Random survival forest model identifies novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia

Survival prediction in second primary breast cancer patients with machine learning: An analysis of SEER database

BACKGROUND

Studies have found that first primary cancer (FPC) survivors are at high risk of developing second primary breast cancer (SPBC). However, there is a lack of prognostic studies specifically focusing on patients with SPBC.

METHODS

This retrospective study used data from Surveillance, Epidemiology and End Results Program. We selected female FPC survivors diagnosed with SPBC from 12 registries (from January 1998 to December 2018) to construct prognostic models. Meanwhile, SPBC patients selected from another five registries (from January 2010 to December 2018) were used as the validation set to test the model's generalization ability. Four machine learning models and a Cox proportional hazards regression (CoxPH) were constructed to predict the overall survival of SPBC patients. Univariate and multivariate Cox regression analyses were used for feature selection. Model performance was assessed using time-dependent area under the ROC curve (t-AUC) and integrated Brier score (iBrier).

RESULTS

A total of 10,321 female FPC survivors with SPBC (mean age [SD]: 66.03 [11.17]) were included for model construction. These patients were randomly split into a training set (mean age [SD]: 65.98 [11.15]) and a test set (mean age [SD]: 66.15 [11.23]) with a ratio of 7:3. In validation set, a total of 3,638 SPBC patients (mean age [SD]: 66.28 [10.68]) were finally enrolled. Sixteen features were selected for model construction through univariate and multivariable Cox regression analyses. Among five models, random survival forest model showed excellent performance with a t-AUC of 0.805 (95 %CI: 0.803 - 0.807) and an iBrier of 0.123 (95 %CI: 0.122 - 0.124) on testing set, as well as a t-AUC of 0.803 (95 %CI: 0.801 - 0.807) and an iBrier of 0.098 (95 %CI: 0.096 - 0.103) on validation set. Through feature importance ranking, the top one and other top five key predictive features of the random survival forest model were identified, namely age, stage, regional nodes positive, latency, radiotherapy, and surgery.

CONCLUSIONS

The random survival forest model outperformed CoxPH and other machine learning models in predicting the overall survival of patients with SPBC, which was helpful for the monitoring of high-risk populations.

Advances in next-generation sequencing for relapsed pediatric acute lymphoblastic leukemia: current insights and future directions

Leukemia is one of the most common cancers in children; and its genetic diversity in the landscape of acute lymphoblastic leukemia (ALL) is important for diagnosis, risk assessment, and therapeutic approaches. Relapsed ALL remains the leading cause of cancer deaths among children. Almost 20% of children who are treated for ALL and achieve complete remission experience disease recurrence. Relapsed ALL has a poor prognosis, and relapses are more likely to have mutations that affect signaling pathways, chromatin patterning, tumor suppression, and nucleoside metabolism. The identification of ALL subtypes has been based on genomic alterations for several decades, using the molecular landscape at relapse and its clinical significance. Next-generation sequencing (NGS), also known as massive parallel sequencing, is a high-throughput, quick, accurate, and sensitive method to examine the molecular landscape of cancer. This has undoubtedly transformed the study of relapsed ALL. The implementation of NGS has improved ALL genomic analysis, resulting in the recent identification of various novel molecular entities and a deeper understanding of existing ones. Thus, this review aimed to consolidate and critically evaluate the most current information on relapsed pediatric ALL provided by NGS technology. In this phase of targeted therapy and personalized medicine, identifying the capabilities, benefits, and drawbacks of NGS will be essential for healthcare professionals and researchers offering genome-driven care. This would contribute to precision medicine to treat these patients and help improve their overall survival and quality of life.

Advancing precision medicine in immunoglobulin light-chain amyloidosis: a novel prognostic model incorporating multi-organ indicators

To develop a more accurate prognostic model that incorporates indicators of multi-organ involvement for immunoglobulin light-chain (AL) Amyloidosis patients. Biopsy-proven AL amyloidosis patients between January 1, 2012, and February 28, 2023, were enrolled and randomly divided into a training set and a test set at a ratio of 7:3. Prognostic indicators that comprehensively cover cardiac, renal, and hepatic involvement were identified in the training set by random survival forest (RSF). Then, RSF and Cox models were established. The Concordance index (C-index) and integrated brier scores (IBS) were applied to evaluate the models' performance in the test set. Besides, the net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated. A total of 173 eligible patients were included. After a median follow-up of 25.9 (9.2, 50.3) months, 48 (27.7%) patients died. Creatine kinase-MB, estimated glomerular filtration rate ≤ 50 mL/min/1.73 m2, interventricular septum ≥ 15 mm, ejection fraction, alanine aminotransferase and Live involved were selected to develop prediction models. The RSF model based on the above indicators achieved C-index and IBS values of 0.834 (95% CI 0.725-0.915) and 0.151 (95% CI 0.1402-0.181), respectively. At last, the NRI and IDI of the RSF model were 0.301 (95% CI 0.048-0.546, P = 0.012) and 0.157 (95% CI 0.041-0.269, P < 0.001) at 5-year by comparing the RSF model with the Cox model which is based on the Mayo 2012 staging system. The RSF model that incorporates indicators of multi-organ involvement had a great performance, which may be helpful for physicians' decision-making and more accurate overall survival prediction.

Identification of KRAS mutation-associated gut microbiota in colorectal cancer and construction of predictive machine learning model

Gut microbiota has demonstrated an increasingly important role in the onset and development of colorectal cancer (CRC). Nonetheless, the association between gut microbiota and KRAS mutation in CRC remains enigmatic. We conducted 16S rRNA sequencing on stool samples from 94 CRC patients and employed the linear discriminant analysis effect size algorithm to identify distinct gut microbiota between KRAS mutant and KRAS wild-type CRC patients. Transcriptome sequencing data from nine CRC patients were transformed into a matrix of immune infiltrating cells, which was then utilized to explore KRAS mutation-associated biological functions, including Gene Ontology items and Kyoto Encyclopedia of Genes and Genomes pathways. Subsequently, we analyzed the correlations among these KRAS mutation-associated gut microbiota, host immunity, and KRAS mutation-associated biological functions. At last, we developed a predictive random forest (RF) machine learning model to predict the KRAS mutation status in CRC patients, based on the gut microbiota associated with KRAS mutation. We identified a total of 26 differential gut microbiota between both groups. Intriguingly, a significant positive correlation was observed between Bifidobacterium spp. and mast cells, as well as between Bifidobacterium longum and chemokine receptor CX3CR1. Additionally, we also observed a notable negative correlation between Bifidobacterium and GOMF:proteasome binding. The RF model constructed using the KRAS mutation-associated gut microbiota demonstrated qualified efficacy in predicting the KRAS phenotype in CRC. Our study ascertained the presence of 26 KRAS mutation-associated gut microbiota in CRC and speculated that Bifidobacterium may exert an essential role in preventing CRC progression, which appeared to correlate with the upregulation of mast cells and CX3CR1 expression, as well as the downregulation of GOMF:proteasome binding. Furthermore, the RF model constructed on the basis of KRAS mutation-associated gut microbiota exhibited substantial potential in predicting KRAS mutation status in CRC patients.IMPORTANCEGut microbiota has emerged as an essential player in the onset and development of colorectal cancer (CRC). However, the relationship between gut microbiota and KRAS mutation in CRC remains elusive. Our study not only identified a total of 26 gut microbiota associated with KRAS mutation in CRC but also unveiled their significant correlations with tumor-infiltrating immune cells, immune-related genes, and biological pathways (Gene Ontology items and Kyoto Encyclopedia of Genes and Genomes pathways). We speculated that Bifidobacterium may play a crucial role in impeding CRC progression, potentially linked to the upregulation of mast cells and CX3CR1 expression, as well as the downregulation of GOMF:Proteasome binding. Furthermore, based on the KRAS mutation-associated gut microbiota, the RF model exhibited promising potential in the prediction of KRAS mutation status for CRC patients. Overall, the findings of our study offered fresh insights into microbiological research and clinical prediction of KRAS mutation status for CRC patients.

Developing a Prognostic Model for Primary Biliary Cholangitis Based on a Random Survival Forest Model

Background: Primary biliary cholangitis (PBC) is a rare autoimmune liver disease with few effective treatments and a poor prognosis, and its incidence is on the rise. There is an urgent need for more targeted treatment strategies to accurately identify high-risk patients. The use of stochastic survival forest models in machine learning is an innovative approach to constructing a prognostic model for PBC that can improve the prognosis by identifying high-risk patients for targeted treatment. Method: Based on the inclusion and exclusion criteria, the clinical data and follow-up data of patients diagnosed with PBC-associated cirrhosis between January 2011 and December 2021 at Taizhou Hospital of Zhejiang Province were retrospectively collected and analyzed. Data analyses and random survival forest model construction were based on the R language. Result: Through a Cox univariate regression analysis of 90 included samples and 46 variables, 17 variables with p-values <0.1 were selected for initial model construction. The out-of-bag (OOB) performance error was 0.2094, and K-fold cross-validation yielded an internal validation C-index of 0.8182. Through model selection, cholinesterase, bile acid, the white blood cell count, total bilirubin, and albumin were chosen for the final predictive model, with a final OOB performance error of 0.2002 and C-index of 0.7805. Using the final model, patients were stratified into high- and low-risk groups, which showed significant differences with a P value <0.0001. The area under the curve was used to evaluate the predictive ability for patients in the first, third, and fifth years, with respective results of 0.9595, 0.8898, and 0.9088. Conclusion: The present study constructed a prognostic model for PBC-associated cirrhosis patients using a random survival forest model, which accurately stratified patients into low- and high-risk groups. Treatment strategies can thus be more targeted, leading to improved outcomes for high-risk patients.

DNA Copy Number Alterations and Copy Neutral Loss of Heterozygosity in Adult Ph-Negative Acute B-Lymphoblastic Leukemia: Focus on the Genes Involved

The landscape of chromosomal aberrations in the tumor cells of the patients with B-ALL is diverse and can influence the outcome of the disease. Molecular karyotyping at the onset of the disease using chromosomal microarray (CMA) is advisable to identify additional molecular factors associated with the prognosis of the disease. Molecular karyotyping data for 36 patients with Ph-negative B-ALL who received therapy according to the ALL-2016 protocol are presented. We analyzed copy number alterations and their prognostic significance for CDKN2A/B, DMRTA, DOCK8, TP53, SMARCA2, PAX5, XPA, FOXE1, HEMGN, USP45, RUNX1, NF1, IGF2BP1, ERG, TMPRSS2, CRLF2, FGFR3, FLNB, IKZF1, RUNX2, ARID1B, CIP2A, PIK3CA, ATM, RB1, BIRC3, MYC, IKZF3, ETV6, ZNF384, PTPRJ, CCL20, PAX3, MTCH2, TCF3, IKZF2, BTG1, BTG2, RAG1, RAG2, ELK3, SH2B3, EP300, MAP2K2, EBI3, MEF2D, MEF2C, CEBPA, and TBLXR1 genes, choosing t(4;11) and t(7;14) as reference events. Of the 36 patients, only 5 (13.8%) had a normal molecular karyotype, and 31 (86.2%) were found to have various molecular karyotype abnormalities-104 deletions, 90 duplications or amplifications, 29 cases of cnLOH and 7 biallelic/homozygous deletions. We found that 11q22-23 duplication involving the BIRC3, ATM and MLL genes was the most adverse prognostic event in the study cohort.

Development and validation of a model for the prediction of disease-specific survival in patients with oral squamous cell carcinoma: based on random survival forest analysis

OBJECTIVE

To establish a model for predicting the disease-specific survival (DSS) of patients with oral squamous cell carcinoma (OSCC).

METHODS

Patients diagnosed with OSCC from the Surveillance, Epidemiology, and End Results (SEER) database were enrolled and randomly divided into development (n = 14,495) and internal validation cohort (n = 9625). Additionally, a cohort from a hospital located in Southeastern China was utilized for external validation (n = 582).

RESULTS

TNM stage, adjuvant treatment, surgery, tumor sites, age, grade, and gender were used for RSF model construction based on the development cohort. The effectiveness of the model was confirmed through time-dependent ROC curves in different cohorts. The risk score exhibited an almost exponential increase in the hazard ratio of death due to OSCC. In development, internal, and external validation cohorts, the prognosis was significantly worse for patients in groups with higher risk scores (all log-rank P < 0.05).

CONCLUSION

Based on RSF, a high-performance prediction model for OSCC prognosis was created and verified in this study.

Using interpretable machine learning to extend heterogeneous antibody-virus datasets

A central challenge in biology is to use existing measurements to predict the outcomes of future experiments. For the rapidly evolving influenza virus, variants examined in one study will often have little to no overlap with other studies, making it difficult to discern patterns or unify datasets. We develop a computational framework that predicts how an antibody or serum would inhibit any variant from any other study. We validate this method using hemagglutination inhibition data from seven studies and predict 2,000,000 new values ± uncertainties. Our analysis quantifies the transferability between vaccination and infection studies in humans and ferrets, shows that serum potency is negatively correlated with breadth, and provides a tool for pandemic preparedness. In essence, this approach enables a shift in perspective when analyzing data from "what you see is what you get" into "what anyone sees is what everyone gets."

Unleashing the Power of Very Small Data to Predict Acute Exacerbations of Chronic Obstructive Pulmonary Disease

Introduction

In this article, we explore to what extent it is possible to leverage on very small data to build machine learning (ML) models that predict acute exacerbations of chronic obstructive pulmonary disease (AECOPD).

Methods

We build ML models using the small data collected during the eHealth Diary telemonitoring study between 2013 and 2017 in Sweden. This data refers to a group of multimorbid patients, namely 18 patients with chronic obstructive pulmonary disease (COPD) as the major reason behind previous hospitalisations. The telemonitoring was supervised by a specialised hospital-based home care (HBHC) unit, which also was responsible for the medical actions needed.

Results

We implement two different ML approaches, one based on time-dependent covariates and the other one based on time-independent covariates. We compare the first approach with standard COX Proportional Hazards (CPH). For the second one, we use different proportions of synthetic data to build models and then evaluate the best model against authentic data.

Discussion

To the best of our knowledge, the present ML study shows for the first time that the most important variable for an increased risk of future AECOPDs is "maintenance medication changes by HBHC". This finding is clinically relevant since a sub-optimal maintenance treatment, requiring medication changes, puts the patient in risk for future AECOPDs.

Conclusion

The experiments return useful insights about the use of small data for ML.

A prediction model for the 5-year, 10-year and 20-year mortality of medullary thyroid carcinoma patients based on lymph node ratio and other predictors

Aim

To explore the predictive value of lymph node ratio (LNR) for the prognosis of medullary thyroid carcinoma (MTC) patients, and constructed prediction models for the 5-year, 10-year and 20-year mortality of MTC patients based on LNR and other predictors.

Methods

This cohort study extracted the data of 2,093 MTC patients aged ≥18 years undergoing total thyroidectomy and neck lymph nodes dissection. Kaplan-Meier curves and log-rank tests were performed to compare survival curves between LNR < 15% group and LNR ≥ 15% group. All data was divided into the training set (n = 1,465) and the testing set (n = 628). The random survival forest model was constructed in the training set and validated in the testing set. The area under the curve (AUC) was employed for evaluating the predictive ability of the model.

Results

The 5-year, 10-year and 20-year overall survival (OS) and cause-specific survival (CSS) of MTC patients with LNR <15% were higher than those with LNR ≥15%. The OS was 46% and the CSS was 75% after 20 years' follow-up. The AUC of the model for the 5-year, 10-year, and 20-year OS in MTC patients was 0.878 (95%CI: 0.856-0.900), 0.859 (95%CI: 0.838-0.879) and 0.843 (95%CI: 0.823-0.862) in the training set and 0.845 (95%CI: 0.807-0.883), 0.841 (95%CI: 0.807-0.875) and 0.841 (95%CI: 0.811-0.872) in the testing set. In the training set, the AUCs were 0.869 (95%CI: 0.845-0.892), 0.843 (95%CI: 0.821-0.865), 0.819 (95%CI: 0.798-0.840) for the 5-year, 10-year and 20-year CCS in MTC patients, respectively. In the testing set, the AUCs were 0.857 (95%CI: 0.822-0.892), 0.839 (95%CI: 0.805-0.873) and 0.826 (95%CI: 0.794-0.857) for the 5-year CCS, 10-year CCS and 20-year CCS in MTC patients, respectively.

Conclusion

The models displayed good predictive performance, which might help identify MTC patients might have poor outcomes and appropriate interventions should be applied in these patients.

Plasma metabolomic and lipidomic alterations associated with anti-tuberculosis drug-induced liver injury

Background: Anti-tuberculosis drug-induced liver injury (ATB-DILI) is an adverse reaction with a high incidence and the greatest impact on tuberculosis treatment. However, there is a lack of effective biomarkers for the early prediction of ATB-DILI. Herein, this study uses UPLC‒MS/MS to reveal the plasma metabolic profile and lipid profile of ATB-DILI patients before drug administration and screen new biomarkers for predicting ATB-DILI. Methods: A total of 60 TB patients were enrolled, and plasma was collected before antituberculosis drug administration. The untargeted metabolomics and lipidomics analyses were performed using UPLC‒MS/MS, and the high-resolution mass spectrometer Q Exactive was used for data acquisition in both positive and negative ion modes. The random forest package of R software was used for data screening and model building. Results: A total of 60 TB patients, including 30 ATB-DILI patients and 30 non-ATB-DILI subjects, were enrolled. There were no significant differences between the ATB-DILI and control groups in age, sex, smoking, drinking or body mass index (p > 0.05). Twenty-two differential metabolites were selected. According to KEGG pathway analysis, 9 significantly enriched metabolic pathways were found, and both drug metabolism-other enzymes and niacin and nicotinamide metabolic pathways were found in both positive and negative ion models. A total of 7 differential lipid molecules were identified between the two groups. Ferroptosis and biosynthesis of unsaturated fatty acids were involved in the occurrence of ATB-DILI. Random forest analysis showed that the model built with the top 30 important variables had an area under the ROC curve of 0.79 (0.65-0.93) for the training set and 0.79 (0.55-1.00) for the validation set. Conclusion: This study demonstrated that potential markers for the early prediction of ATB-DILI can be found through plasma metabolomics and lipidomics. The random forest model showed good clinical predictive value for ATB-DILI.

Deregulated calcium signaling in blood cancer: Underlying mechanisms and therapeutic potential

Intracellular calcium signaling regulates diverse physiological and pathological processes. In solid tumors, changes to calcium channels and effectors via mutations or changes in expression affect all cancer hallmarks. Such changes often disrupt transport of calcium ions (Ca²⁺) in the endoplasmic reticulum (ER) or mitochondria, impacting apoptosis. Evidence rapidly accumulates that this is similar in blood cancer. Principles of intracellular Ca²⁺ signaling are outlined in the introduction. We describe different Ca²⁺-toolkit components and summarize the unique relationship between extracellular Ca²⁺ in the endosteal niche and hematopoietic stem cells. The foundational data on Ca²⁺ homeostasis in red blood cells is discussed, with the demonstration of changes in red blood cell disorders. This leads to the role of Ca²⁺ in neoplastic erythropoiesis. Then we expand onto the neoplastic impact of deregulated plasma membrane Ca²⁺ channels, ER Ca²⁺ channels, Ca²⁺ pumps and exchangers, as well as Ca²⁺ sensor and effector proteins across all types of hematologic neoplasms. This includes an overview of genetic variants in the Ca²⁺-toolkit encoding genes in lymphoid and myeloid cancers as recorded in publically available cancer databases. The data we compiled demonstrate that multiple Ca²⁺ homeostatic mechanisms and Ca²⁺ responsive pathways are altered in hematologic cancers. Some of these alterations may have genetic basis but this requires further investigation. Most changes in the Ca²⁺-toolkit do not appear to define/associate with specific disease entities but may influence disease grade, prognosis, treatment response, and certain complications. Further elucidation of the underlying mechanisms may lead to novel treatments, with the aim to tailor drugs to different patterns of deregulation. To our knowledge this is the first review of its type in the published literature. We hope that the evidence we compiled increases awareness of the calcium signaling deregulation in hematologic neoplasms and triggers more clinical studies to help advance this field.