Development of a Multi-Disease Diagnostic System Utilizing Convolutional Neural Networks (CNNs): A Systematic Review of Deep Learning Applications in Image-Based Medical Diagnosis

CNN-based multi-disease diagnosis systems enhance medical imaging, enabling detection of up to 15 disorders per image. This systematic review (52 papers, 2021–2025) analyzes trends, deficiencies, and clinical impact. Meta-analysis yielded a pooled AUC-ROC of 0.91 ± 0.04 (95% CI 0.87–0.95), with moderate heterogeneity (I2=58%). Thematic analysis revealed five themes: multi-disease classification (29%), data imbalance (23%), hybrid models (19%), XAI (15%), and computational optimization (14%). Advantages include high accuracy (96.5%) and reduced latency (58%). Disadvantages: geographical bias (68% from China), inadequate preprocessing (28% using CLAHE), and limited interpretability (32% using SHAP/LIME). This study uniquely integrates bias, meta-analysis, and ethics. Recommendations include standardized preprocessing, diverse datasets, and comprehensive XAI for universal health access (SDG 3).

• Publication year

  2025

• Venue

  2025 2nd International Conference on Information System and Information Technology (ICISIT)

• Publication date

  2025-11-27

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICISIT66233.2025.11402942
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unveiling Explainable AI in Healthcare: Current Trends, Challenges, and Future Directions

  2025cited by this paper
• CTBViT: A novel ViT for tuberculosis classification with efficient block and randomized classifier

  2025cited by this paper
• Not from scratch: Explainable deep transfer learning fine-tunning with domain adaptation enables trustworthy COVID-19 prediction

  2025cited by this paper
• Multigranularity feature aggregation in vision transformer for lung disease classification and segmentation

  2025cited by this paper
• Automatic diagnosis of CoV-19 in CXR images using haar-like feature and XgBoost classifier

  2024cited by this paper
• Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification

  2024cited by this paper
• Optimizing Deep Learning for Diabetic Retinopathy Diagnosis

  2024cited by this paper
• A Systematic Literature Review on Multimodal Medical Image Fusion

  2023cited by this paper
• WATUNet: a deep neural network for segmentation of volumetric sweep imaging ultrasound

  2023cited by this paper
• DeepMetaForge: A Deep Vision-Transformer Metadata-Fusion Network for Automatic Skin Lesion Classification

  2023cited by this paper
• Automatic Calcification Morphology and Distribution Classification for Breast Mammograms With Multi-Task Graph Convolutional Neural Network

  2023cited by this paper
• GSO-CNN-based model for the identification and classification of thyroid nodule in medical USG images

  2022cited by this paper
• Learning From Multiple Expert Annotators for Enhancing Anomaly Detection in Medical Image Analysis

  2022cited by this paper
• Deployment and validation of an AI system for detecting abnormal chest radiographs in clinical settings

  2022cited by this paper
• COVID‐19 lung infection segmentation from chest CT images based on CAPA‐ResUNet

  2022cited by this paper
• The PRISMA 2020 statement: An updated guideline for reporting systematic reviews

  2021cited by this paper
• A depthwise separable dense convolutional network with convolution block attention module for COVID-19 diagnosis on CT scans

  2021cited by this paper
• Using BI-RADS Stratifications as Auxiliary Information for Breast Masses Classification in Ultrasound Images

  2020cited by this paper
• The FAIR Guiding Principles for scientific data management and stewardship

  2016cited by this paper
• QUADAS-2: A Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies

  2011cited by this paper
• Measuring inconsistency in meta-analyses

  2003cited by this paper
• Bias in meta-analysis detected by a simple, graphical test

  1997cited by this paper
• Meta-analysis in clinical trials.

  1986cited by this paper
• A Coefficient of Agreement for Nominal Scales

  1960cited by this paper
• The comparison of percentages in matched samples.

  1950cited by this paper

• No citing papers are available for this paper.