Continuous Indexing of Fibrosis (CIF): improving the assessment and classification of MPN patients
Hosuk Ryou1, Korsuk Sirinukunwattana2,3,4,5, Alan Aberdeen4
1Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, University of Oxford, Oxford, UK.
Abstract:
The grading of fibrosis in myeloproliferative neoplasms (MPN) is an important component of disease classification, prognostication and monitoring. However, current fibrosis grading systems are only semi-quantitative and fail to fully capture sample heterogeneity. To improve the quantitation of reticulin fibrosis, we developed a machine learning approach using bone marrow trephine (BMT) samples (n = 107) from patients diagnosed with MPN or a reactive marrow. The resulting Continuous Indexing of Fibrosis (CIF) enhances the detection and monitoring of fibrosis within BMTs, and aids MPN subtyping. When combined with megakaryocyte feature analysis, CIF discriminates between the frequently challenging differential diagnosis of essential thrombocythemia (ET) and pre-fibrotic myelofibrosis with high predictive accuracy [area under the curve = 0.94]. CIF also shows promise in the identification of MPN patients at risk of disease progression; analysis of samples from 35 patients diagnosed with ET and enrolled in the Primary Thrombocythemia-1 trial identified features predictive of post-ET myelofibrosis (area under the curve = 0.77). In addition to these clinical applications, automated analysis of fibrosis has clear potential to further refine disease classification boundaries and inform future studies of the micro-environmental factors driving disease initiation and progression in MPN and other stem cell disorders.
Insights
A new machine learning tool, Continuous Indexing of Fibrosis (CIF), accurately quantifies bone marrow fibrosis in myeloproliferative neoplasms (MPN). CIF aids in MPN subtyping and predicting disease progression.
Area of Science:
- Hematology
- Computational Pathology
- Oncology
Background:
- Fibrosis grading in myeloproliferative neoplasms (MPN) is crucial for classification, prognosis, and monitoring.
- Current semi-quantitative methods lack precision and fail to account for sample heterogeneity.
Purpose of the Study:
- To develop and validate a machine learning approach for precise quantitation of reticulin fibrosis in bone marrow trephine (BMT) samples.
- To assess the utility of the developed Continuous Indexing of Fibrosis (CIF) in MPN subtyping and prognostication.
Main Methods:
- A machine learning model was trained on 107 BMT samples from MPN patients and controls.
- The model, termed Continuous Indexing of Fibrosis (CIF), was developed to quantify reticulin fibrosis.
- CIF was evaluated for its ability to differentiate essential thrombocythemia (ET) from pre-fibrotic myelofibrosis and predict post-ET myelofibrosis.
Main Results:
- The CIF model accurately quantifies fibrosis in BMT samples, enhancing detection and monitoring.
- Combined with megakaryocyte analysis, CIF achieved high accuracy (AUC=0.94) in distinguishing ET from pre-fibrotic myelofibrosis.
- CIF identified features predicting progression to myelofibrosis in ET patients (AUC=0.77).
Conclusions:
- The Continuous Indexing of Fibrosis (CIF) offers a quantitative method for assessing bone marrow fibrosis in MPN.
- CIF demonstrates significant potential in improving MPN classification, differential diagnosis, and risk stratification for disease progression.
- Automated fibrosis analysis can refine disease boundaries and guide future research into MPN pathogenesis.
More Related Videos
Related Concept Videos
01:25Ultrasound II: Endoscopic Ultrasound and FibroScan
Endoscopic Ultrasound (EUS):
01:09Introduction to Fibroblasts