Network science meets respiratory medicine for OSAS phenotyping and severity prediction

Abstract

Obstructive sleep apnea syndrome (OSAS) is a common clinical condition. The way that OSAS risk factors associate and converge is not a random process. As such, defining OSAS phenotypes fosters personalized patient management and population screening. In this paper, we present a network-based observational, retrospective study on a cohort of 1,371 consecutive OSAS patients and 611 non-OSAS control patients in order to explore the risk factor associations and their correlation with OSAS comorbidities. To this end, we construct the Apnea Patients Network (APN) using patient compatibility relationships according to six objective parameters: age, gender, body mass index (BMI), blood pressure (BP), neck circumference (NC) and the Epworth sleepiness score (ESS). By running targeted network clustering algorithms, we identify eight patient phenotypes and corroborate them with the co-morbidity types. Also, by employing machine learning on the uncovered phenotypes, we derive a classification tree and introduce a computational framework which render the Sleep Apnea Syndrome Score (SAS Score ); our OSAS score is implemented as an easy-to-use, web-based computer program which requires less than one minute for processing one individual. Our evaluation, performed on a distinct validation database with 231 consecutive patients, reveals that OSAS prediction with SAS Score has a significant specificity improvement (an increase of 234%) for only 8.2% sensitivity decrease in comparison with the stateof-the-art score STOP-BANG. The fact that SAS Score has bigger specificity makes it appropriate for OSAS screening and risk prediction in big, general populations.

Sleep Study and Oximetry Parameters for Predicting Postoperative Complications in Patients With OSA

“…Evidence from a network-based cluster analysis suggests that populations with OSA are much more diverse than traditionally conceived because there are clusters of nonobese, thin-necked, normotensive individuals with OSA. 60 Certain phenotypes of OSA, such as those with high arousal threshold 44 or high loop gain, 61 are underrecognized and may not be apparent immediately from the results of conventional PSG. Those with the phenotype with high arousal threshold have a low propensity to wake with obstructive events, which may predispose them to a greater magnitude of hypoxemia and hypercarbia within a respiratory event vs those in a patient with a similar AHI.…”

HIF-1α as a Mediator of Insulin Resistance, T2DM, and Its Complications: Potential Links With Obstructive Sleep Apnea

“…Although the relationship between OSA and metabolic disorders is intensively analyzed nowadays and OSA is described as an independent risk factor for onset and progression of T2DM and IR, the mechanisms underlying these processes remain not fully elucidated. Better understanding of this link may lead to a more efficient diagnostic process, as well as facilitate personalized treatment strategy (Mihaicuta et al, 2017;Carberry et al, 2018). Possibly underlying mechanisms include hypoxia, sleep fragmentation, inflammation, and oxidative stress, hormonal changes or increased sympathetic tone (Mesarwi et al, 2015;Farr and Mantzoros, 2017).…”

Personalised medicine in sleep respiratory disorders: focus on obstructive sleep apnoea diagnosis and treatment

“…Severe nocturnal hypoxaemia was found in relatively young, severely obese patients who accounted for about half of the total sample, whereas elderly patients with mild nocturnal hypoxaemia and few symptoms accounted for ∼8% of the total sample. Finally, MIHAICUTA et al [92] published a detailed single-centre study including >1300 OSA patients and >600 controls, and identified eight clusters. This complex study assessed not only single comorbidities, but also their overlap in OSA patients, and identified two clusters of female OSA.…”