Dataset Information

Proof of concept for identifying cystic fibrosis from perspiration samples.

ABSTRACT: The gold standard for cystic fibrosis (CF) diagnosis is the determination of chloride concentration in sweat. Current testing methodology takes up to 3 h to complete and has recognized shortcomings on its diagnostic accuracy. We present an alternative method for the identification of CF by combining desorption electrospray ionization mass spectrometry and a machine-learning algorithm based on gradient boosted decision trees to analyze perspiration samples. This process takes as little as 2 min, and we determined its accuracy to be 98 ± 2% by cross-validation on analyzing 277 perspiration samples. With the introduction of statistical bootstrap, our method can provide a confidence estimate of our prediction, which helps diagnosis decision-making. We also identified important peaks by the feature selection algorithm and assigned the chemical structure of the metabolites by high-resolution and/or tandem mass spectrometry. We inspected the correlation between mild and severe CFTR gene mutation types and lipid profiles, suggesting a possible way to realize personalized medicine with this noninvasive, fast, and accurate method.

SUBMITTER: Zhou Z

PROVIDER: S-EPMC6900510 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Proof of concept for identifying cystic fibrosis from perspiration samples.

Zhou Zhenpeng Z Alvarez Daniel D Milla Carlos C Zare Richard N RN

Proceedings of the National Academy of Sciences of the United States of America 20191118 49

The gold standard for cystic fibrosis (CF) diagnosis is the determination of chloride concentration in sweat. Current testing methodology takes up to 3 h to complete and has recognized shortcomings on its diagnostic accuracy. We present an alternative method for the identification of CF by combining desorption electrospray ionization mass spectrometry and a machine-learning algorithm based on gradient boosted decision trees to analyze perspiration samples. This process takes as little as 2 min, ...[more]

PMID: 31740593

Similar Datasets

Project description:Cystic fibrosis (CF) is a disease in which nutritional barriers are diverse and common, with malnutrition greatly influencing pulmonary trajectory and overall outcomes. Despite this, the most effective methods to optimize CF nutrition are unknown, and literature describing patients' perspectives on their specific nutritional needs is lacking, particularly in the modern era of CF care. This study aimed to identify the most important nutritional needs and desired health-improvement resources in a contemporary adult CF cohort. A 14-question investigator-designed survey addressing nutrition concerns, preferred health-improvement resources, and dietary/exercise routines was administered to CF adults. Clinical characteristics and survey responses are presented with descriptive statistics, and responses compared by body mass index (BMI) category (<18.5 kg/m2; 18.5-24.99 kg/m2; 25-29.99 kg/m2; ≥30 kg/m2), gender, and socioeconomic status using Chi square or Fisher's Exact testing. Of 66 total patients, nine (13.6%) were underweight (BMI <18.5 kg/m2), while 19 (28.8%) were overweight or obese (BMI ≥ 25kg/m2). In the overall cohort, the most common primary concern was preventing weight loss [in 20/66 patients (30.3%)], but there were significant differences by BMI (p< 0.001), with the most common concern in the overweight subgroup being preventing weight gain. Fifteen (46.9%) men (BMI mean 20.7, range 16.4-29.2 kg/m2) listed preventing weight loss as the primary concern, compared to only 5 (14.7%) women (BMI mean 18.4, range 16.2-19.9 kg/m2), representing a trend toward a difference in primary concerns by gender (p=0.066).The most commonly desired health-improvement resource was online CF nutrition and fitness information, found in 26 patients (39.4%) in the overall cohort, without significant differences by BMI (p=0.814) or gender (p=0.199). Financial assistance was the preferred resource in 17 (26.2%), without differences by socioeconomic status (p=0.367). We identified a wide variety of nutritional needs in CF adults, including a high prevalence of overweight status, many patients desiring weight loss, and many seeking financial resources. Our findings support the individualization of modern-day CF nutrition programs and development of online resources, in an effort to address the heterogeneous barriers that exist in the contemporary CF population and improve outcomes in patients with the disease.

Dataset Information

Proof of concept for identifying cystic fibrosis from perspiration samples.

Publications

Proof of concept for identifying cystic fibrosis from perspiration samples.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure