Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Dec 21, 2019
Date Accepted: Feb 26, 2020

The final, peer-reviewed published version of this preprint can be found here:

Neural Network–Based Clinical Prediction System for Identifying the Clinical Effects of Saffron (Crocus sativus L) Supplement Therapy on Allergic Asthma: Model Evaluation Study

Hosseini SA, Jamshidnezhad A, Zilaee M, Hosseini SM, Fouladi Dehaghi B, Mohammadi A

Neural Network–Based Clinical Prediction System for Identifying the Clinical Effects of Saffron (Crocus sativus L) Supplement Therapy on Allergic Asthma: Model Evaluation Study

JMIR Med Inform 2020;8(7):e17580

DOI: 10.2196/17580

PMID: 32628613

PMCID: 7381052

A Clinical Predictor System for Detecting the Improvement Level of Allergic Asthma Patients with Saffron Supplement Therapy Running title: Predicting System for Asthma Improvement Level

  • Seyed Ahmad Hosseini; 
  • Amir Jamshidnezhad; 
  • Marzie Zilaee; 
  • Seyed Mohsen Hosseini; 
  • Behzad Fouladi Dehaghi; 
  • Abbas Mohammadi

ABSTRACT

Background:

Asthma is commonly associated with chronic airway inflammation and it is the underlying cause of over a million deaths each year. Statistical reports show that traditional medicine using saffron has anti-inflammatory effects and may be beneficial to asthma. Artificial neural network (ANN) models can offer significant improvement over traditional statistical reports.

Objective:

The objective of this study was to provide a clinical predictor system (CPS) to detect potential effects of saffron supplement on allergic asthma patients using an ANN.

Methods:

A genetic-neural network (GNN) system was designed that utilized clinical, immunologic, hematologic, and demographic information of asthma patients to detect the level of effectiveness of saffron. This model aims to fulfill two main purposes: estimating and predicting the possible effects level of saffron supplement on every risk factors and predicting the level of improvement in patients. For improving the prediction performance a genetic algorithm (GA) model was used to extract the input features of the predictor system. Moreover, an optimization model was developed to address applicable architecture of ANN that classifies the asthma patients with saffron supplement therapy.

Results:

The experimental results showed that the overall performance of the proposed system with the best precision was more than 99% for training and testing experiments. Moreover, the proposed GNN system predicted the level of effects with approximate accuracy rates for anti-HSP (96.5%), HS-CRP (98.9%), FEV1 (98.1%), FVC (97.5%), FEV1/FVC ratio (97%) and FEF25-75 (96.7%) for the testing dataset.

Conclusions:

The proposed system was effective in estimating the potential effects of saffron supplement on the allergic asthma patients. Most importantly, this study contributes to clinical knowledge by helping clinicians to early identify which of the asthma clinical factors will continue to improve during the treatment and draw a plan in order to change the natural course of the disease.


 Citation

Please cite as:

Hosseini SA, Jamshidnezhad A, Zilaee M, Hosseini SM, Fouladi Dehaghi B, Mohammadi A

Neural Network–Based Clinical Prediction System for Identifying the Clinical Effects of Saffron (Crocus sativus L) Supplement Therapy on Allergic Asthma: Model Evaluation Study

JMIR Med Inform 2020;8(7):e17580

DOI: 10.2196/17580

PMID: 32628613

PMCID: 7381052

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.