Topological network analysis of patient similarity for precision management of acute blood pressure in spinal cord injury

eLife, 2021 · DOI: https://doi.org/10.7554/eLife.68015 · Published: November 16, 2021

Spinal Cord Injury Surgery Bioinformatics

Simple Explanation

This study uses machine learning to analyze blood pressure and heart rate data from 118 patients who underwent spinal cord surgery after acute spinal cord injury. The analyses revealed that patients who suffered from either low or high blood pressure during surgery had poorer prospects of recovery. The optimal blood pressure range to ensure recovery lies between 76 to 104-117 mmHg. Any deviation from this narrow window would dramatically worsen the ability to recover.

Study Duration

Not specified

Participants

118 patients with complete MAP and heart rate monitoring

Evidence Level

Not specified

Key Findings

1
Time outside of an optimum MAP range (hypotension or hypertension) during surgery was associated with lower likelihood of neurological recovery at hospital discharge.
2
An optimal MAP range of 76–[104-117] mmHg associated with neurological recovery.
3
Deviation from this optimal MAP range during SCI surgery predicts lower probability of neurological recovery and suggest new targets for therapeutic intervention.

Research Summary

Intra-operative monitoring records (MAP, HR) and neurological outcome data were extracted and curated from two Level 1 trauma centers. A final cohort of 118 patients was included The exploratory network analysis revealed that clusters with higher proportion of patients that increased AIS of at least one grade were associated with having a middle range aMAP The findings indicate that the time of MAP outside a measurable normotensive range during surgery is associated with lower odds of recovering at least one AIS grade.

Practical Implications

Refined Blood Pressure Targets

The study suggests a narrower and potentially lower MAP range (76-104/117 mmHg) for optimal neurological recovery during SCI surgery, challenging the current guideline of maintaining MAP >85 mmHg.

Precision Medicine Approach

The research highlights the potential of using hemodynamic instability as a physiology-based biomarker for predicting recovery, paving the way for precision medicine in SCI management.

Advanced Analytical Workflow

The study showcases a successful translation of machine intelligence analytical tools from animal models to humans, demonstrating the utility of topology-based analytics and patient similarity networks in uncovering associations for hypothesis generation.

Study Limitations

1
Retrospective nature of the analysis
2
Relatively small sample size (although large for SCI)
3
Use of an estimated ordinal scale (AIS grade) as an indicator of neurological recovery

Your Feedback

Was this summary helpful?

Back to Spinal Cord Injury