Cell Population Data-Driven Acute Promyelocytic Leukemia Flagging Through Artificial Neural Network Predictive Modeling

Construction of the prediction model for multiple myeloma based on machine learning

INTRODUCTION

The global burden of multiple myeloma (MM) is increasing every year. Here, we have developed machine learning models to provide a reference for the early detection of MM.

METHODS

A total of 465 patients and 150 healthy controls were enrolled in this retrospective study. Based on the variable screening strategy of least absolute shrinkage and selection operator (LASSO), three prediction models, logistic regression (LR), support vector machine (SVM), and random forest (RF), were established combining complete blood count (CBC) and cell population data (CPD) parameters in the training set (210 cases), and were verified in the validation set (90 cases) and test set (165 cases). The performance of each model was analyzed using receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA). Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC) were applied to evaluate the models. Delong test was used to compare the AUC of the models.

RESULTS

Six parameters including RBC (1012/L), RDW-CV (%), IG (%), NE-WZ, LY-WX, and LY-WZ were screened out by LASSO to construct the model. Among the three models, the AUC of RF model in the training set, validation set, and test set were 0.956, 0.892, and 0.875, which were higher than those of LR model (0.901, 0.849, and 0.858) and SVM model (0.929, 0.868, and 0.846). Delong test showed that there were significant differences among the models in the training set, no significant differences in the validation set, and significant differences only between SVM and RF models in the test set. The calibration curve and DCA showed that the three models had good validity and feasibility, and the RF model performed best.

CONCLUSION

The proposed RF model may be a useful auxiliary tool for rapid screening of MM patients.

Artificial neural network identified the significant genes to distinguish Idiopathic pulmonary fibrosis

Idiopathic pulmonary fibrosis (IPF) is a progressive interstitial lung disease that causes irreversible damage to lung tissue characterized by excessive deposition of extracellular matrix (ECM) and remodeling of lung parenchyma. The current diagnosis of IPF is complex and usually completed by a multidisciplinary team including clinicians, radiologists and pathologists they work together and make decision for an effective treatment, it is imperative to introduce novel practical methods for IPF diagnosis. This study provided a new diagnostic model of idiopathic pulmonary fibrosis based on machine learning. Six genes including CDH3, DIO2, ADAMTS14, HS6ST2, IL13RA2, and IGFL2 were identified based on the differentially expressed genes in IPF patients compare to healthy subjects through a random forest classifier with the existing gene expression databases. An artificial neural network model was constructed for IPF diagnosis based these genes, and this model was validated by the distinctive public datasets with a satisfactory diagnostic accuracy. These six genes identified were significant correlated with lung function, and among them, CDH3 and DIO2 were further determined to be significantly associated with the survival. Putting together, artificial neural network model identified the significant genes to distinguish idiopathic pulmonary fibrosis from healthy people and it is potential for molecular diagnosis of IPF.

Hematology and Machine Learning

BACKGROUND

Substantial improvements in computational power and machine learning (ML) algorithm development have vastly increased the limits of what autonomous machines are capable of. Since its beginnings in the 19th century, laboratory hematology has absorbed waves of progress yielding improvements in both of accuracy and efficiency. The next wave of change in laboratory hematology will be the result of the ML revolution that has already touched many corners of healthcare and society at large.

CONTENT

This review will describe the manifestations of ML and artificial intelligence (AI) already utilized in the clinical hematology laboratory. This will be followed by a topical summary of the innovative and investigational applications of this technology in each of the major subdomains within laboratory hematology.

SUMMARY

Application of this technology to laboratory hematology will increase standardization and efficiency by reducing laboratory staff involvement in automatable activities. This will unleash time and resources for focus on more meaningful activities such as the complexities of patient care, research and development, and process improvement.

A Review of Artificial Intelligence Applications in Hematology Management: Current Practices and Future Prospects

Background

Machine learning (ML) and deep learning (DL) methods have recently garnered a great deal of attention in the field of cancer research by making a noticeable contribution to the growth of predictive medicine and modern oncological practices. Considerable focus has been particularly directed toward hematologic malignancies because of the complexity in detecting early symptoms. Many patients with blood cancer do not get properly diagnosed until their cancer has reached an advanced stage with limited treatment prospects. Hence, the state-of-the-art revolves around the latest artificial intelligence (AI) applications in hematology management.

Objective

This comprehensive review provides an in-depth analysis of the current AI practices in the field of hematology. Our objective is to explore the ML and DL applications in blood cancer research, with a special focus on the type of hematologic malignancies and the patient’s cancer stage to determine future research directions in blood cancer.

Methods

We searched a set of recognized databases (Scopus, Springer, and Web of Science) using a selected number of keywords. We included studies written in English and published between 2015 and 2021. For each study, we identified the ML and DL techniques used and highlighted the performance of each model.

Results

Using the aforementioned inclusion criteria, the search resulted in 567 papers, of which 144 were selected for review.

Conclusions

The current literature suggests that the application of AI in the field of hematology has generated impressive results in the screening, diagnosis, and treatment stages. Nevertheless, optimizing the patient’s pathway to treatment requires a prior prediction of the malignancy based on the patient’s symptoms or blood records, which is an area that has still not been properly investigated.

Deep learning identifies Acute Promyelocytic Leukemia in bone marrow smears

BACKGROUND

Acute promyelocytic leukemia (APL) is considered a hematologic emergency due to high risk of bleeding and fatal hemorrhages being a major cause of death. Despite lower death rates reported from clinical trials, patient registry data suggest an early death rate of 20%, especially for elderly and frail patients. Therefore, reliable diagnosis is required as treatment with differentiation-inducing agents leads to cure in the majority of patients. However, diagnosis commonly relies on cytomorphology and genetic confirmation of the pathognomonic t(15;17). Yet, the latter is more time consuming and in some regions unavailable.

METHODS

In recent years, deep learning (DL) has been evaluated for medical image recognition showing outstanding capabilities in analyzing large amounts of image data and provides reliable classification results. We developed a multi-stage DL platform that automatically reads images of bone marrow smears, accurately segments cells, and subsequently predicts APL using image data only. We retrospectively identified 51 APL patients from previous multicenter trials and compared them to 1048 non-APL acute myeloid leukemia (AML) patients and 236 healthy bone marrow donor samples, respectively.

RESULTS

Our DL platform segments bone marrow cells with a mean average precision and a mean average recall of both 0.97. Further, it achieves high accuracy in detecting APL by distinguishing between APL and non-APL AML as well as APL and healthy donors with an area under the receiver operating characteristic of 0.8575 and 0.9585, respectively, using visual image data only.

CONCLUSIONS

Our study underlines not only the feasibility of DL to detect distinct morphologies that accompany a cytogenetic aberration like t(15;17) in APL, but also shows the capability of DL to abstract information from a small medical data set, i. e. 51 APL patients, and infer correct predictions. This demonstrates the suitability of DL to assist in the diagnosis of rare cancer entities. As our DL platform predicts APL from bone marrow smear images alone, this may be used to diagnose APL in regions were molecular or cytogenetic subtyping is not routinely available and raise attention to suspected cases of APL for expert evaluation.

Beyond the In-Practice CBC: The Research CBC Parameters-Driven Machine Learning Predictive Modeling for Early Differentiation among Leukemias

A targeted and timely treatment can be a beneficial tool for patients with hematological emergencies (particularly acute leukemias). The key challenges in the early diagnosis of leukemias and related hematological disorders are their symptom-sharing nature and prolonged turnaround time as well as the expertise needed in reporting confirmatory tests. The present study made use of the potential morphological and immature fraction-related parameters (research items or cell population data) generated during complete blood cell count (CBC), through artificial intelligence (AI)/machine learning (ML) predictive modeling for early (at the pre-microscopic level) differentiation of various types of leukemias: acute from chronic as well as myeloid from lymphoid. The routine CBC parameters along with research CBC items from a hematology analyzer in the diagnosis of 1577 study subjects with hematological neoplasms were collected. The statistical and data visualization tools, including heat-map and principal component analysis (PCA,) helped in the evaluation of the predictive capacity of research CBC items. Next, research CBC parameter-driven artificial neural network (ANN) predictive modeling was developed to use the hidden trend (disease’s signature) by increasing the auguring accuracy of these potential morphometric parameters in differentiation of leukemias. The classical statistics for routine and research CBC parameters showed that as a whole, all study items are significantly deviated among various types of leukemias (study groups). The CPD parameter-driven heat-map gave clustering (separation) of myeloid from lymphoid leukemias, followed by the segregation (nodding) of the acute from the chronic class of that particular lineage. Furthermore, acute promyelocytic leukemia (APML) was also well individuated from other types of acute myeloid leukemia (AML). The PCA plot guided by research CBC items at notable variance vindicated the aforementioned findings of the CPD-driven heat-map. Through training of ANN predictive modeling, the CPD parameters successfully differentiate the chronic myeloid leukemia (CML), AML, APML, acute lymphoid leukemia (ALL), chronic lymphoid leukemia (CLL), and other related hematological neoplasms with AUC values of 0.937, 0.905, 0.805, 0.829, 0.870, and 0.789, respectively, at an agreeably significant (10.6%) false prediction rate. Overall practical results of using our ANN model were found quite satisfactory with values of 83.1% and 89.4.7% for training and testing datasets, respectively. We proposed that research CBC parameters could potentially be used for early differentiation of leukemias in the hematology–oncology unit. The CPD-driven ANN modeling is a novel practice that substantially strengthens the predictive potential of CPD items, allowing the clinicians to be confident about the typical trend of the “disease fingerprint” shown by these automated potential morphometric items.

A machine learning PROGRAM to identify COVID-19 and other diseases from hematology data

AIM

We propose a method for screening full blood count metadata for evidence of communicable and noncommunicable diseases using machine learning (ML).

MATERIALS & METHODS

High dimensional hematology metadata was extracted over an 11-month period from Sysmex hematology analyzers from 43,761 patients. Predictive models for age, sex and individuality were developed to demonstrate the personalized nature of hematology data. Both numeric and raw flow cytometry data were used for both supervised and unsupervised ML to predict the presence of pneumonia, urinary tract infection and COVID-19. Heart failure was used as an objective to prove method generalizability.

RESULTS

Chronological age was predicted by a deep neural network with R2: 0.59; mean absolute error: 12; sex with AUROC: 0.83, phi: 0.47; individuality with 99.7% accuracy, phi: 0.97; pneumonia with AUROC: 0.74, sensitivity 58%, specificity 79%, 95% CI: 0.73-0.75, p < 0.0001; urinary tract infection AUROC: 0.68, sensitivity 52%, specificity 79%, 95% CI: 0.67-0.68, p < 0.0001; COVID-19 AUROC: 0.8, sensitivity 82%, specificity 75%, 95% CI: 0.79-0.8, p = 0.0006; and heart failure area under the receiver operator curve (AUROC): 0.78, sensitivity 72%, specificity 72%, 95% CI: 0.77-0.78; p < 0.0001.

CONCLUSION

ML applied to hematology data could predict communicable and noncommunicable diseases, both at local and global levels.

Leukocyte cell population data from the blood cell analyzer as a predictive marker for severity of acute pancreatitis

BACKGROUND

The prediction for severe acute pancreatitis (SAP) is the key to give timely targeted treatment. Leukocyte cell population data (CPD) have been widely applied in early prediction and diagnosis of many diseases, but their predictive ability for SAP remains unexplored. We aim to testify whether CPD could be an indicator of AP severity in the early stage of the disease.

METHODS

The prospective observational study was conducted in the emergency department ward of a territory hospital in Shanghai. The enrolled AP patients should meet 2012 Atlanta guideline.

RESULTS

Totally, 103 AP patients and 62 healthy controls were enrolled and patients were classified into mild AP (n = 30), moderate SAP (n = 42), and SAP (n = 31). Forty-two CPD parameters were examined in first 3 days of admission. Four CPD parameters were highest in SAP on admission and were constantly different among 3 groups during first 3 days of hospital stay. Eighteen CPD parameters were found correlated with the occurrence of SAP. Stepwise multivariate logistic regression analysis identified a scoring system of 4 parameters (SD_LALS_NE, MN_LALS_LY, SD_LMALS_MO, and SD_AL2_MO) with a sensitivity of 96.8%, specificity of 65.3%, and AUC of 0.87 for diagnostic accuracy on early identification of SAP. AUC of this scoring system was comparable with MCTSI, SOFA, APACHE II, MMS, BISAP, or biomarkers as CRP, PCT, and WBC in prediction of SAP and ICU transfer or death.

CONCLUSIONS

Several leukocyte CPD parameters have been identified different among MAP, MSAP, and SAP. They might be ultimately incorporated into a predictive system marker for severity of AP.