Advancing Spinal Disorders Diagnosis with Artificial Intelligence

Dear Colleagues,

The accurate, reproducible, and clinically meaningful characterization of spinal disorders remains a foundational challenge in musculoskeletal medicine. While substantial progress has been made in relation to automating the measurement of isolated features—such as spinal alignment, intervertebral motion, disc degeneration, stenosis, and deformity—these structural metrics often show only weak-to-moderate associations with patients’ symptoms, disabilities, and long-term treatment outcomes when considered in isolation.

Because spinal disorders are inherently multifactorial, advancing patient care requires a paradigm shift: moving away from isolated anatomical descriptions toward validated, patient-specific models that integrate structural, functional, and clinical data into actionable prognostic streams.

Artificial intelligence (AI) is uniquely positioned to drive this transition. Beyond standard image segmentation, advanced AI architectures can harmonize unstructured clinical records, integrate continuous data from wearables, model complex biomechanical relationships, and provide real-time quality feedback loops during image acquisition. However, automated measurement is merely the entry point. The field urgently requires rigorous evidence demonstrating how these models generalize across diverse populations, how they integrate into existing clinical workflows, and whether they measurably improve patient outcomes or reduce the cost of care.

This Special Issue, "Advancing Spinal Disorders Diagnosis with Artificial Intelligence," seeks original research, comprehensive reviews, technical reports, and clinically oriented validation studies that bridge the gap between proof-of-concept AI development and its real-world clinical implementation.

We invite high-quality submissions centered around three core thematic pillars:

Pillar 1: Advanced Automated Phenotyping and Functional Biomechanics

• Dynamic and Kinetic Imaging: AI-based assessment of spinal alignment, intervertebral motion, spinal instability, and loss of motion segment integrity from radiographs, CT, MRI, ultrasound, and dynamic modalities.
• Mechanistic and Computational Modeling: AI-assisted biomechanical, finite element, or mechanistic modeling of traumatic, degenerative, inflammatory, and postsurgical spinal processes.
• Trauma and Acute Care Support: AI-enhanced assessment of spinal trauma, including ligamentous injury, occult fractures, fracture stability, and acute triage decision-making.

Pillar 2: Multimodal Fusion and Predictive Analytics

• Multimodal Data Integration: Novel architectures combining imaging features with clinical notes, physical examination findings, patient-reported outcomes (PROMs), laboratory data, and wearable sensor metrics.
• LLM and NLP Applications: Large language model enablement for the extraction, synthesis, and harmonization of structured and unstructured electronic health record (EHR) data relevant to spinal pathology.
• Personalized Reference Models: Demographically conditioned or patient-specific reference models that account for age, sex, body habitus, prior surgical interventions, and longitudinal degenerative changes.

Pillar 3: Clinical Translation, Workflow Integration, and Value-Based Care

• Upstream Quality and Acquisition Feedback: AI methods providing rapid feedback to technologists or clinicians to optimize image acquisition, motion protocols, positioning, and data completeness.
• Companion Diagnostics and Treatment Selection: AI-driven models targeting specific interventions, including biologics, motion-preserving procedures, decompression, fusion deformity correction, and targeted rehabilitation.
• Validation, Trust, and Economics: Multi-site external validation, prospective clinical trials, uncertainty estimation, explainability (XAI), and health economic or cost-effectiveness analyses evaluating the impact of AI on care pathways.

We look forward to your contributions that aim to buildi a more objective, reproducible, and predictive framework for spinal diagnostics.

Dr. John Hipp
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Bioengineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• spine
• spinal disorders
• artificial intelligence
• machine learning
• deep learning
• computer-aided diagnosis
• medical imaging
• dynamic imaging
• intervertebral motion
• spinal instability
• motion segment integrity
• degenerative spine disease
• spinal stenosis
• trauma
• spondylolisthesis
• multimodal AI
• clinical decision support
• natural language processing
• computational biomechanics