scholarly journals Machine Learning to Predict Tamoxifen Nonadherence Among US Commercially Insured Patients With Metastatic Breast Cancer

2021 ◽  
pp. 814-825 ◽  
Author(s):  
Gayathri Yerrapragada ◽  
Athanasios Siadimas ◽  
Amir Babaeian ◽  
Vishakha Sharma ◽  
Tyler J. O'Neill
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Logistic Regression ◽  
Metastatic Breast Cancer ◽  
Receiver Operating Characteristic ◽  
Predictive Value ◽  
Operating Characteristic ◽  
Treatment Initiation ◽  
Metastatic Breast ◽  
Receiver Operating

PURPOSE Adherence to tamoxifen citrate among women diagnosed with metastatic breast cancer can improve survival and minimize recurrence. This study aimed to use real-world data and machine learning (ML) methods to classify tamoxifen nonadherence. METHODS A cohort of women diagnosed with metastatic breast cancer from 2012 to 2017 were identified from IBM MarketScan Commercial Claims and Encounters and Medicare claims databases. Patients with < 80% proportion of days coverage in the year following treatment initiation were classified as nonadherent. Training and internal validation cohorts were randomly generated (4:1 ratio). Clinical procedures, comorbidity, treatment, and health care encounter features in the year before tamoxifen initiation were used to train logistic regression, boosted logistic regression, random forest, and feedforward neural network models and were internally validated on the basis of area under receiver operating characteristic curve. The most predictive ML approach was evaluated to assess feature importance. RESULTS A total of 3,022 patients were included with 40% classified as nonadherent. All models had moderate predictive accuracy. Logistic regression (area under receiver operating characteristic 0.64) was interpreted with 94% sensitivity (95% CI, 89 to 92) and 0.31 specificity (95% CI, 29 to 33). The model accurately classified adherence (negative predictive value 89%) but was nondiscriminate for nonadherence (positive predictive value 48%). Variable importance identified top predictive factors, including age ≥ 55 years and pretreatment procedures (lymphatic nuclear medicine, radiation oncology, and arterial surgery). CONCLUSION ML using baseline administrative data predicts tamoxifen nonadherence. Screening at treatment initiation may support personalized care, improve health outcomes, and minimize cost. Baseline claims may not be sufficient to discriminate adherence. Further validation with enriched longitudinal data may improve model performance.

Machine learning to predict tamoxifen adherence among U.S. commercially insured breast cancer patients.

2020 ◽  
Vol 38 (29_suppl) ◽  
pp. 276-276
Author(s):  
Tyler J. O'Neill ◽  
Vishakha Sharma ◽  
Athanasios Siadimas ◽  
Amir Babaeian ◽  
Gayathri Yerrapragada
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Logistic Regression ◽  
Predictive Value ◽  
Treatment Initiation ◽  
Predictive Accuracy ◽  
Metastatic Breast ◽  
Cost Of Care ◽  
Administrative Claims ◽  
Breast Cancer Patients

276 Background: Adherence to tamoxifen among women diagnosed with hormone receptor positive metastatic breast cancer (mBC) can improve survival and minimize recurrence. Screening for non-adherence at treatment initiation may support personalized care, improve health outcomes, and minimize cost of care. This study aimed to use real world data (RWD) and machine learning (ML) methods to classify tamoxifen non-adherence. Methods: A cohort of women diagnosed with incident mBC from 2012 to 2018 were identified from Truven MarketScan Commercial Claims and Encounters and Medicare supplemental administrative claims databases. Patients with < 80% proportion of days coverage (PDC) in the year following treatment initiation were classified non-adherent. Training and internal validation cohorts were randomly generated (4:1 ratio). Clinical procedures, comorbidity, treatment and healthcare encounter features in the year prior to treatment initiation were used to train logistic regression, boosted logistic regression, random forest, and feed forward neural network models and internally validated based on area under receiver operating characteristic (AUROC) curve. The most predictive ML approach was evaluated to assess feature importance. Results: A total of 3,022 patients were included with 39.9% classified as non-adherent. All ML models had moderate predictive accuracy. Logistic regression (AUROC 0.64) was easily interpreted with sensitivity 94% (95% confidence interval [CI]: 0.89, 0.92) and specificity 0.31 (95% CI: 0.29, 0.33). The model accurately classified adherence (negative predictive value 88.7%) but was non-discriminate for non-adherence (positive predictive value 47.7%). Variable importance identified top predictive factors, including patient features (≥55 years old) and pre-treatment procedures (lymphatic nuclear medicine, radiation oncology, arterial surgery). Conclusions: ML using baseline administrative data predicts tamoxifen adherence. Baseline claims may not be sufficient to predict treatment non-adherence. Further validation with enriched longitudinal data may improve model performance for incorporation of predictions into clinical decision support.

Validity of diagnosis support for attention deficit/hyperactivity disorders - Model discrimination of machine learning approach (Preprint)

2020 ◽  
Author(s):  
Hsin-Jou Huang ◽  
Hsin-Ke Lu ◽  
Peng-Chun Lin ◽  
Kuo-Chung Chu ◽  
Wei-Chih Chin ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Logistic Regression ◽  
Receiver Operating Characteristic ◽  
Attention Deficit ◽  
Operating Characteristic ◽  
Learning Approach ◽  
Adhd Group ◽  
Machine Learning Approach ◽  
Receiver Operating

BACKGROUND Attention deficit hyperactivity disorder (ADHD) is a common neurobehavioral disorder characterized by inattention, hyperactivity, and impulsivity. It is a chronic disorder and often persists into adulthood. Long-term follow-up studies showed that children with ADHD were more impaired in psychosocial, educational, and neuropsychological functioning, and had higher risks for antisocial disorders, major depression, and anxiety disorders as adults. Proper and early diagnosis would save medical resources and assist policy making for ADHD. OBJECTIVE In this research, we developed a diagnosis decision model using machine learning approach to effectively screen the disorder potentials. The model is based on three machine learning algorithms: logistic regression, classification and regression tree (CART), and neural network. They were compared for analysis of the disorder diagnosis with receiver operating characteristic curve. METHODS There were 74 participants in the ADHD group, while 21 participants in non-ADHD control group. The performance of three algorithms is evaluated by receiver operating characteristic (ROC) curve. RESULTS The results showed that the CART outperformed the other two, and the region values of receiver operating characteristic were in the following order: CART (0.848) > logistic regression model (0.826) > neural network (0.67). The sensitivity and specificity of the CART were 88% and 50%, respectively. CONCLUSIONS In the future, this model can also be used in other neuroscience fields, such as diagnosing Asperger Syndrome, Tourette Syndrome, and Dementia. Thereby, it can exert practical value and benefits of the research results.

scholarly journals Comparative study of logistic regression and artificial neural networks on predicting breast cancer cytology

2021 ◽  
Vol 21 (2) ◽  
pp. 1113
Author(s):  
Yosra Abdulaziz Mohammed ◽  
Eman Gadban Saleh
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Logistic Regression ◽  
Artificial Neural Networks ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Performance Metrics ◽  
Artificial Neural ◽  
Sensitivity Specificity ◽  
Receiver Operating

<p>Currently, breast cancer is one of the most common cancers and a main reason of women death worldwide particularly in<strong> </strong>developing countries such as Iraq. our work aims to predict the type of tumor whether benign or malignant through models that were built using logistic regression and neural networks and we hope it will help doctors in detecting the type of breast tumor. Four models were set using binary logistic regression and two different types of artificial neural networks namely multilayer perceptron MLP and radial basis function RBF. Evaluation of validated and trained models was done using several performance metrics like accuracy, sensitivity, specificity, and AUC (area under receiver operating characteristic ROC).   Dataset was downloaded from UCI ml repository; it is composed of 9 attributes and 699 samples. The findings are clearly showing that the RBF NN classifier is the best in prediction of the type of breast tumors since it had recorded the highest performance in terms of correct classification rate (accuracy), sensitivity, specificity, and AUC (area under Receiver Operating Characteristic ROC) among all other models.</p>

scholarly journals Scrutiny of Breast Cancer Detection Techniques of Deeplearning and Machine Learning

2019 ◽  
Vol 8 (2S10) ◽  
pp. 200-209
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Image Segmentation ◽  
Deep Learning ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Focal Point ◽  
Small Scale ◽  
Detection Techniques ◽  
Receiver Operating

Breast cancer is one of the most widely recognized tumors globally among ladies with the data available that one of every eight ladies is influenced by this illness during their lifetime. Mammography is the best imaging methodology for early location of the disease in beginning times. On account of poor complexity and low perceivability in the mammographic pictures, early discovery of the cancer malignant growth is a huge challenge to effective cure of the disease. Distinctive CAD (computer aided detection) supported algorithms have been developed to enable radiologists to give an exact determination. This paper highlights the study of the most widely recognized methodologies of image segmentation created for recognition of calcifications and masses. The principle focal point of this survey is on picture theof strategies and the factors utilized for early bosom disease identification. Surface investigation is the vital advance in any picture division strategies of image segmentation which depend on a nearby spatial variety of color or shading. Subsequently, different techniques for texture investigation for small scale calcification and mass identification in mammography are talked about in the mechanism of mammography. The point of this paper is to audit existing ways to deal with the segmentation of masses and automated detection in mammographic pictures, underlining the key-focuses and primary contrasts among the utilized systems. The key goal is to bring up the preferences and drawbacks of the different methodologies. Conversely with different surveys which just portray and think about various methodologies subjectively, this audit likewise gives a quantifiable examination.In proposed research use deep learning base network for classification of mammography images . In previous approaches use machine learning base learning. The Main drawback of machine learning is selection of features manualy or by functions but in deep learning automatic feature detect and its vary according to image. The demonstration of seven mass recognition techniques is thought about utilizing two distinctive databases of mammography: an open digitized database and a full-field (local) advanced digitized database. The outcomes are given as far as Free reaction Receiver Operating Characteristic (FROC) and Receiver Operating Characteristic (ROC) examination.

A Predictive Model of Intrinsic Factors Associated with Long-Stay Nursing Home Care After Hospitalization

2020 ◽  
pp. 105477382098527
Author(s):  
Jane Flanagan ◽  
Marie Boltz ◽  
Ming Ji
Keyword(s):  
At Risk ◽  
Logistic Regression ◽  
Receiver Operating Characteristic ◽  
Predictive Model ◽  
Operating Characteristic ◽  
Resource Planning ◽  
Term Care ◽  
Intrinsic Factors ◽  
Patients At Risk ◽  
Receiver Operating

We aimed to build a predictive model with intrinsic factors measured upon admission to skilled nursing facilities (SNFs) post-acute care (PAC) to identify older adults transferred from SNFs to long-term care (LTC) instead of home. We analyzed data from Massachusetts in 23,662 persons admitted to SNFs from PAC in 2013. Explanatory logistic regression analysis identified single “intrinsic predictors” related to LTC placement. To assess overfitting, the logistic regression predictive model was cross-validated and evaluated by its receiver operating characteristic (ROC) curve. A 12-variable predictive model with “intrinsic predictors” demonstrated both high in-sample and out-of-sample predictive accuracy in the receiver operating characteristic ROC and area under the ROC among patients at risk of LTC placement. This predictive model may be used for early identification of patients at risk for LTC after hospitalization in order to support targeted rehabilitative approaches and resource planning.

Development of a breast cancer-specific prognostic tool using CancerLinQ Discovery.

2021 ◽  
Vol 39 (28_suppl) ◽  
pp. 275-275
Author(s):  
Emily Miller Ray ◽  
Xinyi Zhang ◽  
Lisette Dunham ◽  
Xianming Tan ◽  
Jennifer Elston Lafata ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Logistic Regression ◽  
Metastatic Breast Cancer ◽  
High Risk ◽  
Performance Status ◽  
Vital Signs ◽  
Metastatic Breast ◽  
Clinical Use ◽  
Final Model ◽  
Prognostic Tool

275 Background: Oncologists often struggle to know which patients are near end of life to enable a timely transition to supportive care. We developed a breast cancer-specific prognostic tool, using electronic health record data from CancerLinQ Discovery (CLQD), to help identify patients at high risk of near-term death. We created multiple candidate models with varying thresholds for defining high risk that will be considered for future clinical use. Methods: We included patients with breast cancer diagnosed between 1/1/2000 to 6/1/2020 who had at least one encounter with vital signs and evidence of metastatic breast cancer (MBC). All encounters from 1/1/2000 to 7/5/2020 were included. We used multiple imputation (MI) to impute missing numeric variables and treated missing values as a new level for categorical variables. We sampled one encounter per patient and oversampled within 30 days of death, so that the event rate (death within 30 days of encounter) was about 10%. We randomly divided these patients into training (70%) and test datasets (30%). We evaluated candidate predictors of the event using logistic regression with forward variable selection. Candidate predictors included age, vital signs, laboratory values, performance status, pain score, time since chemotherapy, and ER/PR/HER2 receptor status, and change from baseline and change rate of numeric variables. We obtained a single final model by combining resulted logistic regression model from 10 MI training sets. We evaluated this final model on the MI test sets. We varied the alert threshold (i.e., high-risk proportion) from 5% to 40%. Results: We identified 9,270 patients, representing 586,801 encounters. Significant predictors of mortality were: increased age, decreased age at diagnosis, negative change in body mass index, low albumin, high ALP, high AST, high WBC, low sodium, high creatinine, worse performance status, low pulse oximetry, increased age with increased creatinine, high pain score with no opiates, increased pulse rate, unknown/missing PR, opiate use in past 3 months, and prior chemotherapy in past 1 year but not past 30 days. Candidate models had prediction accuracy of 70-89% and positive predictive value of 31-77%. Conclusions: Demographic and clinical variables can be used to predict risk of death within 30 days of a clinical encounter for patients with MBC. Next steps include selection of a preferred model for clinical use, balancing performance characteristics and acceptability, followed by implementation and evaluation of the prognostic tool in the clinic. Candidate models, varying by threshold or percentage of patients assumed to be at high risk, for the outcome of death within 30 days among patients with metastatic breast cancer.[Table: see text]

scholarly journals Interaction of MRE11 and Clinicopathologic Characteristics in Recurrence of Breast Cancer: Individual and Cumulated Receiver Operating Characteristic Analyses

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Cheng-Hong Yang ◽  
Sin-Hua Moi ◽  
Li-Yeh Chuang ◽  
Shyng-Shiou F. Yuan ◽  
Ming-Feng Hou ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Receiver Operating Characteristic ◽  
Roc Analysis ◽  
Operating Characteristic ◽  
Growth Factor Receptor ◽  
Cancer Recurrence ◽  
Breast Cancer Recurrence ◽  
Prognostic Indicators ◽  
Clinicopathologic Characteristics ◽  
Receiver Operating

The interaction between the meiotic recombination 11 homolog A (MRE11) oncoprotein and breast cancer recurrence status remains unclear. The aim of this study was to assess the interaction between MRE11 and clinicopathologic variables in breast cancer. A dataset for 254 subjects with breast cancer (220 nonrecurrent and 34 recurrent) was used in individual and cumulated receiver operating characteristic (ROC) analyses of MRE11 and 12 clinicopathologic variables for predicting breast cancer recurrence. In individual ROC analysis, the area under curve (AUC) for each predictor of breast cancer recurrence was smaller than 0.7. In cumulated ROC analysis, however, the AUC value for each predictor improved. Ten relevant variables in breast cancer recurrence were used to find the optimal prognostic indicators. The presence of any six of the following ten variables had a high (79%) sensitivity and a high (70%) specificity for predicting breast cancer recurrence: tumor size ≥ 2.4 cm, tumor stage II/III, therapy other than hormone therapy, age ≥ 52 years, MRE11 positive cells > 50%, body mass index ≥ 24, lymph node metastasis, positivity for progesterone receptor, positivity for epidermal growth factor receptor, and negativity for estrogen receptor. In conclusion, this study revealed that these 10 clinicopathologic variables are the minimum discriminators needed for optimal discriminant effectiveness in predicting breast cancer recurrence.

scholarly journals Age-Adjusted Endothelial Activation and Stress Index for Coronavirus Disease 2019 at Admission Is a Reliable Predictor for 28-Day Mortality in Hospitalized Patients With Coronavirus Disease 2019

2021 ◽  
Vol 8 ◽  
Author(s):  
Felipe Pérez-García ◽  
Rebeca Bailén ◽  
Juan Torres-Macho ◽  
Amanda Fernández-Rodríguez ◽  
Maria Ángeles Jiménez-Sousa ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Receiver Operating Characteristic ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Operating Characteristic ◽  
Predictive Performance ◽  
Endothelial Activation ◽  
Stress Index ◽  
Reliable Predictor ◽  
Receiver Operating

Background: Endothelial Activation and Stress Index (EASIX) predict death in patients undergoing allogeneic hematopoietic stem cell transplantation who develop endothelial complications. Because coronavirus disease 2019 (COVID-19) patients also have coagulopathy and endotheliitis, we aimed to assess whether EASIX predicts death within 28 days in hospitalized COVID-19 patients.Methods: We performed a retrospective study on COVID-19 patients from two different cohorts [derivation (n = 1,200 patients) and validation (n = 1,830 patients)]. The endpoint was death within 28 days. The main factors were EASIX [(lactate dehydrogenase * creatinine)/thrombocytes] and aEASIX-COVID (EASIX * age), which were log2-transformed for analysis.Results: Log2-EASIX and log2-aEASIX-COVID were independently associated with an increased risk of death in both cohorts (p &lt; 0.001). Log2-aEASIX-COVID showed a good predictive performance for 28-day mortality both in the derivation cohort (area under the receiver-operating characteristic = 0.827) and in the validation cohort (area under the receiver-operating characteristic = 0.820), with better predictive performance than log2-EASIX (p &lt; 0.001). For log2 aEASIX-COVID, patients with low/moderate risk (&lt;6) had a 28-day mortality probability of 5.3% [95% confidence interval (95% CI) = 4–6.5%], high (6–7) of 17.2% (95% CI = 14.7–19.6%), and very high (&gt;7) of 47.6% (95% CI = 44.2–50.9%). The cutoff of log2 aEASIX-COVID = 6 showed a positive predictive value of 31.7% and negative predictive value of 94.7%, and log2 aEASIX-COVID = 7 showed a positive predictive value of 47.6% and negative predictive value of 89.8%.Conclusion: Both EASIX and aEASIX-COVID were associated with death within 28 days in hospitalized COVID-19 patients. However, aEASIX-COVID had significantly better predictive performance than EASIX, particularly for discarding death. Thus, aEASIX-COVID could be a reliable predictor of death that could help to manage COVID-19 patients.

Neutrophil-to-lymphocyte and platelet-to-lymphocyte ratios as predictors of outcomes in inflammatory breast cancer

2021 ◽  
Author(s):  
Ouissam Al Jarroudi ◽  
Khalid El Bairi ◽  
Naima Abda ◽  
Adil Zaimi ◽  
Laila Jaouani ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Receiver Operating Characteristic ◽  
Inflammatory Breast Cancer ◽  
Operating Characteristic ◽  
Cox Regression ◽  
Menopausal Status ◽  
Pathologic Complete Response ◽  
Disease Free Survival ◽  
Prognostic Impact ◽  
Receiver Operating

Background: Inflammatory breast cancer (IBC) is uncommon, aggressive and associated with poor survival outcomes. The lack of prognostic biomarkers and therapeutic targets specific to IBC is an added challenge for clinical practice and research. Inflammatory biomarkers such as neutrophil-to-lymphocyte and platelet-to-lymphocyte ratios (NLR and PLR) demonstrated independent prognostic impact for survival in breast cancer. In our study, these biomarkers were investigated in a cohort of patients with nonmetastatic IBC. Methods: A retrospective cohort of 102 IBC patients with nonmetastatic disease was conducted at the Mohammed VI University Hospital (Oujda, Morocco) between January 2010 and December 2014. NLR and PLR were obtained from blood cell count at baseline before neoadjuvant chemotherapy (NACT) from patients’ medical records. The receiver operating characteristic was used to find the optimal cut-off. Correlation between these blood-based biomarkers and response to NACT was analyzed by Chi-squared and Fisher's exact test. Their prognostic value for predicting disease-free survival (DFS) and overall survival (OS) was performed based on Cox regression models. Results: Totally, 102 patients with IBC were included in the analysis. Pathologic complete response (pCR) after NACT, defined by the absence of an invasive tumor in the breast tissues and nodes after surgery (ypT0 ypN0), was observed in eight patients (7.8%). NACT response was found to be associated with menopausal status (p = 0.039) and nodal status (p < 0.001). Patients with a low NLR had a higher pCR rate as compared with the high-NLR group (p = 0.043). However, the pCR rate was not significantly associated with age (p = 0.122), tumor side (p = 0.403), BMI (p = 0.615), histological grade (p = 0.059), hormone receptors status (p = 0.206), human epidermal growth factor receptor 2 (p = 0.491) and PLR (p = 0.096). Pre-treatment blood-based NLR of 2.28 was used as the cut-off value to discriminate between high and low NLR according to the receiver operating characteristic curves. Similarly, a value of 178 was used as the cut off for PLR. Patients with low-NLR had a significantly better 5-year DFS (p < 0.001) and OS (p < 0.001) than the high-NLR group. Moreover, low-PLR was significantly associated with higher DFS (p = 0.001) and OS (p = 0.003). The NLR showed a significant prognostic impact for DFS (HR: 2.57; 95% CI: 1.43–4.61; p = 0.01) and for OS (HR: 2.92; 95% CI: 1.70–5.02; p < 0.001). Similarly, a meaningful association between PLR and 5-year DFS (HR: 1.95; 95% CI: 1.10–3.46; p = 0.021) and OS (HR: 1.82; 95% CI: 1.06–3.14; p = 0.03) was noticed. Conclusions: High NLR and PLR were found associated with reduced DFS and OS in nonmetastatic IBC. Further studies are awaited to confirm these findings.

Sign in / Sign up

Export Citation Format

Share Document