A missense mutation in human INSC causes peripheral neuropathy.

PAR3/INSC/LGN form an evolutionarily conserved complex required for asymmetric cell division in the developing brain, but its post-developmental function and disease relevance in the peripheral nervous system (PNS) remains unknown. We mapped a new locus for axonal Charcot-Marie-Tooth disease (CMT2) and identified a missense mutation c.209 T > G (p.Met70Arg) in the INSC gene. Modeling the INSCM70R variant in Drosophila, we showed that it caused proprioceptive defects in adult flies, leading to gait defects resembling those in CMT2 patients. Cellularly, PAR3/INSC/LGN dysfunction caused tubulin aggregation and necrotic neurodegeneration, with microtubule-stabilizing agents rescuing both morphological and functional defects of the INSCM70R mutation in the PNS. Our findings underscore the critical role of the PAR3/INSC/LGN machinery in the adult PNS and highlight a potential therapeutic target for INSC-associated CMT2.

Using Artificial Intelligence to Interpret Clinical Flow Cytometry Datasets for Automated Disease Diagnosis and/or Monitoring.

Flow cytometry (FC) is routinely used for hematological disease diagnosis and monitoring. Advancement in this technology allows us to measure an increasing number of markers simultaneously, generating complex high-dimensional datasets. However, current analytic software and methods rely on experienced analysts to perform labor-intensive manual inspection and interpretation on a series of 2-dimensional plots via a complex, sequential gating process. With an aggravating shortage of professionals and growing demands, it is very challenging to provide the FC analysis results in a fast, accurate, and reproducible way. Artificial intelligence has been widely used in many sectors to develop automated detection or classification tools. Here we describe a type of machine learning method for developing automated disease classification and residual disease monitoring on clinical flow datasets.

A Coarse-to-Fine Pathology Patch Selection for Improving Gene Mutation Prediction in Acute Myeloid Leukemia.

Identifying gene mutation is essential to prognosis and therapeutic decisions for acute myeloid leukemia (AML) but the current gene analysis is inefficient and non-scalable. Pathological images are readily accessible and can be effectively modeled using deep learning. This work aims at predicting gene mutation directly by modeling bone marrow smear images. Traditionally, bone marrow smear slides are cropped into patches with manual segmentation for patch-level modeling. Slide-level modeling, such as multi-instance learning, could aggregate patches for holistic modeling, though suffer from excessive redundancy. In this study, we propose a discriminative multi-instance approach to select useful patches in a coarse-to-fine process. Specifically, we preprocess a slide into patches by using a trained pre-selector network. Then, we rule out low quality patches in the coarse selection with known prior knowledge, and refine the model using gene-discriminative patches in the fine selection. We evaluate the framework for CEBPA, FLT3, and NPM1 gene mutation prediction and obtain 71.67%, 56.26%, and 56.34% F1-score. Further analysis show the effect of different selection criteria on prediction gene mutations using pathological images.

A Chunking-for-Pooling Strategy for Cytometric Representation Learning for Automatic Hematologic Malignancy Classification.

Differentiating types of hematologic malignancies is vital to determine therapeutic strategies for the newly diagnosed patients. Flow cytometry (FC) can be used as diagnostic indicator by measuring the multi-parameter fluorescent markers on thousands of antibody-bound cells, but the manual interpretation of large scale flow cytometry data has long been a time-consuming and complicated task for hematologists and laboratory professionals. Past studies have led to the development of representation learning algorithms to perform sample-level automatic classification. In this work, we propose a chunking-for-pooling strategy to include large-scale FC data into a supervised deep representation learning procedure for automatic hematologic malignancy classification. The use of discriminatively-trained representation learning strategy and the fixed-size chunking and pooling design are key components of this framework. It improves the discriminative power of the FC sample-level embedding and simultaneously addresses the robustness issue due to an inevitable use of down-sampling in conventional distribution based approaches for deriving FC representation. We evaluated our framework on two datasets. Our framework outperformed other baseline methods and achieved 92.3% unweighted average recall (UAR) for four-class recognition on the UPMC dataset and 85.0% UAR for five-class recognition on the hema.to dataset. We further compared the robustness of our proposed framework with that of the traditional downsampling approach. Analysis of the effects of the chunk size and the error cases revealed further insights about different hematologic malignancy characteristics in the FC data.

A Machine Learning Approach to the Classification of Acute Leukemias and Distinction From Nonneoplastic Cytopenias Using Flow Cytometry Data.

OBJECTIVES: Flow cytometry (FC) is critical for the diagnosis and monitoring of hematologic malignancies. Machine learning (ML) methods rapidly classify multidimensional data and should dramatically improve the efficiency of FC data analysis. We aimed to build a model to classify acute leukemias, including acute promyelocytic leukemia (APL), and distinguish them from nonneoplastic cytopenias. We also sought to illustrate a method to identify key FC parameters that contribute to the model's performance. METHODS: Using data from 531 patients who underwent evaluation for cytopenias and/or acute leukemia, we developed an ML model to rapidly distinguish among APL, acute myeloid leukemia/not APL, acute lymphoblastic leukemia, and nonneoplastic cytopenias. Unsupervised learning using gaussian mixture model and Fisher kernel methods were applied to FC listmode data, followed by supervised support vector machine classification. RESULTS: High accuracy (ACC, 94.2%; area under the curve [AUC], 99.5%) was achieved based on the 37-parameter FC panel. Using only 3 parameters, however, yielded similar performance (ACC, 91.7%; AUC, 98.3%) and highlighted the significant contribution of light scatter properties. CONCLUSIONS: Our findings underscore the potential for ML to automatically identify and prioritize FC specimens that have critical results, including APL and other acute leukemias.

Mitochondrial Function and Parkinson's Disease: From the Perspective of the Electron Transport Chain.

Parkinson's disease (PD) is known as a mitochondrial disease. Some even regarded it specifically as a disorder of the complex I of the electron transport chain (ETC). The ETC is fundamental for mitochondrial energy production which is essential for neuronal health. In the past two decades, more than 20 PD-associated genes have been identified. Some are directly involved in mitochondrial functions, such as PRKN, PINK1, and DJ-1. While other PD-associate genes, such as LRRK2, SNCA, and GBA1, regulate lysosomal functions, lipid metabolism, or protein aggregation, some have been shown to indirectly affect the electron transport chain. The recent identification of CHCHD2 and UQCRC1 that are critical for functions of complex IV and complex III, respectively, provide direct evidence that PD is more than just a complex I disorder. Like UQCRC1 in preventing cytochrome c from release, functions of ETC proteins beyond oxidative phosphorylation might also contribute to the pathogenesis of PD.

Leukoencephalopathy with Brainstem and Spinal Cord Involvement and Lactate Elevation: A Novel DARS2 Mutation and Intra-Familial Heterogeneity.

BACKGROUND: Leukoencephalopathy with brainstem and spinal cord involvement and lactate elevation (LBSL) is characterized by slowly progressive spastic gait, cerebellar symptoms, and posterior cord dysfunction. DARS2, which encodes mitochondrial aspartyl tRNA synthase, is associated with the rare disease. CASES: The proband had gait disturbance since age 56, while her younger brother had the gait problem since his 20s and needed cane-assistance at age 45. Both cases showed typical demyelinating features of LBSL on the magnetic resonance imaging (MRI) involving the periventricular white matter, brainstem, cerebellum and spinal cord. Sequencing of both cases showed compound heterozygous mutations: c.228-16C>A and c.508C>T in DARS2. The c.228-16C>A is a common mutation in splicing site of intron 2, which causes alternative splicing defect of exon 3, while the c.508C>T at the exon 6 is novel. Our patients are unique in the relative late onset and the apparent difference in disease progression. LITERATURE REVIEW: Literatures from PubMed were reviewed. Five families showed intra-familial heterogeneity on age at onset or clinical severity. CONCLUSION: We identified a family of LBSL with compound heterozygous mutations, and c.508C>T at the exon 6 is a novel one. Clinical heterogeneity was observed in the family and other literatures. Further research for underlying mechanism is required.

UQCRC1 engages cytochrome c for neuronal apoptotic cell death.

Human ubiquinol-cytochrome c reductase core protein 1 (UQCRC1) is an evolutionarily conserved core subunit of mitochondrial respiratory chain complex III. We recently identified the disease-associated variants of UQCRC1 from patients with familial parkinsonism, but its function remains unclear. Here we investigate the endogenous function of UQCRC1 in the human neuronal cell line and the Drosophila nervous system. Flies with neuronal knockdown of uqcrc1 exhibit age-dependent parkinsonism-resembling defects, including dopaminergic neuron reduction and locomotor decline, and are ameliorated by UQCRC1 expression. Lethality of uqcrc1-KO is also rescued by neuronally expressing UQCRC1, but not the disease-causing variant, providing a platform to discern the pathogenicity of this mutation. Furthermore, UQCRC1 associates with the apoptosis trigger cytochrome c (cyt-c), and uqcrc1 deficiency increases cyt-c in the cytoplasmic fraction and activates the caspase cascade. Depleting cyt-c or expression of the anti-apoptotic p35 ameliorates uqcrc1-mediated neurodegeneration. Our findings identify a role for UQCRC1 in regulating cyt-c-induced apoptosis.

A Knowledge-Reserved Distillation with Complementary Transfer for Automated FC-based Classification Across Hematological Malignancies.

Acute leukemia often comes with life-threatening prognosis outcome and remains a critical clinical issue today. The implementation of measurable residual disease (MRD) using flow cytometry (FC) is highly effective but the interpretation is time-consuming and suffers from physician idiosyncrasy. Recent machine learning algorithms have been proposed to automatically classify acute leukemia samples with and without MRD to address this clinical need. However, most prior works either validate only on a small data cohort or focus on one specific type of leukemia which lacks generalization. In this work, we propose a transfer learning approach in performing automatic MRD classification that takes advantage of a large scale acute myeloid leukemia (AML) database to facilitate better learning on a small cohort of acute lymphoblastic leukemia (ALL). Specifically, we develop a knowledge-reserved distilled AML pre-trained network with ALL complementary learning to enhance the ALL MRD classification. Our framework achieves 84.5% averaged AUC which shows its transferability across acute leukemia, and our further analysis reveals that younger and elder ALL patient samples benefit more from using the pre-trained AML model.

Predicting Gastrointestinal Bleeding Events from Multimodal In-Hospital Electronic Health Records Using Deep Fusion Networks.

Applying machine learning (ML) methods on electronic health records (EHRs) that accurately predict the occurrence of a variety of diseases or complications related to medications can contribute to improve healthcare quality. EHRs by nature contain multiple modalities of clinical data from heterogeneous sources that require proper fusion strategy. The deep neural network (DNN) approach, which possesses the ability to learn classification and feature representation, is well-suited to be employed in this context. In this study, we collect a large in-hospital EHR database to develop analytics in predicting 1-year gastrointestinal (GI) bleeding hospitalizations for patients taking anticoagulants or antiplatelet drugs. A total of 815,499 records (16,757 unique patients) are used in this study with three different available EHR modalities (disease diagnoses, medications usage, and laboratory testing measurements). We compare the performances of 4 deep multimodal fusion models and other ML approaches. NNs result in higher prediction performances compare to random forest (RF), gradient boosting decision tree (GBDT), and logistic regression (LR) approaches. We further demonstrate that deep multimodal NNs with early fusion can obtain the best GI bleeding predictive power (area under the receiver operator curve [AUROC] 0.876), which is significantly better than the HAS-BLED score (AUROC 0.668).

A BLSTM with Attention Network for Predicting Acute Myeloid Leukemia Patient's Prognosis using Comprehensive Clinical Parameters.

The prognosis management is crucial for highrisk disease like Acute Myeloid Leukemia (AML) in order to support decisions of clinical treatment. However, the challenges of accurate and consistent forecasting lie in the high variability of the disease outcomes and the complexity of the multiple clinical measurements available over the course of the treatment. In order to capture the multi-dimensional and longitudinal aspect of these comprehensive clinical parameters, we utilize an attention-based bi-directional long shortterm memory (Att-BLSTM) network to predict AML patient's survival and relapse. Specifically, we gather a 10-year worth of real patient's clinical data including blood test, medication, HSCT status, and gene mutation information. Our proposed Att-BLSTM framework achieves 77.1% and 67.3% AUC in tasks of predicting the next 2-year mortality and disease relapse with these comprehensive clinical parameters, and our further analysis demonstrates that a next 0 to 3 months prediction performs equally well, i.e., 74.8% and 67% AUC for mortality and relapse respectively.

Learning a Cytometric Deep Phenotype Embedding for Automatic Hematological Malignancies Classification.

Identification of minimal residual disease (MRD) is important in assessing the prognosis of acute myeloid leukemia (AML) and myelodysplastic syndrome (MDS). The current best clinical practice relies heavily on Flow Cytometry (FC) examination. However, the current FC diagnostic examination requires trained physicians to perform lengthy manual interpretation on high-dimensional FC data measurements of each specimen. The difficulty in handling idiosyncrasy between interpreters along with the time-consuming diagnostic process has become one of the major bottlenecks in advancing the treatment of hematological diseases. In this work, we develop an automatic MRD classifications (AML, MDS, normal) algorithm based on learning a deep phenotype representation from a large cohort of retrospective clinical data with over 2000 real patients' FC samples. We propose to learn a cytometric deep embedding through cell-level autoencoder combined with specimen-level latent Fisher-scoring vectorization. Our method achieves an average AUC of 0.943 across four different hematological malignancies classification tasks, and our analysis further reveals that with only half of the FC markers would be sufficient in obtaining these high recognition accuracies.

Clinically validated machine learning algorithm for detecting residual diseases with multicolor flow cytometry analysis in acute myeloid leukemia and myelodysplastic syndrome.

BACKGROUND: Multicolor flow cytometry (MFC) analysis is widely used to identify minimal residual disease (MRD) after treatment for acute myeloid leukemia (AML) and myelodysplastic syndrome (MDS). However, current manual interpretation suffers from drawbacks of time consuming and interpreter idiosyncrasy. Artificial intelligence (AI), with the expertise in assisting repetitive or complex analysis, represents a potential solution for these drawbacks. METHODS: From 2009 to 2016, 5333 MFC data from 1742 AML or MDS patients were collected. The 287 MFC data at post-induction were selected as the outcome set for clinical outcome validation. The rest were 4:1 randomized into the training set (n = 4039) and the validation set (n = 1007). AI algorithm learned a multi-dimensional MFC phenotype from the training set and input it to support vector machine (SVM) classifier after Gaussian mixture model (GMM) modeling, and the performance was evaluated in The validation set. FINDINGS: Promising accuracies (84·6% to 92·4%) and AUCs (0·921-0·950) were achieved by the developed algorithms. Interestingly, the algorithm from even one testing tube achieved similar performance. The clinical significance was validated in the outcome set, and normal MFC interpreted by the AI predicted better progression-free survival (10·9 vs 4·9 months, p < 0·0001) and overall survival (13·6 vs 6·5 months, p < 0·0001) for AML. INTERPRETATION: Through large-scaled clinical validation, we showed that AI algorithms can produce efficient and clinically-relevant MFC analysis. This approach also possesses a great advantage of the ability to integrate other clinical tests. FUND: This work was supported by the Ministry of Science and Technology (107-2634-F-007-006 and 103-2314-B-002-185-MY2) of Taiwan.