Sleep Disorders |

AER Score: A Social-Network-Inspired Predictor for Sleep Apnea Syndrome FREE TO VIEW

Mihai Udrescu, PhD; Alexandru Topirceanu, BS; Razvan Avram, BS; Stefan Mihaicuta, MD
Author and Funding Information

University of Medicine and Pharmacy, Timisoara, Romania

Chest. 2014;145(3_MeetingAbstracts):609A. doi:10.1378/chest.1824353
Text Size: A A A
Published online



SESSION TYPE: Slide Presentations

PRESENTED ON: Monday, March 24, 2014 at 10:45 AM - 11:45 AM

PURPOSE: Polysomnography (PSG) is a costly and time-consuming investigation for the evaluation of sleep apnea syndrome(SAS). Since it is not feasible to referred all individuals to PSG, it is useful to define predictors of OSA among these subjects. The aim is to identify specific patterns of developing apnea, by taking into consideration the multiple connections between risk factors in a relevant population of patients. Using a social network analysis pattern, we have developed incentives for predicting the apnea stage for any new patient by evaluating its network topological position and assigning a proposed ApnEa Risk score (AER)- a numerical predictor for the risk of severe apnea.

METHODS: 1348 patients from Timisoara “Victor Babes” Hospital (March 2005- December 2012), with over 100 measured criteria, were used to define a methodology which is inspired by the Network Medicine approach. Patients are nodes in a graph and are linked to other patients who have a risk compatibility of at least 4 out of 6 identical parameters: gender, age, blood pressure, obesity, neck circumference and mean de-saturation

RESULTS: From the generated graph, 7 distinct compatibility clusters were found. Each of these clusters corresponds to a specific patient profile which leads to a certain probability of developing the disease. The AER score predictor emerges from the statistical analysis of these clusters and helps easily and rapidly assess the risk of OSA of a new patient. Using it to prioritize patient treatment/evaluation we manage to improve to overall process efficacy by 53%, in terms of cumulative AHI diagnosed, as compared to the first-come, first-served (non-prioritized) method currently used.

CONCLUSIONS: Relying on simple parameters, the AER score may pave the way for automatically predicting, with a high degree of accuracy, if a patient is prone to developing OSA, and thus classify and prioritize patients for diagnostic evaluation.

CLINICAL IMPLICATIONS: The predictive accuracy of the AER score facilitates an early prioritization of patients being appointed for PSG. This helps increase the overall efficiency of diagnosis and treatment by investigating more severe cases preemptively.

DISCLOSURE: The following authors have nothing to disclose: Mihai Udrescu, Alexandru Topirceanu, Razvan Avram, Stefan Mihaicuta

No Product/Research Disclosure Information




Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Find Similar Articles
CHEST Journal Articles
PubMed Articles
  • CHEST Journal
    Print ISSN: 0012-3692
    Online ISSN: 1931-3543