December 20, 2017Journal of Applied Biomedicine

Nonlinear Heart Rate Variability based artificial intelligence in lung cancer prediction

Q: What is the clinical evidence from this study?

Study design: Cross-Sectional. Population: Lung cancer (n=134). Intervention: Nonlinear Heart Rate Variability (HRV) indices via Artificial Intelligence vs. Healthy controls. Primary outcome: Classification accuracy of lung cancer performance status (ECOG 1-4 and controls).

View Full Paper

Ask AI

Bookmark

Key result

Artificial neural network and support vector machine models using nonlinear heart rate variability indices classified lung cancer performance status with an overall accuracy of 93.09% and 100%, respectively.

Why the study?

Does nonlinear heart rate variability analysis combined with artificial intelligence accurately classify the performance status of lung cancer patients?

Population

104 lung cancer subjects and 30 healthy controls. Excluded: cardiac disorder, diabetes, hypertensive and…

Comparison

Nonlinear heart rate variability analysis… vs Healthy controls and comparison across different…

Design

Case-control

Authors

RSReema Shyamsunder Shukla YAYogender AggarwalBirla Institute of Technology, Mesra

Discussion

Member takes

Implication

Nonlinear HRV-based ML models may aid lung cancer performance status assessment; leaves open prospective validation before clinical use.

Study Design

Type

Cross-Sectional (n=134)

Structured PICO

Does nonlinear heart rate variability analysis combined with artificial intelligence accurately classify the performance status of lung cancer patients?

Population

134 participants, including 104 with lung cancer and 30 healthy controls, free of cardiac and metabolic disorders, evaluated for heart rate variability.

Exposure

Nonlinear heart rate variability (HRV) analysis combined with artificial neural network (ANN) and support vector machine (SVM) algorithms

Comparator

Healthy controls and comparison across different Eastern Cooperative Oncology Group (ECOG) performance status stages

Outcome

Accuracy of ANN and SVM in classifying ECOG performance status and healthy controls using nonlinear HRV indicessurrogate

Nonlinear HRV indices combined with machine learning algorithms can accurately classify the performance status of lung cancer patients, suggesting a potential non-invasive prognostic tool.

Limitations

Real-time testing is yet to be done
More varied number of cancer cases are required in future to optimize the system
Real-time testing has not yet been performed
Accuracy may vary with other AI techniques for offline and real-time applications

Cite This Study

Shukla et al. (2017) conducted a cross-sectional in Lung cancer (n=134). Nonlinear Heart Rate Variability (HRV) indices via Artificial Intelligence vs. Healthy controls was evaluated on Classification accuracy of lung cancer performance status (ECOG 1-4 and controls). Artificial neural network and support vector machine models using nonlinear heart rate variability indices classified lung cancer performance status with an overall accuracy of 93.09% and 100%, respectively.

synapsesocial.com/papers/6a71d55e26a7f98052de000a https://doi.org/10.1016/j.jab.2017.12.002

View Full Paper

Ask AI

Bookmark

Nonlinear Heart Rate Variability based artificial intelligence in lung cancer prediction

Discussion

Member takes

Implication

Study Design

Structured PICO

Limitations

Cite This Study

Nonlinear Heart Rate Variability based artificial intelligence in lung cancer prediction

Discussion

Member takes

Implication

Study Design

Structured PICO

Limitations

Cite This Study

Also Consider

Also Consider