Cluster Analysis of Obesity Disease Based on Comorbidities Extracted from Clinical Notes

Reátegui, Ruth; Ratté, Sylvie; Bautista-Valarezo, Estefanía; Duque, Vítor

doi:10.1007/s10916-019-1172-1

Cited by 14 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the lack of clusters in our motor FND group of patients, previous high-quality studies using the same methodology (gap statistics) reported homogeneous clusters including drug-naive parkinsonism (Jain, Park, & Comer, 2015), comorbidities associated with obesity (Reategui, Ratte, Bautista-Valarezo, & Duque, 2019), breast cancer progression data (Alexe, Dalgin, Ganesan, Delisi, & Bhanot, 2007). However, most cluster analysis studies in neurological conditions with motor symptoms such as Parkinson's disease (Ba, Obaid, Wieler, Camicioli, & Martin, 2016; Mu et al, 2017; Yang, Kim, Yun, Kim, & Jeon, 2014) or fibromyalgia (Yim et al, 2017) suffered from important methodological problems which could have led to false-positive cluster identification.…”

Section: Cluster Analysiscontrasting

confidence: 79%

The complex syndrome of functional neurological disorder

et al. 2022

View full text Add to dashboard Cite

Background Patients with functional neurological disorders (FND) often present with multiple motor, sensory, psychological and cognitive symptoms. In order to explore the relationship between these common symptoms, we performed a detailed clinical assessment of motor, non-motor symptoms, health-related quality of life (HRQoL) and disability in a large cohort of patients with motor FND. To understand the clinical heterogeneity, cluster analysis was used to search for subgroups within the cohort. Methods One hundred fifty-two patients with a clinically established diagnosis of motor FND were assessed for motor symptom severity using the Simplified Functional Movement Disorder Rating Scale (S-FMDRS), the number of different motor phenotypes (i.e. tremor, dystonia, gait disorder, myoclonus, and weakness), gait severity and postural instability. All patients then evaluated each motor symptom type severity on a Likert scale and completed questionnaires for depression, anxiety, pain, fatigue, cognitive complaints and HRQoL. Results Significant correlations were found among the self-reported and all objective motor symptoms severity measures. All self-reported measures including HRQoL correlated strongly with each other. S-FMDRS weakly correlated with HRQoL. Hierarchical cluster analysis supplemented with gap statistics revealed a homogenous patient sample which could not be separated into subgroups. Conclusions We interpret the lack of evidence of clusters along with a high degree of correlation between all self-reported and objective measures of motor or non-motor symptoms and HRQoL within current neurobiological models as evidence to support a unified pathophysiology of ‘functional’ symptoms. Our results support the unification of functional and somatic syndromes in classification schemes and for future mechanistic and therapeutic research.

show abstract

Section: Cluster Analysiscontrasting

confidence: 79%

The complex syndrome of functional neurological disorder

et al. 2022

View full text Add to dashboard Cite

show abstract

“…With an increase in income and quality of life, the rate of obesity in the middle-aged population is higher than that in the elderly population (age > 65 years) 23 . Although the obese patients are young, they have multiple the obesity-related comorbidities such as metabolic syndrome and CAD 2 . The adverse effects of obesity on cardiovascular haemodynamics, structure, impaired systolic and/or diastolic ventricular function, and increased risk of cardiac failure have been widely reported 24 , 25 .…”

Section: Discussionmentioning

confidence: 99%

“…In 2011, the World Health Organization (WHO) reported a significant increase in the prevalence of obesity in the United States; 62% of the adult population was categorised as overweight, including 26% obese adults 1 . Obesity is correlated with several comorbidities, such as metabolic syndrome, coronary artery disease (CAD), neoplasm, musculoskeletal disorders, and idiopathic sudden cardiac arrest (SCA) 2 , 3 . Obese patients account for 300,000 SCA cases in the United States annually 3 .…”

Section: Introductionmentioning

confidence: 99%

Obese cardiogenic arrest survivors with significant coronary artery disease had worse in-hospital mortality and neurological outcomes

Sung

Chen

Chang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Cardiogenic arrest is the major cause of sudden cardiac arrest (SCA), accounting for 20% of all deaths annually. The association between obesity and outcomes in cardiac arrest survivors is debatable. However, the effect of obesity on the prognosis of patients with significant coronary artery disease (CAD) successfully resuscitated from cardiogenic arrest is unclear. Thus, the association between body mass index (BMI) and outcomes in cardiogenic arrest survivors with significant CAD was investigated. This multicentre retrospective cohort study recruited 201 patients from January 2011 to September 2017. The eligible cardiogenic arrest survivors were non-traumatic adults who had undergone emergency coronary angiography after sustained return of spontaneous circulation and had significant coronary artery stenosis. BMI was used to classify the patients into underweight, normal-weight, overweight, and obese groups (< 18.5, 18.5–24.9, 25.0–29.9, and ≥ 30 kg/m2; n = 9, 87, 72, and 33, respectively). In-hospital mortality and unsatisfactory neurological outcomes (cerebral performance scale scores = 3–5) were compared among the groups. The obese group presented higher in-hospital mortality and unsatisfactory neurological outcome risks than the normal-weight group (in-hospital mortality: adjusted hazard ratio = 4.27, 95% confidence interval (CI) 1.87–12.04, P = 0.008; unsatisfactory neurological outcomes: adjusted odds ratio = 3.33, 95% CI 1.42–8.78, P = 0.009). Subgroup analysis showed significantly higher in-hospital mortality in the obese patients than in the others in each clinical characteristic. In cardiogenic arrest survivors with significant CAD, obesity was associated with high risks of mortality and unsatisfactory neurological recovery.

show abstract

“…Here, similar participants were clustered together by running an initial pre-clustering followed by a hierarchical clustering method. In another study on patients with obesity, three types of clusters were identified based on the number of comorbidities and the percentage of patients suffering from them [8]. A sparse k-means algorithm was also used at two-levels to identify subgroups among the groups of individuals based on 14 comorbidities related to obesity and contrasted them against experts' annotations [8].…”

Section: B Patient Subtypingmentioning

confidence: 99%

Subtyping patients with chronic disease using longitudinal BMI patterns

Mottalib¹,

Jones-Smith²,

Sheridan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Obesity is a major health problem, increasing the risk of various major chronic diseases, such as diabetes, cancer, and stroke. While the role of obesity identified by cross-sectional BMI recordings has been heavily studied, the role of BMI trajectories is much less explored. In this study, we use a machine learning approach to subtype individuals' risk of developing 18 major chronic diseases by using their BMI trajectories extracted from a large and geographically diverse EHR dataset capturing the health status of around two million individuals for a period of six years. We define nine new interpretable and evidencebased variables based on the BMI trajectories to cluster the patients into subgroups using the k-means clustering method. We thoroughly review each clusters' characteristics in terms of demographic, socioeconomic, and physiological measurement variables to specify the distinct properties of the patients in the clusters. In our experiments, direct relationship of obesity with diabetes, hypertension, Alzheimer's, and dementia have been reestablished and distinct clusters with specific characteristics for several of the chronic diseases have been found to be conforming or complementary to the existing body of knowledge.

show abstract

Cluster Analysis of Obesity Disease Based on Comorbidities Extracted from Clinical Notes

Cited by 14 publications

References 37 publications

The complex syndrome of functional neurological disorder

The complex syndrome of functional neurological disorder

Obese cardiogenic arrest survivors with significant coronary artery disease had worse in-hospital mortality and neurological outcomes

Subtyping patients with chronic disease using longitudinal BMI patterns

Contact Info

Product

Resources

About