Dataset Information

Reducing False-Positive Results in Newborn Screening Using Machine Learning.

ABSTRACT: Newborn screening (NBS) for inborn metabolic disorders is a highly successful public health program that by design is accompanied by false-positive results. Here we trained a Random Forest machine learning classifier on screening data to improve prediction of true and false positives. Data included 39 metabolic analytes detected by tandem mass spectrometry and clinical variables such as gestational age and birth weight. Analytical performance was evaluated for a cohort of 2777 screen positives reported by the California NBS program, which consisted of 235 confirmed cases and 2542 false positives for one of four disorders: glutaric acidemia type 1 (GA-1), methylmalonic acidemia (MMA), ornithine transcarbamylase deficiency (OTCD), and very long-chain acyl-CoA dehydrogenase deficiency (VLCADD). Without changing the sensitivity to detect these disorders in screening, Random Forest-based analysis of all metabolites reduced the number of false positives for GA-1 by 89%, for MMA by 45%, for OTCD by 98%, and for VLCADD by 2%. All primary disease markers and previously reported analytes such as methionine for MMA and OTCD were among the top-ranked analytes. Random Forest's ability to classify GA-1 false positives was found similar to results obtained using Clinical Laboratory Integrated Reports (CLIR). We developed an online Random Forest tool for interpretive analysis of increasingly complex data from newborn screening.

SUBMITTER: Peng G

PROVIDER: S-EPMC7080200 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Reducing False-Positive Results in Newborn Screening Using Machine Learning.

Peng Gang G Tang Yishuo Y Cowan Tina M TM Enns Gregory M GM Zhao Hongyu H Scharfe Curt C

International journal of neonatal screening 20200303 1

Newborn screening (NBS) for inborn metabolic disorders is a highly successful public health program that by design is accompanied by false-positive results. Here we trained a Random Forest machine learning classifier on screening data to improve prediction of true and false positives. Data included 39 metabolic analytes detected by tandem mass spectrometry and clinical variables such as gestational age and birth weight. Analytical performance was evaluated for a cohort of 2777 screen positives r ...[more]

PMID: 32190768

Similar Datasets

Project description:IntroductionEarly cancer detection can significantly improve patient outcomes and reduce mortality rates. Novel cancer screening approaches, including multi-cancer early detection tests, have been developed. Cost-utility analyses will be needed to examine their value, and these models require health state utilities. The purpose of this study was to estimate the disutility (i.e., decrease in health state utility) associated with false-positive cancer screening results.MethodsIn composite time trade-off interviews using a 1-year time horizon, UK general population participants valued 10 health state vignettes describing cancer screening with true-negative or false-positive results. Each false-positive vignette described a common diagnostic pathway following a false-positive result suggesting lung, colorectal, breast, or pancreatic cancer. Every pathway ended with a negative result (no cancer detected). The disutility of each false positive was calculated as the difference between the true-negative and each false-positive health state, and because of the 1-year time horizon, each disutility can be interpreted as a quality-adjusted life-year decrement associated with each type of false-positive experience.ResultsA total of 203 participants completed interviews (49.8% male; mean age = 42.0 years). The mean (SD) utility for the health state describing a true-negative result was 0.958 (0.065). Utilities for false-positive health states ranged from 0.847 (0.145) to 0.932 (0.059). Disutilities for false positives ranged from - 0.031 to - 0.111 (- 0.041 to - 0.111 for lung cancer; - 0.079 for colorectal cancer; - 0.031 to - 0.067 for breast cancer; - 0.048 to - 0.088 for pancreatic cancer).ConclusionAll false-positive results were associated with a disutility. Greater disutility was associated with more invasive follow-up diagnostic procedures, longer duration of uncertainty regarding the eventual diagnosis, and perceived severity of the suspected cancer type. Utility values estimated in this study would be useful for economic modeling examining the value of cancer screening procedures.

Project description:Very-long-chain acyl-CoA dehydrogenase (VLCAD) deficiency, a condition in which the body is unable to break down long-chain fatty acids properly, is the most common fatty acid oxidation disorder in Japan. Tandem mass spectrometry has been used in newborn screening (NBS), allowing the detection of patients with VLCAD deficiency even before symptoms manifest. However, tandem mass spectrometry has a high false positive rate. We investigated the clinical characteristics of patients with false positive results for tetradecenoyl acylcarnitine (C14:1). This case-control study used data collected between the 1st of January 2014 and the 31st of March 2019. The case group was defined as patients having levels of both C14:1 and C14:1/C2 ratio higher than cut-off levels in the first newborn mass screening, who were eventually diagnosed as false positives by attending doctors at Kobe University Hospital, Palmore Hospital, or Kakogawa Central City Hospital in Japan. The control group comprised 100 patients randomly selected from the three facilities. The false positive group included 17 cases, and the control group contained 300 patients. The demographics of each group did not show any significant differences in sex, body weight at birth, Cesarean section rate, complete breastfeeding rate, or the number of feedings per day. However, the change in body weight at the sampling day of NBS in the false positive and control groups was -10.2%, and - 4.6%, respectively, showing a statistically significant difference (p < 0.01). In addition, body weight gain at the one-month medical checkup was 38.9 g/day in the false positive group and 44.1 g/day in the control group (p < 0.05). An elevation of C14:1 carnitine has been reported in situations involving the catalysis of fatty acid. Therefore, patients with severe body weight loss might be associated with poor sucking or poor milk supply, which might cause a false positive elevation of C14:1 and C14:1/C2. In suspected VLCAD deficiency, attending doctors should pay attention to body weight changes recorded during newborn mass screening.

Dataset Information

Reducing False-Positive Results in Newborn Screening Using Machine Learning.

Publications

Reducing False-Positive Results in Newborn Screening Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets