Utilizing Augmented Artificial Intelligence for Aminoacidopathies Using Collaborative Laboratory Integrated Reporting- A Cross-sectional Study

Overview

Journal Ann Med Surg (Lond)

Publisher Wolters Kluwer

Specialty Medical Education

Date 2022 Oct 21

PMID 36268324

Authors

Zaib Un Nisa Khan

Lena Jafri

Patricia L Hall

Matthew J Schultz

Sibtain Ahmed

Aysha Habib Khan

Hafsa Majid

Affiliations

Soon will be listed here.

Abstract

Introduction: Plasma amino acids profiling can aid in the screening and diagnosis of aminoacidopathies. The goal of the current study was to analyze and report the metabolic profiles of plasma amino acid (PAA) and additionally to compare PAA-reference intervals (RI) from Pakistan with more countries utilizing Clinical Laboratory Integrated Reports (CLIR).

Methods: This was a cross sectional prospective single center study. Twenty-two amino acids were analyzed in each sample received for one year at the clinical laboratory Data was divided into reference and case data files after interpretation by a team of pathologists and technologists. All PAA samples were analyzed using ion-exchange high-performance chromatography. The CLIR application of Amino Acid in Plasma (AAQP) was used for statistical analysis for both data sets and post-analytical interpretive tools using a single condition tool was applied.

Result: The majority of 92% (n = 1913) of PAA profiles out of the total 2081 tests run were non-diagnostic; the PAA values were within the age-specific RI. The PAA median was in close comparison close to the 50th percentile of reference data available in CLIR software. Out of the total 2081 tests run, one hundred and sixty-eight had abnormal PAA levels; 27.38% were labeled as non-fasting samples, and the main aminoacidopathies identified were Phenylketonuria and Maple Syrup Urine Disorder.

Conclusion: An agreement of >95% was observed between the reporting done by the pathologists and technologists' team and then after the application of CLIR. Augmented artificial intelligence using CLIR can improve the accuracy of reporting rare aminoacidopathies in a developing country like ours.

Citing Articles

Current Status of Newborn Bloodspot Screening Worldwide 2024: A Comprehensive Review of Recent Activities (2020-2023).

Therrell B, Padilla C, Borrajo G, Khneisser I, Schielen P, Knight-Madden J Int J Neonatal Screen. 2024; 10(2).

PMID: 38920845 PMC: 11203842. DOI: 10.3390/ijns10020038.

References

Peng G, Tang Y, Cowan T, Enns G, Zhao H, Scharfe C . Reducing False-Positive Results in Newborn Screening Using Machine Learning. Int J Neonatal Screen. 2020; 6(1). PMC: 7080200. DOI: 10.3390/ijns6010016. View

Rowe A, Stoway S, Ahlman H, Arora V, Caggana M, Fornari A . A Novel Approach to Improve Newborn Screening for Congenital Hypothyroidism by Integrating Covariate-Adjusted Results of Different Tests into CLIR Customized Interpretive Tools. Int J Neonatal Screen. 2021; 7(2). PMC: 8167643. DOI: 10.3390/ijns7020023. View

Tortorelli S, Eckerman J, Orsini J, Stevens C, Hart J, Hall P . Moonlighting newborn screening markers: the incidental discovery of a second-tier test for Pompe disease. Genet Med. 2017; 20(8):840-846. DOI: 10.1038/gim.2017.190. View

Martin M, Wilson R, Caggana M, Orsini J . The Impact of Post-Analytical Tools on New York Screening for Krabbe Disease and Pompe Disease. Int J Neonatal Screen. 2020; 6(3). PMC: 7569953. DOI: 10.3390/ijns6030065. View

Wilkes E, Emmett E, Beltran L, Woodward G, Carling R . A Machine Learning Approach for the Automated Interpretation of Plasma Amino Acid Profiles. Clin Chem. 2020; 66(9):1210-1218. DOI: 10.1093/clinchem/hvaa134. View

Minter Baerg M, Stoway S, Hart J, Mott L, Peck D, Nett S . Precision newborn screening for lysosomal disorders. Genet Med. 2017; 20(8):847-854. DOI: 10.1038/gim.2017.194. View

Mak C, Hencher Lee H, Chan A, Lam C . Inborn errors of metabolism and expanded newborn screening: review and update. Crit Rev Clin Lab Sci. 2013; 50(6):142-62. DOI: 10.3109/10408363.2013.847896. View

Karam P, Habbal M, Mikati M, Zaatari G, Cortas N, Daher R . Diagnostic challenges of aminoacidopathies and organic acidemias in a developing country: a twelve-year experience. Clin Biochem. 2013; 46(18):1787-92. DOI: 10.1016/j.clinbiochem.2013.08.009. View

Fleischman A, Thompson J, Glass M . Systematic Data Collection to Inform Policy Decisions: Integration of the Region 4 Stork (R4S) Collaborative Newborn Screening Database to Improve MS/MS Newborn Screening in Washington State. JIMD Rep. 2013; 13:15-21. PMC: 4110324. DOI: 10.1007/8904_2013_266. View

10.

Sanders K, Gavrilov D, Oglesbee D, Raymond K, Tortorelli S, Hopwood J . A Comparative Effectiveness Study of Newborn Screening Methods for Four Lysosomal Storage Disorders. Int J Neonatal Screen. 2020; 6(2). PMC: 7423013. DOI: 10.3390/ijns6020044. View

11.

Majid H, Jafri L, Ali Z, Afroze B . Is diagnosing patients with Organic Acidurias and Aminoacidopathies enough? Conundrums of a low middle-income country. Pak J Med Sci. 2021; 37(7):1896-1901. PMC: 8613019. DOI: 10.12669/pjms.37.7.3887. View

12.

Tangeraas T, Saeves I, Klingenberg C, Jorgensen J, Kristensen E, Gunnarsdottir G . Performance of Expanded Newborn Screening in Norway Supported by Post-Analytical Bioinformatics Tools and Rapid Second-Tier DNA Analyses. Int J Neonatal Screen. 2020; 6(3):51. PMC: 7570219. DOI: 10.3390/ijns6030051. View

13.

Tang H, Matteson J, Rinaldo P, Tortorelli S, Currier R, Sciortino S . The Clinical Impact of CLIR Tools toward Rapid Resolution of Post-Newborn Screening Confirmatory Testing for X-Linked Adrenoleukodystrophy in California. Int J Neonatal Screen. 2020; 6(3):62. PMC: 7570356. DOI: 10.3390/ijns6030062. View

14.

Sorensen L, von Dobeln U, Ahlman H, Ohlsson A, Engvall M, Naess K . Expanded Screening of One Million Swedish Babies with R4S and CLIR for Post-Analytical Evaluation of Data. Int J Neonatal Screen. 2020; 6(2):42. PMC: 7423009. DOI: 10.3390/ijns6020042. View

15.

Hall P, Wittenauer A, Hagar A . Post-Analytical Tools for the Triage of Newborn Screening Results in Follow-up Can Reduce Confirmatory Testing and Guide Performance Improvement. Int J Neonatal Screen. 2020; 6(1):20. PMC: 7422973. DOI: 10.3390/ijns6010020. View

16.

Hafeez A, Ijaz A, Chaudhry N, Ali O, Khadim M . Diagnosis of inherited metabolic disorders by selective metabolite testing: three years' experience at a tertiary care center in Rawalpindi. J Pak Med Assoc. 2020; 70(1):53-57. DOI: 10.5455/JPMA.301908. View

17.

McHugh D, Cameron C, Abdenur J, Abdulrahman M, Adair O, Al Nuaimi S . Clinical validation of cutoff target ranges in newborn screening of metabolic disorders by tandem mass spectrometry: a worldwide collaborative project. Genet Med. 2011; 13(3):230-54. DOI: 10.1097/GIM.0b013e31820d5e67. View

18.

Saudubray J, Garcia-Cazorla A . Inborn Errors of Metabolism Overview: Pathophysiology, Manifestations, Evaluation, and Management. Pediatr Clin North Am. 2018; 65(2):179-208. DOI: 10.1016/j.pcl.2017.11.002. View

19.

Sherazi N, Khan A, Jafri L, Jamil A, Khan N, Afroze B . Selective Screening for Organic Acidurias and Amino Acidopathies in Pakistani Children. J Coll Physicians Surg Pak. 2017; 27(4):218-221. DOI: 2593. View

20.

Marquardt G, Currier R, McHugh D, Gavrilov D, Magera M, Matern D . Enhanced interpretation of newborn screening results without analyte cutoff values. Genet Med. 2012; 14(7):648-55. DOI: 10.1038/gim.2012.2. View