Machine Learning for Early Diagnosis of ATTRv Amyloidosis in Non-Endemic Areas: A Multicenter Study from Italy.
ATTRv
TTR
genetic screening
genetic testing
hereditary amyloid neuropathy
machine learning
Journal
Brain sciences
ISSN: 2076-3425
Titre abrégé: Brain Sci
Pays: Switzerland
ID NLM: 101598646
Informations de publication
Date de publication:
16 May 2023
16 May 2023
Historique:
received:
06
04
2023
revised:
12
05
2023
accepted:
14
05
2023
medline:
27
5
2023
pubmed:
27
5
2023
entrez:
27
5
2023
Statut:
epublish
Résumé
Hereditary transthyretin amyloidosis with polyneuropathy (ATTRv) is an adult-onset multisystemic disease, affecting the peripheral nerves, heart, gastrointestinal tract, eyes, and kidneys. Nowadays, several treatment options are available; thus, avoiding misdiagnosis is crucial to starting therapy in early disease stages. However, clinical diagnosis may be difficult, as the disease may present with unspecific symptoms and signs. We hypothesize that the diagnostic process may benefit from the use of machine learning (ML). 397 patients referring to neuromuscular clinics in 4 centers from the south of Italy with neuropathy and at least 1 more red flag, as well as undergoing genetic testing for ATTRv, were considered. Then, only probands were considered for analysis. Hence, a cohort of 184 patients, 93 with positive and 91 (age- and sex-matched) with negative genetics, was considered for the classification task. The XGBoost (XGB) algorithm was trained to classify positive and negative diabetes, gender, unexplained weight loss, cardiomyopathy, bilateral carpal tunnel syndrome (CTS), ocular symptoms, autonomic symptoms, ataxia, renal dysfunction, lumbar canal stenosis, and history of autoimmunity were used for the model training. The XGB model showed an accuracy of 0.707 ± 0.101, a sensitivity of 0.712 ± 0.147, a specificity of 0.704 ± 0.150, and an AUC-ROC of 0.752 ± 0.107. Using the SHAP explanation, it was confirmed that unexplained weight loss, gastrointestinal symptoms, and cardiomyopathy showed a significant association with the genetic diagnosis of ATTRv, while bilateral CTS, diabetes, autoimmunity, and ocular and renal involvement were associated with a negative genetic test. Our data show that ML might potentially be a useful instrument to identify patients with neuropathy that should undergo genetic testing for ATTRv. Unexplained weight loss and cardiomyopathy are relevant red flags in ATTRv in the south of Italy. Further studies are needed to confirm these findings.
Sections du résumé
BACKGROUND
BACKGROUND
Hereditary transthyretin amyloidosis with polyneuropathy (ATTRv) is an adult-onset multisystemic disease, affecting the peripheral nerves, heart, gastrointestinal tract, eyes, and kidneys. Nowadays, several treatment options are available; thus, avoiding misdiagnosis is crucial to starting therapy in early disease stages. However, clinical diagnosis may be difficult, as the disease may present with unspecific symptoms and signs. We hypothesize that the diagnostic process may benefit from the use of machine learning (ML).
METHODS
METHODS
397 patients referring to neuromuscular clinics in 4 centers from the south of Italy with neuropathy and at least 1 more red flag, as well as undergoing genetic testing for ATTRv, were considered. Then, only probands were considered for analysis. Hence, a cohort of 184 patients, 93 with positive and 91 (age- and sex-matched) with negative genetics, was considered for the classification task. The XGBoost (XGB) algorithm was trained to classify positive and negative
RESULTS
RESULTS
diabetes, gender, unexplained weight loss, cardiomyopathy, bilateral carpal tunnel syndrome (CTS), ocular symptoms, autonomic symptoms, ataxia, renal dysfunction, lumbar canal stenosis, and history of autoimmunity were used for the model training. The XGB model showed an accuracy of 0.707 ± 0.101, a sensitivity of 0.712 ± 0.147, a specificity of 0.704 ± 0.150, and an AUC-ROC of 0.752 ± 0.107. Using the SHAP explanation, it was confirmed that unexplained weight loss, gastrointestinal symptoms, and cardiomyopathy showed a significant association with the genetic diagnosis of ATTRv, while bilateral CTS, diabetes, autoimmunity, and ocular and renal involvement were associated with a negative genetic test.
CONCLUSIONS
CONCLUSIONS
Our data show that ML might potentially be a useful instrument to identify patients with neuropathy that should undergo genetic testing for ATTRv. Unexplained weight loss and cardiomyopathy are relevant red flags in ATTRv in the south of Italy. Further studies are needed to confirm these findings.
Identifiants
pubmed: 37239276
pii: brainsci13050805
doi: 10.3390/brainsci13050805
pmc: PMC10216819
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
Amyloid. 2011 Jun;18(2):53-62
pubmed: 21463231
Curr Probl Cardiol. 2023 Feb;48(2):101487
pubmed: 36336119
Genes (Basel). 2021 May 28;12(6):
pubmed: 34071271
Comput Methods Programs Biomed. 2019 Aug;177:89-112
pubmed: 31319964
Amyloid. 2019 Sep;26(3):139-147
pubmed: 31210531
J Peripher Nerv Syst. 2021 Jun;26(2):155-159
pubmed: 33960565
J Clin Med. 2020 May 03;9(5):
pubmed: 32375287
Neurol Sci. 2020 Dec;41(12):3719-3727
pubmed: 32518996
ESC Heart Fail. 2019 Oct;6(5):1041-1051
pubmed: 31487121
J Neurol. 2022 Aug;269(8):4281-4287
pubmed: 35279758
J Neurol. 2021 Jun;268(6):2109-2122
pubmed: 31907599
Neurology. 1982 Dec;32(12):1364-8
pubmed: 6890642
J Neurol Neurosurg Psychiatry. 2017 May;88(5):457-458
pubmed: 28188196
Muscle Nerve. 2018 May;57(5):829-837
pubmed: 29211930
J Cardiovasc Magn Reson. 2020 Dec 7;22(1):84
pubmed: 33287829
Orphanet J Rare Dis. 2020 Dec 14;15(1):348
pubmed: 33317601
Orphanet J Rare Dis. 2018 Jan 17;13(1):6
pubmed: 29343286
Brain Sci. 2020 Oct 26;10(11):
pubmed: 33114611
Nat Mach Intell. 2020 Jan;2(1):56-67
pubmed: 32607472
J Gastroenterol Hepatol. 2018 Mar;33(3):583-590
pubmed: 28940821
Amyloid. 2020 Dec;27(4):279-280
pubmed: 32515606
Pharmgenomics Pers Med. 2022 May 12;15:499-514
pubmed: 35592550
PLoS Med. 2018 Nov 27;15(11):e1002702
pubmed: 30481173
Orphanet J Rare Dis. 2019 Feb 8;14(1):34
pubmed: 30736835
Biomedicines. 2022 Dec 27;11(1):
pubmed: 36672570
Adv Tech Stand Neurosurg. 2007;32:175-249
pubmed: 17907478
Crit Rev Clin Lab Sci. 2021 Jun;58(4):275-296
pubmed: 33739235
BMC Med Inform Decis Mak. 2020 Nov 30;20(1):310
pubmed: 33256715
Amyloid. 1999 Jun;6(2):124-9
pubmed: 10439119
Brain Sci. 2020 Dec 09;10(12):
pubmed: 33316911
Front Neurol. 2022 Feb 28;13:835812
pubmed: 35295833
JAMA. 1999 Jul 14;282(2):153-8
pubmed: 10411196
J Peripher Nerv Syst. 2016 Mar;21(1):5-9
pubmed: 26663427
Neurol Ther. 2020 Dec;9(2):317-333
pubmed: 32948978
BMC Bioinformatics. 2019 Jul 30;20(1):409
pubmed: 31362694
J Diabetes Complications. 2019 Aug;33(8):598-601
pubmed: 31129004
Heart Fail Rev. 2022 May;27(3):785-793
pubmed: 33609196
Orphanet J Rare Dis. 2014 Apr 27;9:61
pubmed: 24767411
Diabetologia. 2021 Feb;64(2):275-287
pubmed: 33313987
Amyloid. 2020 Dec;27(4):259-265
pubmed: 32696671
Neurol Sci. 2022 May;43(5):3435-3438
pubmed: 35098361
BMC Fam Pract. 2020 Sep 23;21(1):198
pubmed: 32967612
Comput Biol Med. 2021 May;132:104335
pubmed: 33812263
N Engl J Med. 2018 Sep 13;379(11):1007-1016
pubmed: 30145929
Prim Care Diabetes. 2019 Dec;13(6):521-528
pubmed: 31126745