omics factors, proteomic tests, host immune classifiers, and machine learning algorithms, has gained attention. In this review, we provide a comprehensive overview of the different positive prognostic and predictive factors in treating preoperative patients with ICIs, highlight the recent advances made in the efficacy prediction of neoadjuvant immunotherapy, and provide an outlook for joint predictors.

Establishment of a new practical telesurgical platform using the hinotori™ Surgical Robot System: a preclinical study

Aim

The recent development of new surgical robots and network telecommunication technology has opened new avenues for robotic telesurgery. Although a few gastroenterological surgeries have been performed in the telesurgery setting, more technically demanding procedures including gastrectomy with D2 lymphadenectomy and intracorporeal anastomosis have never been reported. We examined the feasibility of telesurgical robotic gastrectomy using the hinotori™ Surgical Robot System in a preclinical setting.

Methods

First, the suturing time in the dry model was measured in the virtual telesurgery setting to determine the latency time threshold. Second, a surgeon cockpit and a patient unit were installed at Okazaki Medical Center and Fujita Health University, respectively (approximately 30 km apart), and connected using a 10-Gbps leased optic-fiber network. After evaluating the feasibility in the dry gastrectomy model, robotic distal gastrectomies with D2 lymphadenectomy and intracorporeal B-I anastomosis were performed in two porcine models.

Results

The virtual telesurgery study identified a latency time threshold of 125 ms. In the actual telesurgery setting, the latency time was 27 ms, including a 2-ms telecommunication network delay and a 25-ms local information process delay. After verifying the feasibility of the operative procedures using a gastrectomy model, two telesurgical gastrectomies were successfully completed without any unexpected events. No fluctuation was observed across the actual telesurgeries.

Conclusion

Short-distance telesurgical robotic surgery for technically more demanding procedure may be safely conducted using the hinotori Surgical Robot System connected by high-speed optic-fiber communication.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00423-022-02710-6.