---
title: "Interpretable deep learning (TabNet) predicts early immune-related adverse events in hepatocellula"
id: "frontiers-in-immunology-2-development-and-external-validation-of-an-interpretable-deep-learning-model-for"
canonical_url: "https://medichelpline.com/clinical-feed/frontiers-in-immunology-2-development-and-external-validation-of-an-interpretable-deep-learning-model-for"
content_type: "clinical_feed_article"
specialty: "Oncology"
source_name: "Frontiers in Immunology"
source_url: "https://www.frontiersin.org/articles/10.3389/fimmu.2026.1886946"
published_at: "2026-09-21T00:00:00.000Z"
evidence_level: "Journal Feed"
license: "CC-BY-NC-4.0 / Informational Use"
---
# Interpretable deep learning (TabNet) predicts early immune-related adverse events in hepatocellula
## Provenance & Clinical Metadata
- **Canonical URL:** https://medichelpline.com/clinical-feed/frontiers-in-immunology-2-development-and-external-validation-of-an-interpretable-deep-learning-model-for
- **Specialty:** [Oncology](https://medichelpline.com/clinical-feed/oncology.md)
- **Primary Source:** Frontiers in Immunology
- **Source URL:** [Original Journal Publication](https://www.frontiersin.org/articles/10.3389/fimmu.2026.1886946)
- **Published At:** 2026-09-21T00:00:00.000Z
- **Evidence Rating:** Journal Feed
## Executive GIST (TL;DR)
- This multicenter retrospective cohort study developed and externally validated an interpretable deep learning model to predict early clinically significant **immune-related adverse events (irAEs)** in patients with **hepatocellular carcinoma (HCC)** treated with atezolizumab plus bevacizumab. - Early irAEs were defined as CTCAE grade ≥2 events occurring within 3 months of treatment initiation. The study used a prespecified set of 51 baseline clinical, laboratory, and immunological predictors obtained before therapy. - The training cohort comprised 453 patients (141 early irAE events) from Harbin Medical University Cancer Hospital; the external validation cohort included 201 patients from two independent centers (59 early irAE events). - Five models were developed using the same predictors: **TabNet**, logistic regression, random forest, XGBoost, and support vector machine. Models were tuned by stratified 5-fold cross-validation in the training cohort and evaluated on an independent external validation cohort. - The TabNet model had the most favorable overall profile across discrimination, calibration, clinical utility, and external validation. Calibration showed good agreement between predicted and observed risks; decision curve and clinical impact analyses indicated meaningful utility across a range of thresholds. - Interpretability and feature-attribution analyses identified the **CD4/CD8 ratio**, serum **IgG**, **albumin**, **platelet count**, and proportion of **CD19-positive B cells** as key contributors to predicted early irAE risk. - Risk-stratified feature clustering suggested two complementary dimensions associated with predicted early toxicity: immune-related features and host functional reserve. - The study emphasizes pre-treatment risk stratification using routinely available immunological and clinical markers to inform monitoring and management of early irAEs in HCC patients receiving ICI-based therapy.
## Clinical Analysis & Structured Key Points
Frontiers | Development and external validation of an interpretable deep learning model for early immune-related adverse events in hepatocellular carcinoma ORIGINAL RESEARCH article Front. Immunol. , 21 September 2026 Sec. Cancer Immunity and Immunotherapy Volume 17 - 2026 | https://doi.org/10.3389/fimmu.2026.1886946 Published in Frontiers in Immunology Cancer Immunity and Immunotherapy 7 impact factor 11.3 citescore Part of a Research Topic Community Series in Novel Biomarkers in Tumor Immunity and Immunotherapy: Volume III 31k views 14 articles Editor & Reviewers Edited by T M Takaji Matsutani Reviewed by J T Jianhui Tian N L Nanqing Liao Outline Figures and Tables Figure 1 View in article Figure 2 View in article Figure 3 View in article Figure 4 View in article Figure 5 View in article Figure 6 View in article Figure 7 View in article Figure 8 View in article Figure 9 View in article Figure 10 View in article Figure 11 View in article Table 1 Patients characteristics. View in article ORIGINAL RESEARCH article Front. Immunol. , 21 September 2026 Sec. Cancer Immunity and Immunotherapy Volume 17 - 2026 | https://doi.org/10.3389/fimmu.2026.1886946 Development and external validation of an interpretable deep learning model for early immune-related adverse events in hepatocellular carcinoma H P Hongming Pan 1,2 † C Z Chunyan Zhao 1 † H S Hao Sun 2,3 H Z Han Zhao 1 G T Guhang Tang 1 X D Xianfeng Du 1 T X Taiyu Xia 1 * 1. Department of Oncology, The Affiliated Dazu Hospital of Chongqing Medical University, Chongqing, China 2. Department of Gastrointestinal Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, China 3. Department of Breast Surgery, Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China See more Article metrics View details Abstract Objective: To develop and externally validate an interpretable deep learning model for pre-treatment prediction of early clinically significant immune-related adverse events in patients with hepatocellular carcinoma receiving immune checkpoint inhibitor–based therapy. Methods: We conducted a multicenter retrospective cohort study of patients with hepatocellular carcinoma receiving immune checkpoint inhibitor–based therapy, with atezolizumab plus bevacizumab serving as the representative regimen in this cohort. The study population was divided into a training cohort and an independent external validation cohort. Early immune-related adverse events were defined as clinically significant events occurring within three months after treatment initiation. Five prediction models were constructed using baseline clinical and circulating immunological variables obtained prior to treatment, including TabNet, logistic regression, random forest, extreme gradient boosting, and support vector machine models. Model performance was evaluated using discrimination, calibration, and clinical utility metrics, and model interpretability was assessed using feature attribution analyses. Results: Among all models, the TabNet model showed the most favorable overall performance profile, considering discrimination, calibration, clinical utility, and external validation performance. Calibration analysis showed good agreement between predicted risks and observed event rates, while decision curve analysis and clinical impact assessment indicated meaningful clinical utility across a range of threshold probabilities. Interpretability analyses identified the CD4 to CD8 ratio, serum immunoglobulin G level, albumin, platelet count, and the proportion of CD19-positive B cells as key contributors to model-predicted early immune-related adverse event risk. Risk-stratified feature clustering further suggested that immune-related features and host functional reserve may represent complementary dimensions associated with model-predicted early immune-related toxicity risk. Conclusions: An interpretable deep learning model was developed and externally validated for pre-treatment prediction of early clinically significant immune-related adverse events in hepatocellular carcinoma patients receiving immune checkpoint inhibitors. 1 Introduction Immune checkpoint inhibitors (ICIs) have fundamentally transformed the therapeutic landscape of hepatocellular carcinoma (HCC), particularly for patients with advanced-stage disease ( 1 ). The combination of atezolizumab plus bevacizumab has demonstrated superior survival benefits compared with previous standard therapies and is now widely adopted as first-line treatment ( 2 , 3 ). However, alongside these therapeutic gains, immune-related adverse events (irAEs) have emerged as a major clinical challenge. IrAEs can affect multiple organ systems and frequently lead to treatment interruption, systemic immunosuppression, or permanent discontinuation of ICIs, thereby compromising treatment continuity, patient safety, and real-world effectiveness ( 4 – 6 ). As the use of ICIs continues to expand in HCC, identifying patients at increased risk of clinically significant irAEs has become an important unmet clinical need. IrAEs are increasingly recognized as manifestations of systemic immune dysregulation induced by checkpoint blockade ( 7 ). Susceptibility to irAEs has been associated with baseline host immune status, inflammatory burden, and organ functional reserve prior to treatment initiation ( 8 ). Nevertheless, current clinical practice lacks reliable tools for prospective, pre-treatment risk assessment. Most existing studies have focused on post-treatment biomarkers, single clinical variables, or the overall occurrence of irAEs without differentiating between early- and late-onset toxicities ( 9 ). Such approaches may limit clinical applicability, particularly during the initial treatment phase when management decisions are most critical. Importantly, early-onset clinically significant irAEs may represent a biologically and clinically distinct phenotype ( 10 ). Events occurring within the first few treatment cycles are more likely to reflect baseline immune predisposition and host susceptibility rather than cumulative immune perturbation induced by prolonged exposure ( 11 ). In contrast, late irAEs may be influenced by dynamic immune remodeling and evolving tumor–immune interactions ( 12 ). Pooling early and late toxicities into a single composite endpoint may therefore obscure meaningful heterogeneity and reduce the precision of risk stratification. In routine clinical practice, irAEs of grade ≥2 is particularly relevant because they typically require active intervention, such as treatment delay or corticosteroid initiation, and may disrupt early therapeutic continuity. Recent advances in machine learning provide opportunities to integrate multidimensional clinical and immunological data for individualized risk prediction. Deep learning models designed for tabular data, such as TabNet, enable modeling of nonlinear feature interactions while maintaining interpretability through attention-based feature selection ( 13 ). However, externally validated and interpretable deep learning models specifically targeting early clinically significant irAEs in HCC remain limited. In this study, we developed and externally validated an interpretable deep learning model to predict the risk of early-onset clinically significant irAEs (grade ≥2) in patients with HCC receiving atezolizumab plus bevacizumab as a representative ICI-based combination regimen. By integrating routinely available clinical variables with baseline immunological markers obtained prior to treatment initiation, we aimed to establish a pre-treatment risk prediction framework that balances predictive accuracy, generalizability, and interpretability, and to elucidate baseline immune features associated with early immune-related toxicity. 2 Patients and methods 2.1 Patients This study was designed as a multicenter retrospective cohort study. We initially screened 741 patients with HCC who received treatment at participating centers between May 2020 and December 2023. Patients were allocated to the training or external validation source cohorts according to the hospital of treatment. The training source cohort included 518 patients from Harbin Medical University Cancer Hospital. After applying the predefined eligibility criteria, 453 patients were included as the final training cohort, with 141 early clinically significant irAE events. The external validation source cohort included 223 patients from two independent centers, including the Sixth Affiliated Hospital of Harbin Medical University (n = 37) and the People’s Hospital of Dazu District, Chongqing (n = 186). After screening, 201 patients were included in the final external validation cohort, including 31 patients from the Sixth Affiliated Hospital of Harbin Medical University and 170 patients from the People’s Hospital of Dazu District, Chongqing, contributing 7 and 52 early clinically significant irAE events, respectively. The training and external validation cohorts were separated at the hospital level, and no patient overlap existed between the two cohorts. The same inclusion and exclusion criteria were applied across participating centers. The detailed patient screening and exclusion process is shown in Figure 1 ; specifically, 13 patients were excluded because of missing prespecified key baseline variables, including 9 from the training source cohort and 4 from the external validation source cohort. Figure 1 Patient selection flowchart. The diagnosis of HCC was established in accordance with the guidelines of the Chinese Society of Clinical Oncology (CSCO), based on histopathological examination or noninvasive imaging criteria using contrast-enhanced computed tomography (CT) or magnetic resonance imaging (MRI) ( 14 ). To ensure population homogeneity and data quality for model development, uniform eligibility criteria were applied across participating centers. The inclusion criteria were as follows: (1) age ≥18 years; (2) confirmed diagnosis of HCC; and (3) receipt of atezolizumab plus bevacizumab (Atezo+Bev) therapy with at least one complete treatment cycle. Patients meeting any of the following criteria were excluded: (1) presence of another concurrent primary malignancy; (2) history of liver transplantation or severe autoimmune disease; (3) absence of prespecified key pretreatment clinical, laboratory, serological, or immunological variables included in the predefined predictor set; (4) incomplete follow-up or unknown early irAE outcome within the prespecified 3-month observation window; and (5) evidence of active infection at baseline requiring systemic antibiotic therapy, which could confound baseline inflammatory or immunological biomarker measurements. This multicenter retrospective study was reviewed and approved by the Ethics Committee of Harbin Medical University Cancer Hospital (Approval No. ALTN-AK105-III-06), the Ethics Committee of the Sixth Affiliated Hospital of Harbin Medical University (Approval No. LC2024-052), and the Ethics Committee of the Affiliated Dazu Hospital of Chongqing Medical University (Approval No. 2026 Scientific Ethics Review No. 038). All procedures were conducted in accordance with the Declaration of Helsinki. Written informed consent for the use of clinical data for research purposes was obtained from all participants. 2.2 Treatment regimen and definition of irAEs All patients received the atezolizumab plus bevacizumab (Atezo+Bev) regimen, a widely used immune checkpoint inhibitor–based combination regimen for HCC. Atezolizumab was administered intravenously at a fixed dose of 1200 mg, and bevacizumab was administered intravenously at a dose of 15 mg/kg, with each treatment cycle repeated every 3 weeks. To ensure treatment exposure, only patients who received at least one complete treatment cycle were included in the analysis. The number of completed Atezo+Bev treatment cycles during the prespecified 3-month observation window was recorded descriptively and was not included as a model predictor. Patients who discontinued treatment because of an irAE were retained in the analysis and classified as having experienced the study outcome. Patients who discontinued treatment because of disease progression or other non-irAE reasons remained eligible if their early irAE status could still be clearly ascertained within the 3-month observation window. Patients with incomplete follow-up or an indeterminate early irAE outcome were excluded rather than classified as non-irAE cases. Immune-related adverse events were defined as adverse events with a suspected immune-mediated etiology occurring after initiation of ICIs therapy. All irAEs were graded by treating physicians according to the Common Terminology Criteria for Adverse Events (CTCAE), version 5.0, and events of grade ≥2 were considered clinically significant. The ascertainment of irAEs was based on systematic review of electronic medical records, including outpatient and inpatient clinical notes, laboratory test results, imaging findings, and relevant specialist consultation records. During the original outcome assessment process, suspected irAEs were first identified based on clinical diagnosis and medical records and were then reviewed by a panel of two to three experienced clinicians according to a unified CTCAE v5.0-based adjudication standard. Final classification was determined by consensus discussion. For each suspected event, adjudication considered symptom onset, temporal relationship with Atezo+Bev therapy, laboratory trends, imaging findings, microbiological evidence, tumor progression status, concomitant medications, and relevant specialist consultation records. In patients with HCC, particular attention was paid to distinguishing immune-related toxicity from hepatic decompensation, infection, disease progression, bevacizumab-related adverse events, and fluctuations in underlying liver disease. Events with a more plausible non-immune-related etiology were not classified as irAEs. To enhance clinical interpretability and focus on early immune toxicity that may directly affect treatment monitoring and management, outcome assessment was restricted to a prespecified 3-month observation window following the first ICIs therapy. The follow-up cutoff date was March 21, 2024. Patients were followed from treatment initiation until the occurrence of the first qualifying irAE, death, the last clinical contact, or completion of the 3-month observation period, whichever occurred first. Patients were classified into the irAE and non-irAE groups based on the occurrence of at least one CTCAE grade ≥2 irAE within this early observation window. For descriptive profiling of early clinically significant irAEs, organ-system category, CTCAE grade, time to onset, glucocorticoid use, treatment interruption, and permanent discontinuation were also extracted from medical records. These irAE-related characteristics were used exclusively for descriptive clinical profiling and were not included as model predictors, because they were determined after treatment initiation; the prespecified prediction outcome was the occurrence of at least one grade ≥2 irAE within the 3-month observation window. 2.3 Candidate predictors and baseline assessment Candidate predictors were prespecified based on clinical relevance, biological plausibility, and availability in routine clinical practice, with the aim of enabling true pre-treatment risk prediction. The required baseline variables were prespecified before model development and were not selected retrospectively according to the performance or requirements of any specific algorithm. Given the immune-mediated nature of irAEs, candidate variables were defined to comprehensively capture baseline host immune status in addition to conventional clinical and laboratory indicators. Only variables obtained prior to the initiation of ICIs therapy were considered for model development. No univariate pre-screening was performed before model development because the candidate predictors had been prespecified on clinical and biological grounds, and variables with limited marginal associations could still contribute to multivariable prediction through nonlinear relationships or interactions with other features. A total of 51 pretreatment candidate predictors were prespecified for model development. Clinical variables included age, body mass index (BMI), sex, smoking status, drinking status, Child–Pugh class, ABO blood type, previous surgery, tumor number, tumor size, liver cirrhosis, and BCLC stage. Immunological variables included serum immunoglobulin A (IgA), immunoglobulin G (IgG), and immunoglobulin M (IgM); the proportions of CD3+, CD4+, and CD8+ T cells; the CD4+/CD8+ ratio; CD3+CD4+CD8+ cells; CD19+ B cells; CD3−CD16+CD56+ cells; and CD3+CD16+CD56+ cells. Laboratory variables included alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase (γ-GGT), lactate dehydrogenase (LDH), total bilirubin (TBIL), direct bilirubin (DBIL), indirect bilirubin (IDBIL), total protein (TP), albumin (ALB), globulin (GLOB), albumin-to-globulin ratio (A/G), prealbumin (PALB), blood urea nitrogen (BUN), creatinine (CREA), uric acid (UA), alkaline phosphatase (ALP), glucose (Glu), white blood cell count (WBC), neutrophil count (NEU), lymphocyte count (LYM), monocyte count (MON), red blood cell count (RBC), hemoglobin (HGB), hematocrit (HCT), and platelet count (PLT). Coagulation-related variables included international normalized ratio (INR), fibrinogen (Fbg), and D-dimer. All baseline assessments were performed before the first administration of ICIs. For laboratory measurements, baseline values were defined as the most recent results obtained within 7 days prior to ICIs therapy. When multiple measurements were available within this time window, the value closest to treatment initiation was selected. All baseline data were extracted from electronic medical records and cross-checked for internal consistency and clinical plausibility. Continuous variables were retained in their original scale to preserve quantitative information and were standardized as required for model input. Categorical variables were encoded using appropriate binary or ordinal representations. To prevent information leakage, no post-treatment variables or time-dependent features were included in the analysis. To ensure data quality and model comparability across algorithms, only patients with complete baseline data for the prespecified candidate predictors were included in the final analysis in accordance with the predefined complete-case strategy. As a result, no missing data imputation was performed in this study. Detailed definitions and distributions of the candidate predictors are provided in Supplementary Table 3 . With 141 early clinically significant irAE events in the training cohort, the crude events-per-candidate-predictor ratio was 2.76. 2.4 Model development and validation Five prediction models, including TabNet, logistic regression, random forest, extreme gradient boosting (XGBoost), and support vector machine, were developed in parallel using the same set of baseline predictors. All models were trained exclusively in the training cohort and evaluated in an independent external validation cohort, with no information from the validation cohort used during model training or hyperparameter optimization to prevent information leakage. For logistic regression, multicollinearity among candidate variables was assessed using tolerance and variance inflation factor (VIF) to ensure model stability. Hyperparameter tuning was performed exclusively within the training cohort using stratified 5-fold cross-validation, with AUC as the tuning metric. During cross-validation, all preprocessing procedures, including continuous-variable standardization and categorical-variable encoding, were fitted exclusively within each training fold and then applied to
## Related Clinical Research

- [Investigation finds 20 unnecessary mastectomies at County Durham and Darlington trust](https://medichelpline.com/clinical-feed/bmj-2-mastectomy-scandal-twenty-women-had-unnecessary-procedure-at-trust.md)
- [EnBCDet: Explainable Contrastive Self-Supervised Model for Malignant Cell Detection in Urine Cytol](https://medichelpline.com/clinical-feed/pubmed-42765133.md) (DOI: 10.1088/2057-1976/aea429)
- [BCLXL blockade as strategy to overcome PARP inhibitor resistance in ovarian cancer](https://medichelpline.com/clinical-feed/pubmed-42764286.md) (DOI: 10.1038/s41392-026-02870-7)
- [Telix to Acquire ITM in $1.65B Radiopharmaceuticals Merger](https://medichelpline.com/clinical-feed/stat-news-8-stat-radiopharma-companies-merge-after-one-receives-surprise-fda-rejection.md)
- [Measurement reliability limits functional benchmarks and shifts where variant effect predictors fa](https://medichelpline.com/clinical-feed/biorxiv-17-measurement-reliability-bounds-functional-benchmarks-and-relocates-where.md)

## Navigation
- [← Back to Oncology Feed](https://medichelpline.com/clinical-feed/oncology.md)
- [← All Clinical Specialties](https://medichelpline.com/clinical-feed.md)
## Medical & Regulatory Disclaimer

> [!CAUTION]
> MedicHelpline content is structured for research, educational, and professional discovery purposes. It does not constitute individual medical advice, clinical diagnosis, or treatment recommendations.
> Always verify dosing, contraindications, and regulatory alerts against official product labeling and primary regulatory sources before clinical decision-making.