scholarly journals Cancer Grade Model: a multi-gene machine learning-based risk classification for improving prognosis in breast cancer

2021 ◽  
Author(s):  
E. Amiri Souri ◽  
A. Chenoweth ◽  
A. Cheung ◽  
S. N. Karagiannis ◽  
S. Tsoka
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Clinical Decision Making ◽  
Histological Grade ◽  
Tumour Size ◽  
Clinical Decision ◽  
Gene Signature ◽  
Risk Classification ◽  
Breast Cancers ◽  
Grade 3

Abstract Background Prognostic stratification of breast cancers remains a challenge to improve clinical decision making. We employ machine learning on breast cancer transcriptomics from multiple studies to link the expression of specific genes to histological grade and classify tumours into a more or less aggressive prognostic type. Materials and methods Microarray data of 5031 untreated breast tumours spanning 33 published datasets and corresponding clinical data were integrated. A machine learning model based on gradient boosted trees was trained on histological grade-1 and grade-3 samples. The resulting predictive model (Cancer Grade Model, CGM) was applied on samples of grade-2 and unknown-grade (3029) for prognostic risk classification. Results A 70-gene signature for assessing clinical risk was identified and was shown to be 90% accurate when tested on known histological-grade samples. The predictive framework was validated through survival analysis and showed robust prognostic performance. CGM was cross-referenced with existing genomic tests and demonstrated the competitive predictive power of tumour risk. Conclusions CGM is able to classify tumours into better-defined prognostic categories without employing information on tumour size, stage, or subgroups. The model offers means to improve prognosis and support the clinical decision and precision treatments, thereby potentially contributing to preventing underdiagnosis of high-risk tumours and minimising over-treatment of low-risk disease.

Discovery and validation of a cross-platform 21-gene prognostic signature in neuroblastoma.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 10035-10035
Author(s):  
Mehul Gupta ◽  
Sunand Nageswaran Kannappan ◽  
Aru Narendran ◽  
Pinaki Bose
Keyword(s):  
Machine Learning ◽  
Risk Stratification ◽  
Clinical Decision Making ◽  
Proportional Hazards ◽  
Risk Model ◽  
Learning Algorithm ◽  
Clinical Decision ◽  
Gene Signature ◽  
Cox Proportional Hazards ◽  
Transcriptomic Signature

10035 Background: Neuroblastoma (NB) is the most common extracranial solid tumor in children. Despite the development of risk stratification tools to improve prognostication, prediction of patient survival outcomes in NB remains poor. In this study we used an unbiased machine-learning algorithm to develop and validate a transcriptomic signature capable of predicting 5-year overall (OS) and event-free survival (EFS) in these patients. Methods: The TARGET-Neuroblastoma dataset (n = 243) was used as the training set. Two independent NB cohorts, E-MTAB-179 (n = 478) and GSE85047 (n = 266) were used as validation sets. Elastic net regression was employed to identify transcripts associated with EFS. Association of the developed signature with EFS and OS was evaluated using univariate Cox proportional hazards (CoxPH), Kaplan-Meier, and 5-year receiver-operator characteristic curves in validation cohorts. Further, the independent prognostic value of the signature was assessed using multivariate CoxPH models with relevant clinicopathologic variables including age, INSS stage, and N-Myc amplification status in both validation sets. Finally, a nomogram was developed to integrate the signature with prognostic clinicopathologic variables to evaluate their combined efficacy for prediction of 5-year EFS and OS. Results: We identified a 21-gene signature that demonstrates significant association with EFS and OS in both E-MTAB-178 and GSE49710 validation cohorts. Moreover, the signature is independent of clinicopathological variables and can be effectively incorporated into a risk model, improving the prognostic performance. Several genes within the signature have been previously implicated in NB, including ECEL1, HOXC9 and ARAF1. Conclusions: To the best of our knowledge, we are the first to use an unbiased machine learning approach to generate a transcriptomic gene signature for neuroblastoma prognosis externally validated in multiple cohorts across platforms. This 21-gene transcriptomic signature significantly associated with EFS and OS in this disease. Combining this signature with current prognostic clinicopathologic variables will improve risk stratification of affected patients and may inform effective clinical decision-making.[Table: see text]

scholarly journals NUCLEAR MORPHOMETRY IN AFRICAN BREAST CANCER

2011 ◽  
Vol 21 (2) ◽  
pp. 145 ◽  
Author(s):  
Offiong Francis Ikpatt ◽  
Teijo Kuopio ◽  
Yrjö Collan
Keyword(s):  
Breast Cancer ◽  
Histological Grade ◽  
Tumour Size ◽  
Continuous Variable ◽  
Grading System ◽  
Breast Cancers ◽  
Nuclear Area ◽  
Cut Point ◽  
Nuclear Morphometry ◽  
Cox's Regression

Three hundred cases of invasive breast cancer diagnosed between 1983 and 1999 in Calabar, Nigeria were analysed to determine the nuclear morphometric variables, and evaluate the prognostic potential of nuclear morphometry in Nigerian breast cancers. The necessary follow-up was available for 129 patients. The nuclear area was the most valuable variable. In the Nigerian material, the mean nuclear area (MNA) (SD) was 89.2 (34.0) μm2. MNA was significantly higher in tumours of the postmenopausal than premenopausal (p = 0.0405), in LN+ than LN- (p = 0.0202) patients, and in tumours over 3 cm than smaller ones (p < 0.0001). There were also significant differences between different clinical stages, histological grades, and histological types of tumours. Significant correlations were observed between MNA and histological grade (r = 0.64), standard mitotic index (r = 0.45) and tumour size (r = 0.20). MNA as a continuous variable was a statistically significant prognosticator in the whole material (p = 0.0281), and among the postmenopausal patients (p = 0.0238). Univariate cox's regression demonstrated one significant grading cutpoint at MNA = 111 μm2, which divided the material into two groups of different survival. The development of a morphometric grading system optimal for the Nigerian material could use the latter cut-point between nuclear scores 2 and 3 in the grading system. The earlier proven cut-point of 47 μm2 could be used between nuclear scores 1 and 2.

scholarly journals Nuclear DNA Content of Fine Needle Aspirates of Invasive Ductal Carcinomas of the Breast

1997 ◽  
Vol 13 (1) ◽  
pp. 1-8 ◽  
Author(s):  
Sudip Sarker ◽  
Allan Spigelman ◽  
Marjorie Walker ◽  
Dulcie Coleman
Keyword(s):  
Breast Cancer ◽  
Dna Content ◽  
Nuclear Dna ◽  
Histological Grade ◽  
Tumour Size ◽  
Nuclear Dna Content ◽  
Biological Assessment ◽  
Breast Cancers ◽  
Fine Needle ◽  
Fine Needle Aspirates

Patients with aggressive breast cancers benefit from chemotherapy prior to surgery. If the biology of the breast cancers were better characterised pre‐operatively, more patients at risk could be offered chemotherapy. We have assessed nuclear DNA content of fine needle aspirates (FNA) of 103 invasive ductal breast cancers and compared this to tumour size, node status and histological grade. Median follow‐up was 18 months so no prognostic studies were made. Diploid and non‐diploid tumours were distributed equally in node negative and positive patients. However non‐diploidy status increased in line with known prognostic markers of tumour size and histological grade. This suggests that ploidy might contribute to the pre‐operative assessment of prognosis. We conclude that nuclear DNA of breast cancer FNAs may be of value in the pre‐operative biological assessment of breast cancer patients.

Machine learning in clinical decision making

Med ◽  
2021 ◽  
Author(s):  
Lorenz Adlung ◽  
Yotam Cohen ◽  
Uria Mor ◽  
Eran Elinav
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision

scholarly journals Evaluation of multiple transcriptomic gene risk signatures in male breast cancer

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Jane Bayani ◽  
Coralie Poncet ◽  
Cheryl Crozier ◽  
Anouk Neven ◽  
Tammy Piper ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Male Breast Cancer ◽  
Univariate Analysis ◽  
Gene Signature ◽  
Male Breast ◽  
Risk Scores ◽  
Breast Cancers ◽  
Academic Risk ◽  
Genomic Grade Index ◽  
Prognostic Utility

AbstractMale breast cancer (BCa) is a rare disease accounting for less than 1% of all breast cancers and 1% of all cancers in males. The clinical management is largely extrapolated from female BCa. Several multigene assays are increasingly used to guide clinical treatment decisions in female BCa, however, there are limited data on the utility of these tests in male BCa. Here we present the gene expression results of 381 M0, ER+ve, HER2-ve male BCa patients enrolled in the Part 1 (retrospective analysis) of the International Male Breast Cancer Program. Using a custom NanoString™ panel comprised of the genes from the commercial risk tests Prosigna®, OncotypeDX®, and MammaPrint®, risk scores and intrinsic subtyping data were generated to recapitulate the commercial tests as described by us previously. We also examined the prognostic value of other risk scores such as the Genomic Grade Index (GGI), IHC4-mRNA and our prognostic 95-gene signature. In this sample set of male BCa, we demonstrated prognostic utility on univariate analysis. Across all signatures, patients whose samples were identified as low-risk experienced better outcomes than intermediate-risk, with those classed as high risk experiencing the poorest outcomes. As seen with female BCa, the concordance between tests was poor, with C-index values ranging from 40.3% to 78.2% and Kappa values ranging from 0.17 to 0.58. To our knowledge, this is the largest study of male breast cancers assayed to generate risk scores of the current commercial and academic risk tests demonstrating comparable clinical utility to female BCa.

scholarly journals Clinician checklist for assessing suitability of machine learning applications in healthcare

2021 ◽  
Vol 28 (1) ◽  
pp. e100251
Author(s):  
Ian Scott ◽  
Stacey Carter ◽  
Enrico Coiera
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Clinical Decision Making ◽  
Improve Patient Care ◽  
Clinical Decision ◽  
Routine Care ◽  
Machine Learning Algorithms ◽  
Clinical Settings ◽  
Machine Learning Applications ◽  
Key Issues

Machine learning algorithms are being used to screen and diagnose disease, prognosticate and predict therapeutic responses. Hundreds of new algorithms are being developed, but whether they improve clinical decision making and patient outcomes remains uncertain. If clinicians are to use algorithms, they need to be reassured that key issues relating to their validity, utility, feasibility, safety and ethical use have been addressed. We propose a checklist of 10 questions that clinicians can ask of those advocating for the use of a particular algorithm, but which do not expect clinicians, as non-experts, to demonstrate mastery over what can be highly complex statistical and computational concepts. The questions are: (1) What is the purpose and context of the algorithm? (2) How good were the data used to train the algorithm? (3) Were there sufficient data to train the algorithm? (4) How well does the algorithm perform? (5) Is the algorithm transferable to new clinical settings? (6) Are the outputs of the algorithm clinically intelligible? (7) How will this algorithm fit into and complement current workflows? (8) Has use of the algorithm been shown to improve patient care and outcomes? (9) Could the algorithm cause patient harm? and (10) Does use of the algorithm raise ethical, legal or social concerns? We provide examples where an algorithm may raise concerns and apply the checklist to a recent review of diagnostic imaging applications. This checklist aims to assist clinicians in assessing algorithm readiness for routine care and identify situations where further refinement and evaluation is required prior to large-scale use.

scholarly journals Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Imogen Schofield ◽  
David C. Brodbelt ◽  
Noel Kennedy ◽  
Stijn J. M. Niessen ◽  
David B. Church ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cushing’S Syndrome ◽  
Clinical Decision Making ◽  
Predictive Performance ◽  
Clinical Decision ◽  
Cushing's Syndrome ◽  
Machine Learning Algorithms ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Clinical Records

AbstractCushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.

scholarly journals Nottingham Prognostic Index Plus (NPI+): a modern clinical decision making tool in breast cancer

2014 ◽  
Vol 110 (7) ◽  
pp. 1688-1697 ◽  
Author(s):  
E A Rakha ◽  
D Soria ◽  
A R Green ◽  
C Lemetre ◽  
D G Powe ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Prognostic Index ◽  
Clinical Decision ◽  
Nottingham Prognostic Index ◽  
Decision Making Tool

Male Versus Female Breast Cancers

2003 ◽  
Vol 127 (1) ◽  
pp. 36-41 ◽  
Author(s):  
D. Muir ◽  
R. Kanthan ◽  
S. C. Kanthan
Keyword(s):  
Breast Cancer ◽  
Estrogen Receptor ◽  
Progesterone Receptor ◽  
Male Breast Cancer ◽  
Male Breast ◽  
High Grade ◽  
Breast Cancers ◽  
Receptor Status ◽  
Female Breast ◽  
Grade 3

Abstract Context.—The rate of male breast cancer is a small fraction of that observed in females, thus severely limiting our understanding of the pathogenesis of this condition. It remains unclear whether the biological behavior and tumor progression associated with male breast cancer parallel that of the female form. Objectives.—To evaluate the immunohistochemical profile of male breast carcinomas and to compare this profile with that of stage-matched female breast cancers. Design.—Seventy-five cases of primary male breast cancer were identified using the records of the Saskatchewan Cancer Foundation over a period of 26 years (1970–1996). Fifty-nine of these cases had formalin-fixed, paraffin-embedded tissue blocks available for the purposes of this study. All cases were reviewed and a standardized modified Bloom-Richardson grading criterion was applied. Estrogen receptor status, progesterone receptor status, c-Erb-B2 expression, p53 expression, and Bcl-2 expression were evaluated by immunohistochemistry. Results from 240 consecutive cases of stage-matched female breast cancers analyzed in the same laboratory were used as a standard set for comparison. Results.—Male breast cancers tended to be high grade (85% grade 3) in comparison with the female breast cancers (50% grade 3). In descriptive analysis across all stages of disease, male carcinomas were more frequently estrogen receptor positive (81% vs 69%) than their female counterparts. Despite their high grade, they were less likely to overexpress p53 (9% vs 28%) and Erb-B2 (5% vs 17%) than the female counterparts. There was no significant difference in either progesterone receptor (63% vs 56%) or Bcl-2 (79% vs 76%) overexpression. Stratified analysis by stage-matched controls showed no statistically significant differences among the men and women with stage I disease. However, in stage II–matched samples, statistically significant differences were observed between the 2 groups. The male cancers were more likely to overexpress estrogen receptor (81.6% vs 64.4%, P = .04), progesterone receptor (71.1% vs 47.5%, P = .01), and Bcl-2 (78.9% vs 69.4%, P = .20). They also showed statistically significant lower expression of p53 (7.9% vs 36.3%, P = .001) and Erb-B2 (5.3% vs 23.8% P = .01). Conclusion.—Male breast cancers display distinct immunophenotypic differences from those occurring in women, implying a different pathogenesis in the evolution and progression of this disease. Such differences may play key roles in therapeutic management, warranting different treatment strategies in comparison to female breast cancers.

Sign in / Sign up

Export Citation Format

Share Document