Machine Learning and Deep Learning Applications in Multiple Myeloma Diagnosis, Prognosis, and Treatment Selection

Artificial intelligence in the clinical laboratory

Laboratory medicine has become a highly automated medical discipline. Nowadays, artificial intelligence (AI) applied to laboratory medicine is also gaining more and more attention, which can optimize the entire laboratory workflow and even revolutionize laboratory medicine in the future. However, only a few commercially available AI models are currently approved for use in clinical laboratories and have drawbacks such as high cost, lack of accuracy, and the need for manual review of model results. Furthermore, there are a limited number of literature reviews that comprehensively address the research status, challenges, and future opportunities of AI applications in laboratory medicine. Our article begins with a brief introduction to AI and some of its subsets, then reviews some AI models that are currently being used in clinical laboratories or that have been described in emerging studies, and explains the existing challenges associated with their application and possible solutions, finally provides insights into the future opportunities of the field. We highlight the current status of implementation and potential applications of AI models in different stages of the clinical testing process.

Enhancing diagnostic accuracy of multiple myeloma through ML-driven analysis of hematological slides: new dataset and identification model to support hematologists

Multiple Myeloma (MM) is a hematological malignancy characterized by the clonal proliferation of plasma cells within the bone marrow. Diagnosing MM presents considerable challenges, involving the identification of plasma cells in cytology examinations on hematological slides. At present, this is still a time-consuming manual task and has high labor costs. These challenges have adverse implications, which rely heavily on medical professionals' expertise and experience. To tackle these challenges, we present an investigation using Artificial Intelligence, specifically a Machine Learning analysis of hematological slides with a Deep Neural Network (DNN), to support specialists during the process of diagnosing MM. In this sense, the contribution of this study is twofold: in addition to the trained model to diagnose MM, we also make available to the community a fully-curated hematological slide dataset with thousands of images of plasma cells. Taken together, the setup we established here is a framework that researchers and hospitals with limited resources can promptly use. Our contributions provide practical results that have been directly applied in the public health system in Brazil. Given the open-source nature of the project, we anticipate it will be used and extended to diagnose other malignancies.

Artificial Intelligence: A Snapshot of Its Application in Chronic Inflammatory and Autoimmune Skin Diseases

Immuno-correlated dermatological pathologies refer to skin disorders that are closely associated with immune system dysfunction or abnormal immune responses. Advancements in the field of artificial intelligence (AI) have shown promise in enhancing the diagnosis, management, and assessment of immuno-correlated dermatological pathologies. This intersection of dermatology and immunology plays a pivotal role in comprehending and addressing complex skin disorders with immune system involvement. The paper explores the knowledge known so far and the evolution and achievements of AI in diagnosis; discusses segmentation and the classification of medical images; and reviews existing challenges, in immunological-related skin diseases. From our review, the role of AI has emerged, especially in the analysis of images for both diagnostic and severity assessment purposes. Furthermore, the possibility of predicting patients' response to therapies is emerging, in order to create tailored therapies.

Deep Learning Enables Spatial Mapping of the Mosaic Microenvironment of Myeloma Bone Marrow Trephine Biopsies

Bone marrow trephine biopsy is crucial for the diagnosis of multiple myeloma. However, the complexity of bone marrow cellular, morphologic, and spatial architecture preserved in trephine samples hinders comprehensive evaluation. To dissect the diverse cellular communities and mosaic tissue habitats, we developed a superpixel-inspired deep learning method (MoSaicNet) that adapts to complex tissue architectures and a cell imbalance aware deep learning pipeline (AwareNet) to enable accurate detection and classification of rare cell types in multiplex immunohistochemistry images. MoSaicNet and AwareNet achieved an AUC of >0.98 for tissue and cellular classification on separate test datasets. Application of MoSaicNet and AwareNet enabled investigation of bone heterogeneity and thickness as well as spatial histology analysis of bone marrow trephine samples from monoclonal gammopathies of undetermined significance (MGUS) and from paired newly diagnosed and posttreatment multiple myeloma. The most significant difference between MGUS and newly diagnosed multiple myeloma (NDMM) samples was not related to cell density but to spatial heterogeneity, with reduced spatial proximity of BLIMP1+ tumor cells to CD8+ cells in MGUS compared with NDMM samples. Following treatment of patients with multiple myeloma, there was a reduction in the density of BLIMP1+ tumor cells, effector CD8+ T cells, and regulatory T cells, indicative of an altered immune microenvironment. Finally, bone heterogeneity decreased following treatment of patients with multiple myeloma. In summary, deep learning-based spatial mapping of bone marrow trephine biopsies can provide insights into the cellular topography of the myeloma marrow microenvironment and complement aspirate-based techniques.

SIGNIFICANCE

Spatial analysis of bone marrow trephine biopsies using histology, deep learning, and tailored algorithms reveals the bone marrow architectural heterogeneity and evolution during myeloma progression and treatment.

Staging classification of omicron variant SARS-CoV-2 infection based on dual-spectrometer LIBS (DS-LIBS) combined with machine learning

Effective differentiation of the infection stages of omicron can provide significant assistance in transmission control and treatment strategies. The combination of LIBS serum detection and machine learning methods, as a novel disease auxiliary diagnostic approach, has a high potential for rapid and accurate staging classification of Omicron infection. However, conventional single-spectrometer LIBS serum detection methods focus on detecting the spectra of major elements, while trace elements are more closely related to the progression of COVID-19. Here, we proposed a rapid analytical method with dual-spectrometer LIBS (DS-LIBS) assisted with machine learning to classify different infection stages of omicron. The DS-LIBS, including a broadband spectrometer and a narrowband spectrometer, enables synchronous collection of major and trace elemental spectra in serum, respectively. By employing the RF machine learning models, the classification accuracy using the spectra data collected from DS-LIBS can reach 0.92, compared to 0.84 and 0.73 when using spectra data collected from single-spectrometer LIBS. This significant improvement in classification accuracy highlights the efficacy of the DS-LIBS approach. Then, the performance of four different models, SVM, RF, IGBT, and ETree, is compared. ETree demonstrates the best, with cross-validation and test set accuracies of 0.94 and 0.93, respectively. Additionally, it achieves classification accuracies of 1.00, 0.92, 0.92, and 0.89 for the four stages B1-acute, B1-post, B2, and B3. Overall, the results demonstrate that DS-LIBS combined with the ETree machine learning model enables effective staging classification of omicron infection.

Current Status and Future of Artificial Intelligence in MM Imaging: A Systematic Review

Artificial intelligence (AI) has attracted increasing attention as a tool for the detection and management of several medical conditions. Multiple myeloma (MM), a malignancy characterized by uncontrolled proliferation of plasma cells, is one of the most common hematologic malignancies, which relies on imaging for diagnosis and management. We aimed to review the current literature and trends in AI research of MM imaging. This study was performed according to the PRISMA guidelines. Three main concepts were used in the search algorithm, including "artificial intelligence" in "radiologic examinations" of patients with "multiple myeloma". The algorithm was used to search the PubMed, Embase, and Web of Science databases. Articles were screened based on the inclusion and exclusion criteria. In the end, we used the checklist for Artificial Intelligence in Medical Imaging (CLAIM) criteria to evaluate the manuscripts. We provided the percentage of studies that were compliant with each criterion as a measure of the quality of AI research on MM. The initial search yielded 977 results. After reviewing them, 14 final studies were selected. The studies used a wide array of imaging modalities. Radiomics analysis and segmentation tasks were the most popular studies (10/14 studies). The common purposes of radiomics studies included the differentiation of MM bone lesions from other lesions and the prediction of relapse. The goal of the segmentation studies was to develop algorithms for the automatic segmentation of important structures in MM. Dice score was the most common assessment tool in segmentation studies, which ranged from 0.80 to 0.97. These studies show that imaging is a valuable data source for medical AI models and plays an even greater role in the management of MM.

Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach

This paper describes a machine learning (ML) decision support system to provide a list of chemotherapeutics that individual multiple myeloma (MM) patients are sensitive/resistant to, based on their proteomic profile. The methodology used in this study involved understanding the parameter space and selecting the dominant features (proteomics data), identifying patterns of proteomic profiles and their association to the recommended treatments, and defining the decision support system of personalized treatment as a classification problem. During the data analysis, we compared several ML algorithms, such as linear regression, Random Forest, and support vector machines, to classify patients as sensitive/resistant to therapeutics. A further analysis examined data-balancing techniques that emerged due to the small cohort size. The results suggest that utilizing proteomics data is a promising approach for identifying effective treatment options for patients with MM (reaching on average an accuracy of 81%). Although this pilot study was limited by the small patient cohort (39 patients), which restricted the training and validation of the explored ML solutions to identify complex associations between proteins, it holds great promise for developing personalized anti-MM treatments using ML approaches.

Machine Learning Approach for Rapid, Accurate Point-of-Care Prediction of M-Spike Values in Multiple Myeloma

PURPOSE

The gold standard for monitoring response status in patients with multiple myeloma (MM) is serum and urine protein electrophoresis which quantify M-spike proteins; however, the turnaround time for results is 3-7 days which delays treatment decisions. We hypothesized that machine learning (ML) could integrate readily available clinical and laboratory data to rapidly and accurately predict patient M-spike values.

METHODS

A retrospective chart review was performed using the deidentified, electronic medical records of 171 patients with MM.

RESULTS

Random forest (RF) analysis identified the weighted value of each independent variable (N = 43) integrated into the ML algorithm. Pearson and Spearman coefficients indicated that the ML-predicted M-spike values correlated highly with laboratory-measured serum protein electrophoresis values. Feature selected RF modeling revealed that only two variables-the first lagged M-spike and serum total protein-accurately predicted the M-spike.

CONCLUSION

Taken together, our results demonstrate the feasibility and prognostic potential of ML tools that integrate electronic data to longitudinally monitor disease burden. ML tools support the seamless, secure exchange of patient information to expedite and personalize clinical decision making and overcome geographic, financial, and social barriers that currently limit the access of underserved populations to cancer care specialists so that the benefits of medical progress are not limited to selected groups.

New Developments in Myeloma Treatment and Response Assessment

Recent innovative strategies have dramatically redefined the therapeutic landscape for treating multiple myeloma patients. In particular, the development and application of immunotherapy and high-dose therapy have demonstrated high response rates and have prolonged remission duration. Over the past decade, new morphologic or hybrid imaging techniques have gradually replaced conventional skeletal surveys. PET/CT using 18F-FDG is a powerful imaging tool for the workup at diagnosis and for therapeutic evaluation allowing medullary and extramedullary assessment. The independent negative prognostic value for progression-free and overall survival derived from baseline PET-derived parameters such as the presence of extramedullary disease or paramedullary disease, as well as the number of focal bone lesions and SUVmax, has been reported in several large prospective studies. During therapeutic evaluation, 18F-FDG PET/CT is considered the reference imaging technique because it can be performed much earlier than MRI, which lacks specificity. Persistence of significant abnormal 18F-FDG uptake after therapy is an independent negative prognostic factor, and 18F-FDG PET/CT and medullary flow cytometry are complementary tools for detecting minimal residual disease before maintenance therapy. The definition of a PET metabolic complete response has recently been standardized and the interpretation criteria harmonized. The development of advanced PET analysis and radiomics using machine learning, as well as hybrid imaging with PET/MRI, offers new perspectives for multiple myeloma imaging. Most recently, innovative radiopharmaceuticals such as C-X-C chemokine receptor type 4-targeted small molecules and anti-CD38 radiolabeled antibodies have shown promising results for tumor phenotype imaging and as potential theranostics.

Hybrid black widow optimization with iterated greedy algorithm for gene selection problems

Gene Selection (GS) is a strategy method targeted at reducing redundancy, limited expressiveness, and low informativeness in gene expression datasets obtained by DNA Microarray technology. These datasets contain a plethora of diverse and high-dimensional samples and genes, with a significant discrepancy in the number of samples and genes present. The complexities of GS are especially noticeable in the context of microarray expression data analysis, owing to the inherent data imbalance. The main goal of this study is to offer a simplified and computationally effective approach to dealing with the conundrum of attribute selection in microarray gene expression data. We use the Black Widow Optimization algorithm (BWO) in the context of GS to achieve this, using two unique methodologies: the unaltered BWO variation and the hybridized BWO variant combined with the Iterated Greedy algorithm (BWO-IG). By improving the local search capabilities of BWO, this hybridization attempts to promote more efficient gene selection. A series of tests was carried out using nine benchmark datasets that were obtained from the gene expression data repository in the pursuit of empirical validation. The results of these tests conclusively show that the BWO-IG technique performs better than the traditional BWO algorithm. Notably, the hybridized BWO-IG technique excels in the efficiency of local searches, making it easier to identify relevant genes and producing findings with higher levels of reliability in terms of accuracy and the degree of gene pruning. Additionally, a comparison analysis is done against five modern wrapper Feature Selection (FS) methodologies, namely BIMFOHHO, BMFO, BHHO, BCS, and BBA, in order to put the suggested BWO-IG method's effectiveness into context. The comparison that follows highlights BWO-IG's obvious superiority in reducing the number of selected genes while also obtaining remarkably high classification accuracy. The key findings were an average classification accuracy of 94.426, average fitness values of 0.061, and an average number of selected genes of 2933.767.

Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.

18F‑FDG PET/CT based radiomics features improve prediction of prognosis: multiple machine learning algorithms and multimodality applications for multiple myeloma

PURPOSE

Multiple myeloma (MM), the second most hematological malignancy, have been studied extensively in the prognosis of the clinical parameters, however there are only a few studies have discussed the role of dual modalities and multiple algorithms of ¹⁸F-FDG (¹⁸F-fluorodeoxyglucose) PET/CT based radiomics signatures for prognosis in MM patients. We hope to deeply mine the utility of raiomics data in the prognosis of MM.

METHODS

We extensively explored the predictive ability and clinical decision-making ability of different combination image data of PET, CT, clinical parameters and six machine learning algorithms, Cox proportional hazards model (Cox), linear gradient boosting models based on Cox's partial likelihood (GB-Cox), Cox model by likelihood based boosting (CoxBoost), generalized boosted regression modelling (GBM), random forests for survival model (RFS) and support vector regression for censored data model (SVCR). And the model evaluation methods include Harrell concordance index, time dependent receiver operating characteristic (ROC) curve, and decision curve analysis (DCA).

RESULTS

We finally confirmed 5 PET based features, and 4 CT based features, as well as 6 clinical derived features significantly related to progression free survival (PFS) and we included them in the model construction. In various modalities combinations, RSF and GBM algorithms significantly improved the accuracy and clinical net benefit of predicting prognosis compared with other algorithms. For all combinations of various modalities based models, single-modality PET based prognostic models' performance was outperformed baseline clinical parameters based models, while the performance of models of PET and CT combined with clinical parameters was significantly improved in various algorithms.

CONCLUSION

¹⁸F‑FDG PET/CT based radiomics models implemented with machine learning algorithms can significantly improve the clinical prediction of progress and increased clinical benefits providing prospects for clinical prognostic stratification for precision treatment as well as new research areas.

ML-based sequential analysis to assist selection between VMP and RD for newly diagnosed multiple myeloma

Optimal first-line treatment that enables deeper and longer remission is crucially important for newly diagnosed multiple myeloma (NDMM). In this study, we developed the machine learning (ML) models predicting overall survival (OS) or response of the transplant-ineligible NDMM patients when treated by one of the two regimens-bortezomib plus melphalan plus prednisone (VMP) or lenalidomide plus dexamethasone (RD). Demographic and clinical characteristics obtained during diagnosis were used to train the ML models, which enabled treatment-specific risk stratification. Survival was superior when the patients were treated with the regimen to which they were low risk. The largest difference in OS was observed in the VMP-low risk & RD-high risk group, who recorded a hazard ratio of 0.15 (95% CI: 0.04-0.55) when treated with VMP vs. RD regimen. Retrospective analysis showed that the use of the ML models might have helped to improve the survival and/or response of up to 202 (39%) patients among the entire cohort (N = 514). In this manner, we believe that the ML models trained on clinical data available at diagnosis can assist the individualized selection of optimal first-line treatment for transplant-ineligible NDMM patients.

A machine learning analysis to evaluate the outcome measures in inflammatory myopathies

OBJECTIVE

To assess the long-term outcome in patients with Inflammatory Idiopathic Myopathies (IIM), focusing on damage and activity disease indexes using artificial intelligence (AI).

BACKGROUND

IIM are a group of rare diseases characterized by involvement of different organs in addition to the musculoskeletal. Machine Learning analyses large amounts of information, using different algorithms, decision-making processes, self-learning neural networks.

METHODS

We evaluate the long-term outcome of 103 patients with IIM, diagnosed on 2017 EULAR/ACR criteria. We considered different parameters, including clinical manifestations and organ involvement, number and type of treatments, serum creatine kinase levels, muscle strength (MMT8 score), disease activity (MITAX score), disability (HAQ-DI score), disease damage (MDI score), and physician and patient global assessment (PGA). The data collected were analysed, applying, with R, supervised ML algorithms such as lasso, ridge, elastic net, classification, and regression trees (CART), random forest and support vector machines (SVM) to find the factors that best predict disease outcome.

RESULTS AND CONCLUSION

Using artificial intelligence algorithms we identified the parameters that best correlate with the disease outcome in IIM. The best result was on MMT8 at follow-up, predicted by a CART regression tree algorithm. MITAX was predicted based on clinical features such as the presence of RP-ILD and skin involvement. A good predictive capacity was also demonstrated on damage scores: MDI and HAQ-DI. In the future Machine Learning will allow us to identify the strengths or weaknesses of the composite disease activity and damage scores, to validate new criteria or to implement classification criteria.

Clinical Value of FDG-PET/CT in Multiple Myeloma: An Update

FDG-PET/CT is a standardized imaging technique that has reached a great importance in the management of patients affected by Multiple Myeloma. It is proved, in fact, that it allows a deep evaluation of therapy efficacy and provides several prognostic indexes both at staging and after therapy. For this reason, it is now recognised as a gold standard for therapy assessment. Beside this, in reacent years FDG-PET/CT contribution to the understanding of Multiple Myeloma has progressively grown. Papers have been published analyzing the prognostic value of active disease volume measurement and standardization issues, the meaning of FDG positive paramedullary and extrameduallary disease, the prognostic impact of FDG positive minimal residual disease, the relation between focal lesions and clonal eterogenity of this disease and the comparison with whole body DWI-MR in terms of detection and therapy assessment. These newer aspects not of clinical impact yet, of FDG-PET/CT in Multiple Myeloma will be presented and discussed in this review.

Machine Learning Approaches in Diagnosis, Prognosis and Treatment Selection of Cardiac Amyloidosis

Cardiac amyloidosis is an uncommon restrictive cardiomyopathy featuring an unregulated amyloid protein deposition that impairs organic function. Early cardiac amyloidosis diagnosis is generally delayed by indistinguishable clinical findings of more frequent hypertrophic diseases. Furthermore, amyloidosis is divided into various groups, according to a generally accepted taxonomy, based on the proteins that make up the amyloid deposits; a careful differentiation between the various forms of amyloidosis is necessary to undertake an adequate therapeutic treatment. Thus, cardiac amyloidosis is thought to be underdiagnosed, which delays necessary therapeutic procedures, diminishing quality of life and impairing clinical prognosis. The diagnostic work-up for cardiac amyloidosis begins with the identification of clinical features, electrocardiographic and imaging findings suggestive or compatible with cardiac amyloidosis, and often requires the histological demonstration of amyloid deposition. One approach to overcome the difficulty of an early diagnosis is the use of automated diagnostic algorithms. Machine learning enables the automatic extraction of salient information from “raw data” without the need for pre-processing methods based on the a priori knowledge of the human operator. This review attempts to assess the various diagnostic approaches and artificial intelligence computational techniques in the detection of cardiac amyloidosis.

AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design

Convolutional neural networks (CNNs) have demonstrated exceptional results in the analysis of time- series data when used for Human Activity Recognition (HAR). The manual design of such neural architectures is an error-prone and time-consuming process. The search for optimal CNN architectures is considered a revolution in the design of neural networks. By means of Neural Architecture Search (NAS), network architectures can be designed and optimized automatically. Thus, the optimal CNN architecture representation can be found automatically because of its ability to overcome the limitations of human experience and thinking modes. Evolution algorithms, which are derived from evolutionary mechanisms such as natural selection and genetics, have been widely employed to develop and optimize NAS because they can handle a blackbox optimization process for designing appropriate solution representations and search paradigms without explicit mathematical formulations or gradient information. The Genetic optimization algorithm (GA) is widely used to find optimal or near-optimal solutions for difficult problems. Considering these characteristics, an efficient human activity recognition architecture (AUTO-HAR) is presented in this study. Using the evolutionary GA to select the optimal CNN architecture, the current study proposes a novel encoding schema structure and a novel search space with a much broader range of operations to effectively search for the best architectures for HAR tasks. In addition, the proposed search space provides a reasonable degree of depth because it does not limit the maximum length of the devised task architecture. To test the effectiveness of the proposed framework for HAR tasks, three datasets were utilized: UCI-HAR, Opportunity, and DAPHNET. Based on the results of this study, it has been found that the proposed method can efficiently recognize human activity with an average accuracy of 98.5% (∓1.1), 98.3%, and 99.14% (∓0.8) for UCI-HAR, Opportunity, and DAPHNET, respectively.

A deep learning algorithm for detecting lytic bone lesions of multiple myeloma on CT

BACKGROUND

Whole-body low-dose CT is the recommended initial imaging modality to evaluate bone destruction as a result of multiple myeloma. Accurate interpretation of these scans to detect small lytic bone lesions is time intensive. A functional deep learning) algorithm to detect lytic lesions on CTs could improve the value of these CTs for myeloma imaging. Our objectives were to develop a DL algorithm and determine its performance at detecting lytic lesions of multiple myeloma.

METHODS

Axial slices (2-mm section thickness) from whole-body low-dose CT scans of subjects with biochemically confirmed plasma cell dyscrasias were included in the study. Data were split into train and test sets at the patient level targeting a 90%/10% split. Two musculoskeletal radiologists annotated lytic lesions on the images with bounding boxes. Subsequently, we developed a two-step deep learning model comprising bone segmentation followed by lesion detection. Unet and "You Look Only Once" (YOLO) models were used as bone segmentation and lesion detection algorithms, respectively. Diagnostic performance was determined using the area under the receiver operating characteristic curve (AUROC).

RESULTS

Forty whole-body low-dose CTs from 40 subjects yielded 2193 image slices. A total of 5640 lytic lesions were annotated. The two-step model achieved a sensitivity of 91.6% and a specificity of 84.6%. Lesion detection AUROC was 90.4%.

CONCLUSION

We developed a deep learning model that detects lytic bone lesions of multiple myeloma on whole-body low-dose CTs with high performance. External validation is required prior to widespread adoption in clinical practice.

An evolutionary machine learning for multiple myeloma using Runge Kutta Optimizer from multi characteristic indexes

Multiple myeloma (MM) is a malignant plasma cell disease that is the second most prevalent hematological malignancy in high-income nations and accounts for around 1.8% of all cancers and 18% of hematologic malignancies in the United States. In this research, we try to design a machine learning framework for MM diagnosis from multi characteristic indexes using slime mould Runge Kutta Optimizer (MSRUN) and kernel extreme learning machine, which is called as MSRUN-KELM. An efficient slime mould learning operator is introduced to the initial Runge Kutta Optimizer in MSRUN, ensuring that the trade-off between intensity and diversity is satisfied. The MSRUN was evaluated using IEEE CEC2014 benchmark functions, and the statistical results indicate a significant increase in the search performance of MSRUN. In MSRUN-KELM, kernel extreme machine learning is constructed on MM from multi-characteristic indexes with MSRUN, parameter optimization, and feature selection synchronized by MSRUN. The results of MSRUN-KELM on MM are accuracy of 93.88%, a Matthews correlation coefficient of 0.922677, and sensitivities of 93.41% and 93.19%. The suggested MSRUN-KELM may be utilized to analyze MM from multi-characteristic indexes well, and it can be treated as a potential tool for MM diagnosis.

Estimating the Prognosis of Low-Grade Glioma with Gene Attention Using Multi-Omics and Multi-Modal Schemes

The prognosis estimation of low-grade glioma (LGG) patients with deep learning models using gene expression data has been extensively studied in recent years. However, the deep learning models used in these studies do not utilize the latest deep learning techniques, such as residual learning and ensemble learning. To address this limitation, in this study, a deep learning model using multi-omics and multi-modal schemes, namely the Multi-Prognosis Estimation Network (Multi-PEN), is proposed. When using Multi-PEN, gene attention layers are employed for each datatype, including mRNA and miRNA, thereby allowing us to identify prognostic genes. Additionally, recent developments in deep learning, such as residual learning and layer normalization, are utilized. As a result, Multi-PEN demonstrates competitive performance compared to conventional models for prognosis estimation. Furthermore, the most significant prognostic mRNA and miRNA were identified using the attention layers in Multi-PEN. For instance, MYBL1 was identified as the most significant prognostic mRNA. Such a result accords with the findings in existing studies that have demonstrated that MYBL1 regulates cell survival, proliferation, and differentiation. Additionally, hsa-mir-421 was identified as the most significant prognostic miRNA, and it has been extensively reported that hsa-mir-421 is highly associated with various cancers. These results indicate that the estimations of Multi-PEN are valid and reliable and showcase Multi-PEN's capacity to present hypotheses regarding prognostic mRNAs and miRNAs.

An energy-efficient in-memory computing architecture for survival data analysis based on resistive switching memories

One of the objectives fostered in medical science is the so-called precision medicine, which requires the analysis of a large amount of survival data from patients to deeply understand treatment options. Tools like machine learning (ML) and deep neural networks are becoming a de-facto standard. Nowadays, computing facilities based on the Von Neumann architecture are devoted to these tasks, yet rapidly hitting a bottleneck in performance and energy efficiency. The in-memory computing (IMC) architecture emerged as a revolutionary approach to overcome that issue. In this work, we propose an IMC architecture based on resistive switching memory (RRAM) crossbar arrays to provide a convenient primitive for matrix-vector multiplication in a single computational step. This opens massive performance improvement in the acceleration of a neural network that is frequently used in survival analysis of biomedical records, namely the DeepSurv. We explored how the synaptic weights mapping strategy and the programming algorithms developed to counter RRAM non-idealities expose a performance/energy trade-off. Finally, we discussed how this application is tailored for the IMC architecture rather than being executed on commodity systems.

An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma

While estimating the prognosis of low-grade glioma (LGG) is a crucial problem, it has not been extensively studied to introduce recent improvements in deep learning to address the problem. The attention mechanism is one of the significant advances; however, it is still unclear how attention mechanisms are used in gene expression data to estimate prognosis because they were designed for convolutional layers and word embeddings. This paper proposes an attention mechanism called gene attention for gene expression data. Additionally, a deep learning model for prognosis estimation of LGG is proposed using gene attention. The proposed Gene Attention Ensemble NETwork (GAENET) outperformed other conventional methods, including survival support vector machine and random survival forest. When evaluated by C-Index, the GAENET exhibited an improvement of 7.2% compared to the second-best model. In addition, taking advantage of the gene attention mechanism, HILS1 was discovered as the most significant prognostic gene in terms of deep learning training. While HILS1 is known as a pseudogene, HILS1 is a biomarker estimating the prognosis of LGG and has demonstrated a possibility of regulating the expression of other prognostic genes.

Factors Associated With Lower Respiratory Tract Infection Among Chinese Students Aged 6-14 Years

AIMS

We employed machine-learning methods to explore data from a large survey on students, with the goal of identifying and validating a thrifty panel of important factors associated with lower respiratory tract infection (LRTI).

METHODS

Cross-sectional cluster sampling was performed for a survey of students aged 6-14 years who attended primary or junior high school in Beijing within January, 2022. Data were collected via electronic questionnaires. Statistical analyses were completed using the PyCharm (Edition 2018.1 x64) and Python (Version 3.7.6).

RESULTS

Data from 11,308 students (5,527 girls and 5,781 boys) were analyzed, and 909 of them had LRTI with the prevalence of 8.01%. After a comprehensive evaluation, the Gaussian naive Bayes (gNB) algorithm outperformed the other machine-learning algorithms. The gNB algorithm had accuracy of 0.856, precision of 0.140, recall of 0.165, F1 score of 0.151, and area under the receiver operating characteristic curve (AUROC) of 0.652. Using the optimal gNB algorithm, top five important factors, including age, rhinitis, sitting time, dental caries, and food or drug allergy, had decent prediction performance. In addition, the top five factors had prediction performance comparable to all factors modeled. For example, under the sequential deep-learning model, the accuracy and loss were separately gauged at 92.26 and 25.62% when incorporating the top five factors, and 92.22 and 25.52% when incorporating all factors.

CONCLUSIONS

Our findings showed the top five important factors modeled by gNB algorithm can sufficiently represent all involved factors in predicting LRTI risk among Chinese students aged 6-14 years.