Breast cancer risk estimation with artificial neural networks revisited: discrimination and calibration

From Data to Insights: Machine Learning Empowers Prognostic Biomarker Prediction in Autism

Autism Spectrum Disorder (ASD) poses significant challenges to society and science due to its impact on communication, social interaction, and repetitive behavior patterns in affected children. The Autism and Developmental Disabilities Monitoring (ADDM) Network continuously monitors ASD prevalence and characteristics. In 2020, ASD prevalence was estimated at 1 in 36 children, with higher rates than previous estimates. This study focuses on ongoing ASD research conducted by Erciyes University. Serum samples from 45 ASD patients and 21 unrelated control participants were analyzed to assess the expression of 372 microRNAs (miRNAs). Six miRNAs (miR-19a-3p, miR-361-5p, miR-3613-3p, miR-150-5p, miR-126-3p, and miR-499a-5p) exhibited significant downregulation in all ASD patients compared to healthy controls. The current study endeavors to identify dependable diagnostic biomarkers for ASD, addressing the pressing need for non-invasive, accurate, and cost-effective diagnostic tools, as current methods are subjective and time-intensive. A pivotal discovery in this study is the potential diagnostic value of miR-126-3p, offering the promise of earlier and more accurate ASD diagnoses, potentially leading to improved intervention outcomes. Leveraging machine learning, such as the K-nearest neighbors (KNN) model, presents a promising avenue for precise ASD diagnosis using miRNA biomarkers.

Breast cancer pre-clinical screening using infrared thermography and artificial intelligence: a prospective, multicentre, diagnostic accuracy cohort study

BACKGROUND

Given the limited access to breast cancer (BC) screening, the authors developed and validated a mobile phone-artificial intelligence-based infrared thermography (AI-IRT) system for BC screening.

MATERIALS AND METHODS

This large prospective clinical trial assessed the diagnostic performance of the AI-IRT system. The authors constructed two datasets and two models, performed internal and external validation, and compared the diagnostic accuracy of the AI models and clinicians. Dataset A included 2100 patients recruited from 19 medical centres in nine regions of China. Dataset B was used for independent external validation and included 102 patients recruited from Langfang People's Hospital.

RESULTS

The area under the receiver operating characteristic curve of the binary model for identifying low-risk and intermediate/high-risk patients was 0.9487 (95% CI: 0.9231-0.9744) internally and 0.9120 (95% CI: 0.8460-0.9790) externally. The accuracy of the binary model was higher than that of human readers (0.8627 vs. 0.8088, respectively). In addition, the binary model was better than the multinomial model and used different diagnostic thresholds based on BC risk to achieve specific goals.

CONCLUSIONS

The accuracy of AI-IRT was high across populations with different demographic characteristics and less reliant on manual interpretations, demonstrating that this model can improve pre-clinical screening and increase screening rates.

Predicting breast cancer-specific survival in metaplastic breast cancer patients using machine learning algorithms

Metaplastic breast cancer (MpBC) is a rare and aggressive subtype of breast cancer, with data emerging on prognostic factors and survival prediction. This study aimed to develop machine learning models to predict breast cancer-specific survival (BCSS) in MpBC patients, utilizing a dataset of 160 patients with clinical, pathological, and biological variables. An in-depth variable selection process was carried out using gain ratio and correlation-based methods, resulting in 10 variables for model estimation. Five models (decision tree with bagging; logistic regression; multilayer perceptron; naïve Bayes; and, random forest algorithms) were evaluated using 10-fold cross-validation. Despite the constraints posed by the absence of therapeutic information, the random forest model exhibited the highest performance in predicting BCSS, with an ROC area of 0.808. This study emphasizes the potential of machine learning algorithms in predicting prognosis for complex and heterogeneous cancer subtypes using clinical datasets, and their potential to contribute to patient management. Further research that incorporates additional variables, such as treatment response, and more advanced machine learning techniques will likely enhance the predictive power of MpBC prognostic models.

Personalized Risk Analysis to Improve the Psychological Resilience of Women Undergoing Treatment for Breast Cancer: Development of a Machine Learning-Driven Clinical Decision Support Tool

BACKGROUND

Health professionals are often faced with the need to identify women at risk of manifesting poor psychological resilience following the diagnosis and treatment of breast cancer. Machine learning algorithms are increasingly used to support clinical decision support (CDS) tools in helping health professionals identify women who are at risk of adverse well-being outcomes and plan customized psychological interventions for women at risk. Clinical flexibility, cross-validated performance accuracy, and model explainability permitting person-specific identification of risk factors are highly desirable features of such tools.

OBJECTIVE

This study aimed to develop and cross-validate machine learning models designed to identify breast cancer survivors at risk of poor overall mental health and global quality of life and identify potential targets of personalized psychological interventions according to an extensive set of clinical recommendations.

METHODS

A set of 12 alternative models was developed to improve the clinical flexibility of the CDS tool. All models were validated using longitudinal data from a prospective, multicenter clinical pilot at 5 major oncology centers in 4 countries (Italy, Finland, Israel, and Portugal; the Predicting Effective Adaptation to Breast Cancer to Help Women to BOUNCE Back [BOUNCE] project). A total of 706 patients with highly treatable breast cancer were enrolled shortly after diagnosis and before the onset of oncological treatments and were followed up for 18 months. An extensive set of demographic, lifestyle, clinical, psychological, and biological variables measured within 3 months after enrollment served as predictors. Rigorous feature selection isolated key psychological resilience outcomes that could be incorporated into future clinical practice.

RESULTS

Balanced random forest classifiers were successful at predicting well-being outcomes, with accuracies ranging between 78% and 82% (for 12-month end points after diagnosis) and between 74% and 83% (for 18-month end points after diagnosis). Explainability and interpretability analyses built on the best-performing models were used to identify potentially modifiable psychological and lifestyle characteristics that, if addressed systematically in the context of personalized psychological interventions, would be most likely to promote resilience for a given patient.

CONCLUSIONS

Our results highlight the clinical utility of the BOUNCE modeling approach by focusing on resilience predictors that can be readily available to practicing clinicians at major oncology centers. The BOUNCE CDS tool paves the way for personalized risk assessment methods to identify patients at high risk of adverse well-being outcomes and direct valuable resources toward those most in need of specialized psychological interventions.

Diagnosis of Breast Cancer Using Computational Intelligence Models and IoT Applications

The use of computer-aided diagnostic (CAD) models has been proposed to aid in the detection and classification of breast cancer. In this work, we evaluated the performance of multilayer perceptron neural network and nonlinear support vector machine models to classify breast cancer nodules. From the contour of 569 samples, ten morphological features were used as input to the classifiers. The average results obtained in the set of 50 simulations performed show that the proposed models showed good performance (all exceeded 90.0%) in terms of accuracy in the test set. The nonlinear support vector machine algorithm stands out when compared to the proposed multilayer perceptron neural network algorithm, with 99% accuracy and a 2% false-negative rate. The neural network model presented lower performance than the nonlinear support vector machine classifier. With the application of the proposed models, the average results obtained are promising in the classification of breast cancer.

Present and future of machine learning in breast surgery: systematic review

BACKGROUND

Machine learning is a set of models and methods that can automatically detect patterns in vast amounts of data, extract information, and use it to perform decision-making under uncertain conditions. The potential of machine learning is significant, and breast surgeons must strive to be informed with up-to-date knowledge and its applications.

METHODS

A systematic database search of Embase, MEDLINE, the Cochrane database, and Google Scholar, from inception to December 2021, was conducted of original articles that explored the use of machine learning and/or artificial intelligence in breast surgery in EMBASE, MEDLINE, Cochrane database and Google Scholar.

RESULTS

The search yielded 477 articles, of which 14 studies were included in this review, featuring 73 847 patients. Four main areas of machine learning application were identified: predictive modelling of surgical outcomes; breast imaging-based context; screening and triaging of patients with breast cancer; and as network utility for detection. There is evident value of machine learning in preoperative planning and in providing information for surgery both in a cancer and an aesthetic context. Machine learning outperformed traditional statistical modelling in all studies for predicting mortality, morbidity, and quality of life outcomes. Machine learning patterns and associations could support planning, anatomical visualization, and surgical navigation.

CONCLUSION

Machine learning demonstrated promising applications for improving breast surgery outcomes and patient-centred care. Neveretheless, there remain important limitations and ethical concerns relating to implementing artificial intelligence into everyday surgical practices.

Development and validation of prognostic models for anal cancer outcomes using distributed learning: protocol for the international multi-centre atomCAT2 study

BACKGROUND

Anal cancer is a rare cancer with rising incidence. Despite the relatively good outcomes conferred by state-of-the-art chemoradiotherapy, further improving disease control and reducing toxicity has proven challenging. Developing and validating prognostic models using routinely collected data may provide new insights for treatment development and selection. However, due to the rarity of the cancer, it can be difficult to obtain sufficient data, especially from single centres, to develop and validate robust models. Moreover, multi-centre model development is hampered by ethical barriers and data protection regulations that often limit accessibility to patient data. Distributed (or federated) learning allows models to be developed using data from multiple centres without any individual-level patient data leaving the originating centre, therefore preserving patient data privacy. This work builds on the proof-of-concept three-centre atomCAT1 study and describes the protocol for the multi-centre atomCAT2 study, which aims to develop and validate robust prognostic models for three clinically important outcomes in anal cancer following chemoradiotherapy.

METHODS

This is a retrospective multi-centre cohort study, investigating overall survival, locoregional control and freedom from distant metastasis after primary chemoradiotherapy for anal squamous cell carcinoma. Patient data will be extracted and organised at each participating radiotherapy centre (n = 18). Candidate prognostic factors have been identified through literature review and expert opinion. Summary statistics will be calculated and exchanged between centres prior to modelling. The primary analysis will involve developing and validating Cox proportional hazards models across centres for each outcome through distributed learning. Outcomes at specific timepoints of interest and factor effect estimates will be reported, allowing for outcome prediction for future patients.

DISCUSSION

The atomCAT2 study will analyse one of the largest available cross-institutional cohorts of patients with anal cancer treated with chemoradiotherapy. The analysis aims to provide information on current international clinical practice outcomes and may aid the personalisation and design of future anal cancer clinical trials through contributing to a better understanding of patient risk stratification.

Investigating the clinical significance of EGFR expression using machine learning in a series of Iraqi patients with triple-negative breast cancer

Breast cancer is a heterogeneous disease with a distinct profile of the expression of each tumor. Triple-negative breast cancer (TNBC) is a molecular subtype of breast cancer characterized by an aggressive clinical behavior linked to loss or reduced expression of estrogen, progesterone, and Her2/neu receptors. The study's main objective was to investigate the clinical significance of epidermal growth factor receptor (EGFR) overexpression in a series of Iraqi patients with TNBC. The sectional analytic study involved immunohistochemical analysis of EGFR expression in randomly selected 53 formalin fixed paraffin embedded tissue blocks of TNBC cases out of 127 Iraqi patients with TNBC and correlated expression data with clinicopathological parameters including survival time. Machine learning (statistical tests and principal component analysis (PCA)) was used to predict the outcome of the patients using EGFR expression data together with clinicopathological parameters. EGFR was expressed in approximately 28% of TNBC cases. We estimated the risk of mortality and distant metastasis based on EGFR expression and clinicopathologic factors using the principal component analysis (PCA) model. We found a substantial positive correlation between clinical stage and distant metastasis, clinical stage and death, death and distant metastasis, and death and positive EGFR expression. Overall, EGFR expression was linked to a poor prognosis and increased mortality. A higher risk of distant metastasis and death was associated with an advanced clinical stage of the tumor. Furthermore, the existence of distant metastases increased the risk of death. These findings raise the possibility of using EGFR expression data with other clinicopathological parameters to predict the outcome of patients with TNBC.

A Novel Hybrid Deep Learning Model for Metastatic Cancer Detection

Cancer has been found as a heterogeneous disease with various subtypes and aims to destroy the body's normal cells abruptly. As a result, it is essential to detect and prognosis the distinct type of cancer since they may help cancer survivors with treatment in the early stage. It must also divide cancer patients into high- and low-risk groups. While realizing efficient detection of cancer is frequently a time-taking and exhausting task with the high possibility of pathologist errors and previous studies employed data mining and machine learning (ML) techniques to identify cancer, these strategies rely on handcrafted feature extraction techniques that result in incorrect classification. On the contrary, deep learning (DL) is robust in feature extraction and has recently been widely used for classification and detection purposes. This research implemented a novel hybrid AlexNet-gated recurrent unit (AlexNet-GRU) model for the lymph node (LN) breast cancer detection and classification. We have used a well-known Kaggle (PCam) data set to classify LN cancer samples. This study is tested and compared among three models: convolutional neural network GRU (CNN-GRU), CNN long short-term memory (CNN-LSTM), and the proposed AlexNet-GRU. The experimental results indicated that the performance metrics accuracy, precision, sensitivity, and specificity (99.50%, 98.10%, 98.90%, and 97.50) of the proposed model can reduce the pathologist errors that occur during the diagnosis process of incorrect classification and significantly better performance than CNN-GRU and CNN-LSTM models. The proposed model is compared with other recent ML/DL algorithms to analyze the model's efficiency, which reveals that the proposed AlexNet-GRU model is computationally efficient. Also, the proposed model presents its superiority over state-of-the-art methods for LN breast cancer detection and classification.

Application and Clinical Value of Machine Learning-Based Cervical Cancer Diagnosis and Prediction Model in Adjuvant Chemotherapy for Cervical Cancer: A Single-Center, Controlled, Non-Arbitrary Size Case-Control Study

Objective

A case-control study was conducted to explore the application and clinical value of machine learning-based cervical cancer (CC) diagnosis and prediction model in adjuvant chemotherapy of CC.

Methods

From August 2019 to August 2021, 46 patients with stage IA CC (study group) and 55 patients with high-grade squamous intraepithelial lesions (HSIL) (control group) were retrospectively analyzed. All patients completed routine MRI examinations, the ADC values of diseased CC and normal cervix and cervical tissues in different stages were compared, and the changes of ADC values in CC tissues before and after chemotherapy were analyzed. The training set (IA = 37, HSIL = 44) and test set (IA = 9, HSIL = 11) are set in a ratio of 4 : 1. The preoperative MRI images were collected and uploaded to the radiomics cloud platform after preprocessing, and the cervix was manually delineated layer by layer on OSag-T2WI, OAx-T1WI, and OAx-T2FS, respectively, to obtain a three-dimensional volume of interest (VOI) of the cervix to extract omics features. Variance Threshold analysis, univariate feature selection (SelectKBest), and least absolute shrinkage and selection operator (LASSO) are adopted to reduce the dimension of data and enroll features. The arbitrary forest model was adopted for machine learning, the ROC curve was drawn, and the diagnostic performance of different sequence omics models was analyzed.

Results

Compared with ADC of stage A CC and HSIL, the ADC value of CC was remarkably lower than that of normal CC (P < 0.05). The ROC curve analysis of ADC value to differentiate CC and normal cervix indicated that the AUC was 0.838 and the 95% confidence interval was 0.721–0.955. According to the maximum Youden index of 0.848, the optimal critical value of ADC was 1.267 × 10⁻³ mm²/s and the sensitivity and specificity were 92.21% and 9.48%, respectively. All results are indicated in Table 2. After CC treatment, 12 patients were effective (CR + PR) and 4 patients were ineffective (PD + SD). When the b value was 1000 s/mm², the ADC value of the effective patients after the second chemotherapy was significantly higher than that of the first chemotherapy and before treatment (P < 0.05). There was no significant difference between the ADC value after the first chemotherapy and before treatment, compared with before treatment (P > 0.05). There was no significant difference in ADC value between the ineffective patients before treatment and after the first and second chemotherapy (P > 0.05). A total of 8 omics features were extracted based on OSag-T2WI, all of which were wavelet features, including 7 texture features and 1 first-order feature. A total of 10 omics features were extracted based on OAx-T1WI, including 6 wavelet first-order features, 2 gradient first-order features, and 2 wavelet texture features. Based on OAx-T2FS, 6 omics features were extracted, including 3 wavelet texture features, 2 original shape features, and 1 logarithmic first-order feature. Based on OSag-T2WI&OAx-T2FS, 9 histological features were extracted, 4 from OSag-T2WI and 5 from OAx-T2FS. The diagnostic performance of the four arbitrary forest models is indicated in Table 1, and the ROC curve is indicated in Figure 6. The diagnostic performance of the omics model based on OSag-T2WI&OAx-T2FS was the best in both the training set and the test set. The AUC of the training set was 0.991 (95% CI (0.94, 1.00)), and the accuracy rate was 0.925. The AUC of the test set was 0.894 (95% CI (0.75, 1.00)), and the accuracy rate was 0.835. On the other hand, the diagnostic efficiency of the group model based on OAx-T1WI was the worst in both the training set and the test set. The AUC of the training set was 0.713 (95% CI (0.52, 0.92)), and the accuracy rate was 0.71. The AUC of test set is 0.513 (95% CI (0.24, 0.77)), and the accuracy rate was 0.56, which has no practical clinical significance.

Conclusion

A CC diagnosis and prediction model based on machine learning can better distinguish stage IA CC from HSIL in the absence of clear lesions, which is of great significance for reducing invasive examination before surgery, guiding surgical procedures and adjuvant chemotherapy for CC.

Data mining and mathematical models in cancer prognosis and prediction

Cancer is a fetal and complex disease. Individual differences of the same cancer type or the same patient at different stages of cancer development may require distinct treatments. Pathological differences are reflected in tissues, cells and gene levels etc. The interactions between the cancer cells and nearby microenvironments can also influence the cancer progression and metastasis. It is a huge challenge to understand all of these mechanistically and quantitatively. Researchers applied pattern recognition algorithms such as machine learning or data mining to predict cancer types or classifications. With the rapidly growing and available computing powers, researchers begin to integrate huge data sets, multi-dimensional data types and information. The cells are controlled by the gene expressions determined by the promoter sequences and transcription regulators. For example, the changes in the gene expression through these underlying mechanisms can modify cell progressing in the cell-cycle. Such molecular activities can be governed by the gene regulations through the underlying gene regulatory networks, which are essential for cancer study when the information and gene regulations are clear and available. In this review, we briefly introduce several machine learning methods of cancer prediction and classification which include Artificial Neural Networks (ANNs), Decision Trees (DTs), Support Vector Machine (SVM) and naive Bayes. Then we describe a few typical models for building up gene regulatory networks such as Correlation, Regression and Bayes methods based on available data. These methods can help on cancer diagnosis such as susceptibility, recurrence, survival etc. At last, we summarize and compare the modeling methods to analyze the development and progression of cancer through gene regulatory networks. These models can provide possible physical strategies to analyze cancer progression in a systematic and quantitative way.

Application of the Machine-Learning Model to Improve Prediction of Non-Sentinel Lymph Node Metastasis Status Among Breast Cancer Patients

Background

Performing axillary lymph node dissection (ALND) is the current standard option after a positive sentinel lymph node (SLN). However, whether 1–2 metastatic SLNs require ALND is debatable. The probability of metastasis in non-sentinel lymph nodes (NSLNs) can be calculated using nomograms. In this study, we developed an individualized model using machine-learning (ML) methods to select potential variables, which influence NSLN metastasis.

Materials and Methods

Cohorts of patients with early breast cancer who underwent SLN biopsy and ALND between 2012 and 2021 were created (training cohort, N 157 and validation cohort, N 58) for the development of the nomogram. Three ML methods were trained in the training set to create a strong predictive model. Finally, the multiple iterations of the least absolute shrinkage and selection operator regression method were used to determine the variables associated with NSLN status.

Results

Four independent variables (positive SLN number, absence of lymph node hilum, lymphovascular invasion (LVI), and total number of SLNs harvested) were combined to generate the nomogram. The area under the receiver operating characteristic curve (AUC) value of 0.759 was obtained in the entire set. The AUC values for the training set and the test set were 0.782 and 0.705, respectively. The Hosmer-Lemeshow test of the model fit accuracy was identified with p = 0.759.

Conclusion

This study developed a nomogram that incorporates ultrasound (US)-related variables using the ML method and serves to clinically predict the non-metastatic status of NSLN and help in the selection of the appropriate treatment option.

Observation on Application Effect of Arterial Puncture and Catheterization under Guidance of Intelligent Medical Care Ultrasound in Clinical Anesthesia

In clinical anesthesia and the rescue of critically ill patients, arterial puncture and catheterization are the most commonly chosen ways to establish central arterial access for patients. Invasive arterial puncture and catheterization facilitate the grasp of real-time vital sign information of patients during surgery, which strengthens patient monitoring during surgery and improves safety. However, the traditional method of arterial puncture and cannulation through palpation of the radial artery is often prone to complications related to mechanical injury, such as hemorrhage, hematoma, and accidental perforation of the artery. Studies have shown that ultrasound-guided radial artery puncture and cannulation can shorten the puncture cannulation time, reduce the incidence of complications related to puncture cannulation, and improve the success rate of puncture cannulation. In order to verify it, this paper uses the experimental group and the control group to conduct comparative experiments and uses the neural network method to evaluate the effects of the two methods. As a more mature method of artificial intelligence, BP neural network is widely used in a wide range of applications and has the characteristics of strong generalization ability and fast convergence, so we choose it as the base model. The specific work of this paper is as follows: (1) in-depth study of the relevant theory of BP neural network (BPNN), focusing on the structure of BPNN and the working principle of algorithm; the problems to be solved in the clinical anesthesia effect evaluation have laid a theoretical foundation for the establishment of an improved BPNN evaluation model in the following chapters. (2) introduce the basic principle of genetic neural network, analyze the benefits of combining genetic neural network and BPNN; introduce in detail the process of genetic algorithm to optimize the weights and thresholds of BPNN, and establish a GA-BP evaluation model. The test proves the feasibility and superiority of the model.

A Machine Learning Method for Classification of Cervical Cancer

Cervical cancer is one of the leading causes of premature mortality among women worldwide and more than 85% of these deaths are in developing countries. There are several risk factors associated with cervical cancer. In this paper, we developed a predictive model for predicting the outcome of patients with cervical cancer, given risk patterns from individual medical records and preliminary screening. This work presents a decision tree (DT) classification algorithm to analyze the risk factors of cervical cancer. Recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) feature selection techniques were fully explored to determine the most important attributes for cervical cancer prediction. The dataset employed here contains missing values and is highly imbalanced. Therefore, a combination of under and oversampling techniques called SMOTETomek was employed. A comparative analysis of the proposed model has been performed to show the effectiveness of feature selection and class imbalance based on the classifier’s accuracy, sensitivity, and specificity. The DT with the selected features from RFE and SMOTETomek has better results with an accuracy of 98.72% and sensitivity of 100%. DT classifier is shown to have better performance in handling classification problems when the features are reduced, and the problem of high class imbalance is addressed.

Deep Machine Learning for Oral Cancer: From Precise Diagnosis to Precision Medicine

Oral squamous cell carcinoma (OSCC) is one of the most prevalent cancers worldwide and its incidence is on the rise in many populations. The high incidence rate, late diagnosis, and improper treatment planning still form a significant concern. Diagnosis at an early-stage is important for better prognosis, treatment, and survival. Despite the recent improvement in the understanding of the molecular mechanisms, late diagnosis and approach toward precision medicine for OSCC patients remain a challenge. To enhance precision medicine, deep machine learning technique has been touted to enhance early detection, and consequently to reduce cancer-specific mortality and morbidity. This technique has been reported to have made a significant progress in data extraction and analysis of vital information in medical imaging in recent years. Therefore, it has the potential to assist in the early-stage detection of oral squamous cell carcinoma. Furthermore, automated image analysis can assist pathologists and clinicians to make an informed decision regarding cancer patients. This article discusses the technical knowledge and algorithms of deep learning for OSCC. It examines the application of deep learning technology in cancer detection, image classification, segmentation and synthesis, and treatment planning. Finally, we discuss how this technique can assist in precision medicine and the future perspective of deep learning technology in oral squamous cell carcinoma.

Statistical biopsy: An emerging screening approach for early detection of cancers

Despite large investment cancer continues to be a major source of mortality and morbidity throughout the world. Traditional methods of detection and diagnosis such as biopsy and imaging, tend to be expensive and have risks of complications. As data becomes more abundant and machine learning continues advancing, it is natural to ask how they can help solve some of these problems. In this paper we show that using a person's personal health data it is possible to predict their risk for a wide variety of cancers. We dub this process a "statistical biopsy." Specifically, we train two neural networks, one predicting risk for 16 different cancer types in females and the other predicting risk for 15 different cancer types in males. The networks were trained as binary classifiers identifying individuals that were diagnosed with the different cancer types within 5 years of joining the PLOC trial. However, rather than use the binary output of the classifiers we show that the continuous output can instead be used as a cancer risk allowing a holistic look at an individual's cancer risks. We tested our multi-cancer model on the UK Biobank dataset showing that for most cancers the predictions generalized well and that looking at multiple cancer risks at once from personal health data is a possibility. While the statistical biopsy will not be able to replace traditional biopsies for diagnosing cancers, we hope there can be a shift of paradigm in how statistical models are used in cancer detection moving to something more powerful and more personalized than general population screening guidelines.

Synthesizing time-series wound prognosis factors from electronic medical records using generative adversarial networks

Wound prognostic models not only provide an estimate of wound healing time to motivate patients to follow up their treatments but also can help clinicians to decide whether to use a standard care or adjuvant therapies and to assist them with designing clinical trials. However, collecting prognosis factors from Electronic Medical Records (EMR) of patients is challenging due to privacy, sensitivity, and confidentiality. In this study, we developed time series medical generative adversarial networks (GANs) to generate synthetic wound prognosis factors using very limited information collected during routine care in a specialized wound care facility. The generated prognosis variables are used in developing a predictive model for chronic wound healing trajectory. Our novel medical GAN can produce both continuous and categorical features from EMR. Moreover, we applied temporal information to our model by considering data collected from the weekly follow-ups of patients. Conditional training strategies were utilized to enhance training and generate classified data in terms of healing or non-healing. The ability of the proposed model to generate realistic EMR data was evaluated by TSTR (test on the synthetic, train on the real), discriminative accuracy, and visualization. We utilized samples generated by our proposed GAN in training a prognosis model to demonstrate its real-life application. Using the generated samples in training predictive models improved the classification accuracy by 6.66-10.01% compared to the previous EMR-GAN. Additionally, the suggested prognosis classifier has achieved the area under the curve (AUC) of 0.875, 0.810, and 0.647 when training the network using data from the first three visits, first two visits, and first visit, respectively. These results indicate a significant improvement in wound healing prediction compared to the previous prognosis models.

Mechanism-Centric Approaches for Biomarker Detection and Precision Therapeutics in Cancer

Biomarker discovery is at the heart of personalized treatment planning and cancer precision therapeutics, encompassing disease classification and prognosis, prediction of treatment response, and therapeutic targeting. However, many biomarkers represent passenger rather than driver alterations, limiting their utilization as functional units for therapeutic targeting. We suggest that identification of driver biomarkers through mechanism-centric approaches, which take into account upstream and downstream regulatory mechanisms, is fundamental to the discovery of functionally meaningful markers. Here, we examine computational approaches that identify mechanism-centric biomarkers elucidated from gene co-expression networks, regulatory networks (e.g., transcriptional regulation), protein-protein interaction (PPI) networks, and molecular pathways. We discuss their objectives, advantages over gene-centric approaches, and known limitations. Future directions highlight the importance of input and model interpretability, method and data integration, and the role of recently introduced technological advantages, such as single-cell sequencing, which are central for effective biomarker discovery and time-cautious precision therapeutics.

Towards the Interpretability of Machine Learning Predictions for Medical Applications Targeting Personalised Therapies: A Cancer Case Survey

Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. Machine Learning and, in particular, Deep Neural Networks are behind this revolution. Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements. In this sense, learning tools are becoming a commodity but, to be able to assist doctors on a daily basis, it is essential to fully understand how models can be interpreted. In this survey, we analyse current machine learning models and other in-silico tools as applied to medicine-specifically, to cancer research-and we discuss their interpretability, performance and the input data they are fed with. Artificial neural networks (ANN), logistic regression (LR) and support vector machines (SVM) have been observed to be the preferred models. In addition, convolutional neural networks (CNNs), supported by the rapid development of graphic processing units (GPUs) and high-performance computing (HPC) infrastructures, are gaining importance when image processing is feasible. However, the interpretability of machine learning predictions so that doctors can understand them, trust them and gain useful insights for the clinical practice is still rarely considered, which is a factor that needs to be improved to enhance doctors' predictive capacity and achieve individualised therapies in the near future.

A machine learning-based pipeline for modeling medical, socio-demographic, lifestyle and self-reported psychological traits as predictors of mental health outcomes after breast cancer diagnosis: An initial effort to define resilience effects

Displaying resilience following a diagnosis of breast cancer is crucial for successful adaptation to illness, well-being, and health outcomes. Several theoretical and computational models have been proposed toward understanding the complex process of illness adaptation, involving a large variety of patient sociodemographic, lifestyle, medical, and psychological characteristics. To date, conventional multivariate statistical methods have been used extensively to model resilience. In the present work we describe a computational pipeline designed to identify the most prominent predictors of mental health outcomes following breast cancer diagnosis. A machine learning framework was developed and tested on the baseline data (recorded immediately post diagnosis) from an ongoing prospective, multinational study. This fully annotated dataset includes socio-demographic, lifestyle, medical and self-reported psychological characteristics of women recently diagnosed with breast cancer (N = 609). Nine different feature selection and cross-validated classification schemes were compared on their performance in classifying patients into low vs high depression symptom severity. Best-performing approaches involved a meta-estimator combined with a Support Vector Machines (SVMs) classification algorithm, exhibiting balanced accuracy of 0.825, and a fair balance between sensitivity (90%) and specificity (74%). These models consistently identified a set of psychological traits (optimism, perceived ability to cope with trauma, resilience as trait, ability to comprehend the illness), and subjective perceptions of personal functionality (physical, social, cognitive) as key factors accounting for concurrent depression symptoms. A comprehensive supervised learning pipeline is proposed for the identification of predictors of depression symptoms which could severely impede adaptation to illness.

Machine Learning Algorithms to Predict Recurrence within 10 Years after Breast Cancer Surgery: A Prospective Cohort Study

No studies have discussed machine learning algorithms to predict recurrence within 10 years after breast cancer surgery. This study purposed to compare the accuracy of forecasting models to predict recurrence within 10 years after breast cancer surgery and to identify significant predictors of recurrence. Registry data for breast cancer surgery patients were allocated to a training dataset (n = 798) for model development, a testing dataset (n = 171) for internal validation, and a validating dataset (n = 171) for external validation. Global sensitivity analysis was then performed to evaluate the significance of the selected predictors. Demographic characteristics, clinical characteristics, quality of care, and preoperative quality of life were significantly associated with recurrence within 10 years after breast cancer surgery (p < 0.05). Artificial neural networks had the highest prediction performance indices. Additionally, the surgeon volume was the best predictor of recurrence within 10 years after breast cancer surgery, followed by hospital volume and tumor stage. Accurate recurrence within 10 years prediction by machine learning algorithms may improve precision in managing patients after breast cancer surgery and improve understanding of risk factors for recurrence within 10 years after breast cancer surgery.

KRAS, NRAS, and BRAF mutation prevalence, clinicopathological association, and their application in a predictive model in Mexican patients with metastatic colorectal cancer: A retrospective cohort study

Mutations in KRAS, NRAS, and BRAF (RAS/BRAF) genes are the main predictive biomarkers for the response to anti-EGFR monoclonal antibodies (MAbs) targeted therapy in metastatic colorectal cancer (mCRC). This retrospective study aimed to report the mutational status prevalence of these genes, explore their possible associations with clinicopathological features, and build and validate a predictive model. To achieve these objectives, 500 mCRC Mexican patients were screened for clinically relevant mutations in RAS/BRAF genes. Fifty-two percent of these specimens harbored clinically relevant mutations in at least one screened gene. Among these, 86% had a mutation in KRAS, 7% in NRAS, 6% in BRAF, and 2% in both NRAS and BRAF. Only tumor location in the proximal colon exhibited a significant correlation with KRAS and BRAF mutational status (p-value = 0.0414 and 0.0065, respectively). Further t-SNE analyses were made to 191 specimens to reveal patterns among patients with clinical parameters and KRAS mutational status. Then, directed by the results from classical statistical tests and t-SNE analysis, neural network models utilized entity embeddings to learn patterns and build predictive models using a minimal number of trainable parameters. This study could be the first step in the prediction for RAS/BRAF mutational status from tumoral features and could lead the way to a more detailed and more diverse dataset that could benefit from machine learning methods.

CaliForest: Calibrated Random Forest for Health Data

Real-world predictive models in healthcare should be evaluated in terms of discrimination, the ability to differentiate between high and low risk events, and calibration, or the accuracy of the risk estimates. Unfortunately, calibration is often neglected and only discrimination is analyzed. Calibration is crucial for personalized medicine as they play an increasing role in the decision making process. Since random forest is a popular model for many healthcare applications, we propose CaliForest, a new calibrated random forest. Unlike existing calibration methodologies, CaliForest utilizes the out-of-bag samples to avoid the explicit construction of a calibration set. We evaluated CaliForest on two risk prediction tasks obtained from the publicly-available MIMIC-III database. Evaluation on these binary prediction tasks demonstrates that CaliForest can achieve the same discriminative power as random forest while obtaining a better-calibrated model evaluated across six different metrics. CaliForest is published on the standard Python software repository and the code is openly available on Github.

Review of statistical methods for survival analysis using genomic data

Survival analysis mainly deals with the time to event, including death, onset of disease, and bankruptcy. The common characteristic of survival analysis is that it contains "censored" data, in which the time to event cannot be completely observed, but instead represents the lower bound of the time to event. Only the occurrence of either time to event or censoring time is observed. Many traditional statistical methods have been effectively used for analyzing survival data with censored observations. However, with the development of high-throughput technologies for producing "omics" data, more advanced statistical methods, such as regularization, should be required to construct the predictive survival model with high-dimensional genomic data. Furthermore, machine learning approaches have been adapted for survival analysis, to fit nonlinear and complex interaction effects between predictors, and achieve more accurate prediction of individual survival probability. Presently, since most clinicians and medical researchers can easily assess statistical programs for analyzing survival data, a review article is helpful for understanding statistical methods used in survival analysis. We review traditional survival methods and regularization methods, with various penalty functions, for the analysis of high-dimensional genomics, and describe machine learning techniques that have been adapted to survival analysis.

Proteomic research in sarcomas - current status and future opportunities

Sarcomas are a rare group of mesenchymal cancers comprising over 70 different histological subtypes. For the majority of these diseases, the molecular understanding of the basis of their initiation and progression remains unclear. As such, limited clinical progress in prognosis or therapeutic regimens have been made over the past few decades. Proteomics techniques are being increasingly utilised in the field of sarcoma research. Proteomic research efforts have thus far focused on histological subtype characterisation for the improvement of biological understanding, as well as for the identification of candidate diagnostic, predictive, and prognostic biomarkers for use in clinic. However, the field itself is in its infancy, and none of these proteomic research findings have been translated into the clinic. In this review, we provide a brief overview of the proteomic strategies that have been employed in sarcoma research. We evaluate key proteomic studies concerning several rare and ultra-rare sarcoma subtypes including, gastrointestinal stromal tumours, osteosarcoma, liposarcoma, leiomyosarcoma, malignant rhabdoid tumours, Ewing sarcoma, myxofibrosarcoma, and alveolar soft part sarcoma. Consequently, we illustrate how routine implementation of proteomics within sarcoma research, integration of proteomics with other molecular profiling data, and incorporation of proteomics into clinical trial studies has the potential to propel the biological and clinical understanding of this group of complex rare cancers moving forward.

Data Engineering for Machine Learning in Women's Imaging and Beyond

OBJECTIVE. Data engineering is the foundation of effective machine learning model development and research. The accuracy and clinical utility of machine learning models fundamentally depend on the quality of the data used for model development. This article aims to provide radiologists and radiology researchers with an understanding of the core elements of data preparation for machine learning research. We cover key concepts from an engineering perspective, including databases, data integrity, and characteristics of data suitable for machine learning projects, and from a clinical perspective, including the HIPAA, patient consent, avoidance of bias, and ethical concerns related to the potential to magnify health disparities. The focus of this article is women's imaging; nonetheless, the principles described apply to all domains of medical imaging. CONCLUSION. Machine learning research is inherently interdisciplinary: effective collaboration is critical for success. In medical imaging, radiologists possess knowledge essential for data engineers to develop useful datasets for machine learning model development.

Survey of Breast Cancer Detection Using Machine Learning Techniques in Big Data

Cancer is a disease in which cells in body grow and divide beyond the control. Breast cancer is the second most common disease after lung cancer in women. Incredible advances in health sciences and biotechnology have prompted a huge amount of gene expression and clinical data. Machine learning techniques are improving the prior detection of breast cancer from this data. The research work carried out focuses on the application of machine learning methods, data analytic techniques, tools, and frameworks in the field of breast cancer research with respect to cancer survivability, cancer recurrence, cancer prediction and detection. Some of the widely used machine learning techniques used for detection of breast cancer are support vector machine and artificial neural network. Apache Spark data processing engine is found to be compatible with most of the machine learning frameworks.

Artificial Intelligence (AI) for the early detection of breast cancer: a scoping review to assess AI's potential in breast screening practice

INTRODUCTION

Various factors are driving interest in the application of artificial intelligence (AI) for breast cancer (BC) detection, but it is unclear whether the evidence warrants large-scale use in population-based screening.

AREAS COVERED

We performed a scoping review, a structured evidence synthesis describing a broad research field, to summarize knowledge on AI evaluated for BC detection and to assess AI's readiness for adoption in BC screening. Studies were predominantly small retrospective studies based on highly selected image datasets that contained a high proportion of cancers (median BC proportion in datasets 26.5%), and used heterogeneous techniques to develop AI models; the range of estimated AUC (area under ROC curve) for AI models was 69.2-97.8% (median AUC 88.2%). We identified various methodologic limitations including use of non-representative imaging data for model training, limited validation in external datasets, potential bias in training data, and few comparative data for AI versus radiologists' interpretation of mammography screening.

EXPERT OPINION

Although contemporary AI models have reported generally good accuracy for BC detection, methodological concerns, and evidence gaps exist that limit translation into clinical BC screening settings. These should be addressed in parallel to advancing AI techniques to render AI transferable to large-scale population-based screening.

A Deep Learning-Based Decision Support Tool for Precision Risk Assessment of Breast Cancer

PURPOSE

The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting to assess cancer risk and facilitate the decision to biopsy. Because of substantial interobserver variability in the application of the BI-RADS lexicon, the decision to biopsy varies greatly and results in overdiagnosis and excessive biopsies. The false-positive rate from mammograms is estimated to be 7% to approximately 10% overall, but within the BI-RADS 4 category, it is greater than 70%. Therefore, we developed the Breast Cancer Risk Calculator (BRISK) to target a well-characterized and specific patient subgroup (BI-RADS 4) rather than a broad heterogeneous group in assessing breast cancer risk.

METHODS

BRISK provides a novel precise risk assessment model to reduce overdiagnosis and unnecessary biopsies. It was developed by applying natural language processing and deep learning methods on 5,147 patient records archived in the Houston Methodist systemwide data warehouse from 2006 to May 2015, including imaging and pathology reports, mammographic images, and patient demographics. Key characteristics for BI-RADS 4 patients were collected and computed to output an index measure for biopsy recommendation that is clinically relevant and informative and improves upon the traditional BI-RADS 4 scores.

RESULTS

For the validation set, we assessed data from 1,247 BI-RADS 4 patients, including mammographic images and medical reports. The BRISK model sensitivity to predict malignancy was 100%, whereas the specificity was 74%. The total accuracy of our implemented model in BRISK was 81%. Overall area under the curve was 0.93.

CONCLUSION

BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy. Prospective evaluation is under way and can lead to improvement in patient-physician engagement in making informed decisions with regard to biopsy.

Can Contrast-Enhanced Ultrasound Increase or Predict the Success Rate of Testicular Sperm Aspiration in Patients With Azoospermia?

OBJECTIVE. The objective of our study was to determine whether contrast-enhanced ultrasound (CEUS) perfusion measurements obtained before testicular sperm aspiration (TESA) can improve or predict sperm retrieval (SR) outcomes of TESA in patients with azoospermia. SUBJECTS AND METHODS. Between May 2017 and January 2018, 70 patients with azoospermia (mean age, 29 years; age range, 22-41 years) underwent testes CEUS within 10 days before TESA. Major perfusion areas were visually chosen, and their ranges were recorded. The other areas were defined as minor perfusion. CEUS quantitative features were acquired for both the main perfusion area and whole testis. Testis tissue biopsies were taken for both major and minor perfusion areas by cognitive fusion, and SR outcomes were compared. Associations between testicular volume, quantitative CEUS features, and SR outcomes were analyzed. RESULTS. Twenty-four men were found to have obstructive azoospermia (OA), and the remaining 46 had nonobstructive azoospermia (NOA). All patients with OA had spermatozoa in biopsy. Only one patient with NOA had spermatozoa in the major perfusion area but not the minor perfusion area; the other patients with NOA had the same SR outcomes in both major and minor perfusion areas. In patients with NOA, both wash-in and washout CEUS features were correlated with the success of SR in TESA. CONCLUSION. CEUS-guided TESA with cognitive fusion cannot yield improved SR outcomes of TESA in patients with NOA, possibly because of imprecise correlation between biopsy sites and main perfusion area analyzed by CEUS; however, quantitative CEUS features can be useful predictors of the success of SR.

Testing the Utility of the Neural Network Model to Predict History of Arrest among Intimate Partner Violent Men

Risk assessments are typically based on retrospective reports of factors known to be correlated with violence recidivism in simple linear models. Generally, these linear models use only the perpetrators’ reports. Using a community sample of couples recruited for recent male-to-female intimate partner violence (IPV; N = 97 couples), the current study compared non-linear neural network models to traditional linear models in predicting a history of arrest in men who perpetrate IPV. The neural network models were found to be superior to the linear models in their predictive power. Models were slightly improved by adding victims’ report. These findings suggest that the prediction of violence arrest be enhanced through the use of neural network models and by including collateral reports.

Multiple Machine Learnings Revealed Similar Predictive Accuracy for Prognosis of PNETs from the Surveillance, Epidemiology, and End Result Database

Background: Prognosis prediction is indispensable in clinical practice and machine learning has been proved to be helpful. We expected to predict survival of pancreatic neuroendocrine tumors (PNETs) with machine learning, and compared it with the American Joint Committee on Cancer (AJCC) staging system.

Methods: Data of PNETs cases were extracted from The Surveillance, Epidemiology, and End Result (SEER) database. Statistic description, multivariate survival analysis and preprocessing were done before machine learning. Four different algorithms (logistic regression (LR), support vector machines (SVM), random forest (RF) and deep learning (DL)) were used to train the model. We used proper imputations to manage missing data in the database and sensitive analysis was performed to evaluate the imputation. The model with the best predictive accuracy was compared with the AJCC staging system using the SEER cases.

Results: The four models had similar predictive accuracy with no significant difference existed (p = 0.664). The DL model showed a slightly better predictive accuracy than others (81.6% (± 1.9%)), thus it was used for further comparison with the AJCC staging system and revealed a better performance for PNETs cases in SEER database (Area under receiver operating characteristic curve: 0.87 vs 0.76). The validity of missing data imputation was supported by sensitivity analysis.

Conclusions: The models developed with machine learning performed well in survival prediction of PNETs, and the DL model have a better accuracy and specificity than the AJCC staging system in SEER data. The DL model has potential for clinical application but external validation is needed.

Diagnostic Accuracy of Different Machine Learning Algorithms for Breast Cancer Risk Calculation: a Meta-Analysis

Objective: The aim of this study was to determine the diagnostic accuracy of different machine learning algorithms for breast cancer risk calculation. Methods: A meta-analysis was conducted of published research articles on diagnostic test accuracy of different machine learning algorithms for breast cancer risk calculation published between January 2000 and May 2018 in the online article databases of PubMed, ProQuest and EBSCO. Paired forest plots were employed for the analysis. Numerical values for sensitivity and specificity were obtained from false negative (FN), false positive (FP), true negative (TN) and true positive (TP) rates, presented alongside graphical representations with boxes marking the values and horizontal lines showing the confidence intervals (CIs). Summary receiver operating characteristic (SROC) curves were applied to assess the performance of diagnostic tests. Data were processed using Review Manager 5.3 (RevMan 5.3). Results: A total of 1,879 articles were reviewed, of which 11 were selected for systematic review and meta-analysis. Fve algorithms for machine learning able to predict breast cancer risk were identified: Super Vector Machine (SVM); Artificial Neural Networks (ANN); Decision Tree (DT); Naive Bayes (NB); and K-Nearest Neighbor (KNN). With the SVM, the Area Under Curve (AUC) from the SROC was > 90%, therefore classified into the excellent category. Conclusion: The meta-analysis confirmed that the SVM algorithm is able to calculate breast cancer risk with better accuracy value than other machine learning algorithms.

Assessing Breast Cancer Risk with an Artificial Neural Network

Objectives:

Radiologists face uncertainty in making decisions based on their judgment of breast cancer risk. Artificial intelligence and machine learning techniques have been widely applied in detection/recognition of cancer. This study aimed to establish a model to aid radiologists in breast cancer risk estimation. This incorporated imaging methods and fine needle aspiration biopsy (FNAB) for cyto-pathological diagnosis.

Methods:

An artificial neural network (ANN) technique was used on a retrospectively collected dataset including mammographic results, risk factors, and clinical findings to accurately predict the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance.

Result:

The network incorporating the selected features performed best (AUC = 0.955). Sensitivity and specificity of the ANN were respectively calculated as 0.82 and 0.90. In addition, negative and positive predictive values were respectively computed as 0.90 and 0.80.

Conclusion:

ANN has potential applications as a decision-support tool to help underperforming practitioners to improve the positive predictive value of biopsy recommendations.

Application of Genetic Programming (GP) Formalism for Building Disease Predictive Models from Protein-Protein Interactions (PPI) Data

Protein-protein interactions (PPIs) play a vital role in the biological processes involved in the cell functions and disease pathways. The experimental methods known to predict PPIs require tremendous efforts and the results are often hindered by the presence of a large number of false positives. Herein, we demonstrate the use of a new Genetic Programming (GP) based Symbolic Regression (SR) approach for predicting PPIs related to a disease. In a case study, a dataset consisting of one hundred and thirty five PPI complexes related to cancer was used to construct a generic PPI predicting model with good PPI prediction accuracy and generalization ability. A high correlation coefficient(CC) of 0.893, low root mean square error (RMSE) and mean absolute percentage error (MAPE) values of 478.221 and 0.239, respectively were achieved for both the training and test set outputs. To validate the discriminatory nature of the model, it was applied on a dataset of diabetes complexes where it yielded significantly low CC values. Thus, the GP model developed here serves a dual purpose: (a)a predictor of the binding energy of cancer related PPI complexes, and (b)a classifier for discriminating PPI complexes related to cancer from those of other diseases.

Prediction of high on-treatment platelet reactivity in clopidogrel-treated patients with acute coronary syndromes

BACKGROUND

About 40% of clopidogrel-treated patients display high platelet reactivity (HPR). Alternative treatments of HPR patients, identified by platelet function tests, failed to improve their clinical outcomes in large randomized clinical trials. A more appealing alternative would be to identify HPR patients a priori, based on the presence/absence of demographic, clinical and genetic factors that affect PR. Due to the complexity and multiplicity of these factors, traditional statistical methods (TSMs) fail to identify a priori HPR patients accurately. The objective was to test whether Artificial Neural Networks (ANNs) or other Machine Learning Systems (MLSs), which use algorithms to extract model-like 'structure' information from a given set of data, accurately predict platelet reactivity (PR) in clopidogrel-treated patients.

METHODS

A complete set of fifty-nine demographic, clinical, genetic data was available of 603 patients with acute coronary syndromes enrolled in the prospective GEPRESS study, which showed that HPR after 1month of clopidogrel treatment independently predicted adverse cardiovascular events in patients with Syntax Score >14. Data were analysed by MLSs and TSMs. ANNs identified more variables associated PR at 1month, compared to TSMs.

RESULTS

ANNs overall accuracy in predicting PR, although superior to other MLSs was 63% (95% CI 59-66). PR phenotype changed in both directions in 35% of patients across the 3 time points tested (before PCI, at hospital discharge and at 1month).

CONCLUSIONS

Despite their ability to analyse very complex non-linear phenomena, ANNs or MLS were unable to predict PR accurately, likely because PR is a highly unstable phenotype.

Lung cancer prediction from microarray data by gene expression programming

Lung cancer is a leading cause of cancer-related death worldwide. The early diagnosis of cancer has demonstrated to be greatly helpful for curing the disease effectively. Microarray technology provides a promising approach of exploiting gene profiles for cancer diagnosis. In this study, the authors propose a gene expression programming (GEP)-based model to predict lung cancer from microarray data. The authors use two gene selection methods to extract the significant lung cancer related genes, and accordingly propose different GEP-based prediction models. Prediction performance evaluations and comparisons between the authors' GEP models and three representative machine learning methods, support vector machine, multi-layer perceptron and radial basis function neural network, were conducted thoroughly on real microarray lung cancer datasets. Reliability was assessed by the cross-data set validation. The experimental results show that the GEP model using fewer feature genes outperformed other models in terms of accuracy, sensitivity, specificity and area under the receiver operating characteristic curve. It is concluded that GEP model is a better solution to lung cancer prediction problems.

Population-specific prognostic models are needed to stratify outcomes for African-Americans with diffuse large B-cell lymphoma

Diffuse large B-cell lymphoma (DLBCL) demonstrates significant racial differences in age of onset, stage, and survival. To examine whether population-specific models improve prediction of outcomes for African-American (AA) patients with DLBCL, we utilized Surveillance, Epidemiology, and End Results data and compared stratification by the international prognostic index (IPI) in general and AA populations. We also constructed and compared prognostic models for general and AA populations using multivariable logistic regression (LR) and artificial neural network approaches. While the IPI adequately stratified outcomes for the general population, it failed to separate AA DLBCL patients into distinct risk groups. Our AA LR model identified age ≥ 55 (odds ratio 0.45, [95% CI: 0.36, 0.56], male sex (0.75, [0.60, 0.93]), and stage III/IV disease (0.43, [0.34, 0.54]) as adverse predictors of 5-year survival for AA patients. In addition, general-population prognostic models were poorly calibrated for AAs with DLBCL, indicating a need for validated AA-specific prognostic models.

Predicting malignancy from mammography findings and image-guided core biopsies

The main goal of this work is to produce machine learning models that predict the outcome of a mammography from a reduced set of annotated mammography findings. In the study we used a dataset consisting of 348 consecutive breast masses that underwent image guided core biopsy performed between October 2005 and December 2007 on 328 female subjects. We applied various algorithms with parameter variation to learn from the data. The tasks were to predict mass density and to predict malignancy. The best classifier that predicts mass density is based on a support vector machine and has accuracy of 81.3%. The expert correctly annotated 70% of the mass densities. The best classifier that predicts malignancy is also based on a support vector machine and has accuracy of 85.6%, with a positive predictive value of 85%. One important contribution of this work is that our model can predict malignancy in the absence of the mass density attribute, since we can fill up this attribute using our mass density predictor.

Computational Discrimination of Breast Cancer for Korean Women Based on Epidemiologic Data Only

Breast cancer is the second leading cancer for Korean women and its incidence rate has been increasing annually. If early diagnosis were implemented with epidemiologic data, the women could easily assess breast cancer risk using internet. National Cancer Institute in the United States has released a Web-based Breast Cancer Risk Assessment Tool based on Gail model. However, it is inapplicable directly to Korean women since breast cancer risk is dependent on race. Also, it shows low accuracy (58%-59%). In this study, breast cancer discrimination models for Korean women are developed using only epidemiological case-control data (n = 4,574). The models are configured by different classification techniques: support vector machine, artificial neural network, and Bayesian network. A 1,000-time repeated random sub-sampling validation is performed for diverse parameter conditions, respectively. The performance is evaluated and compared as an area under the receiver operating characteristic curve (AUC). According to age group and classification techniques, AUC, accuracy, sensitivity, specificity, and calculation time of all models were calculated and compared. Although the support vector machine took the longest calculation time, the highest classification performance has been achieved in the case of women older than 50 yr (AUC = 64%). The proposed model is dependent on demographic characteristics, reproductive factors, and lifestyle habits without using any clinical or genetic test. It is expected that the model could be implemented as a web-based discrimination tool for breast cancer. This tool can encourage potential breast cancer prone women to go the hospital for diagnostic tests.

Machine learning applications in cancer prognosis and prediction

Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into high or low risk groups has led many research teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs) and Decision Trees (DTs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we present a review of recent ML approaches employed in the modeling of cancer progression. The predictive models discussed here are based on various supervised ML techniques as well as on different input features and data samples. Given the growing trend on the application of ML methods in cancer research, we present here the most recent publications that employ these techniques as an aim to model cancer risk or patient outcomes.

Comparison of new modeling methods for postnatal weight in ELBW infants using prenatal and postnatal data

OBJECTIVES

Postnatal infant weight curves are used to assess fluid management and evaluate postnatal nutrition and growth. Traditionally, postnatal weight curves are based on birth weight and do not incorporate postnatal clinical information. The aim of the present study was to compare the accuracy of birth weight-based weight curves with weight curves created from individual patient records, including electronic records, using 2 predictive modeling methods, linear regression (LR) and an artificial neural network (NN), which apply mathematical relations between predictor and outcome variables.

METHODS

Perinatal demographic and postnatal nutrition data were collected for extremely-low-birth-weight (ELBW; birth weight <1000 g) infants. Static weight curves were generated using published algorithms. The postnatal predictive models were created using the demographic and nutrition dataset.

RESULTS

Birth weight (861 ± 83 g, mean ± 1 standard deviation [SD]), gestational age (26.2 ± 1.4 weeks), and the first month of nutrition data were collected from individual health records for 92 ELBW infants. The absolute residual (|measured-predicted|) for weight was 84.8 ± 74.4 g for the static weight curves, 60.9 ± 49.1 g for the LR model, and 12.9 ± 9.2 g for the NN model, analysis of variance: both LR and NN P<0.01 versus static curve. NPO (nothing by mouth) infants had greater weight curve discrepancies.

CONCLUSIONS

Compared with birth weight-based and logistic regression-generated weight curves, NN-generated weight curves more closely approximated ELBW infant weight curves, and, using the present electronic health record systems, may produce weight curves better reflective of the patient's status.

A new hybrid case-based reasoning approach for medical diagnosis systems

Case-Based Reasoning (CBR) has been applied in many different medical applications. Due to the complexities and the diversities of this domain, most medical CBR systems become hybrid. Besides, the case adaptation process in CBR is often a challenging issue as it is traditionally carried out manually by domain experts. In this paper, a new hybrid case-based reasoning approach for medical diagnosis systems is proposed to improve the accuracy of the retrieval-only CBR systems. The approach integrates case-based reasoning and rule-based reasoning, and also applies the adaptation process automatically by exploiting adaptation rules. Both adaptation rules and reasoning rules are generated from the case-base. After solving a new case, the case-base is expanded, and both adaptation and reasoning rules are updated. To evaluate the proposed approach, a prototype was implemented and experimented to diagnose breast cancer and thyroid diseases. The final results show that the proposed approach increases the diagnosing accuracy of the retrieval-only CBR systems, and provides a reliable accuracy comparing to the current breast cancer and thyroid diagnosis systems.

Optimal Policies for Reducing Unnecessary Follow-up Mammography Exams in Breast Cancer Diagnosis

Mammography is the most effective screening tool for early diagnosis of breast cancer. Based on the mammography findings, radiologists need to choose from one of the following three alternatives: 1) take immediate diagnostic actions including prompt biopsy to confirm breast cancer; 2) recommend a follow-up mammogram; 3) recommend routine annual mammography. There are no validated structured guidelines based on a decision-analytical framework to aid radiologists in making such patient management decisions. Surprisingly, only 15-45% of the breast biopsies and less than 1% of short-interval follow-up recommendations are found to be malignant, resulting in unnecessary tests and patient-anxiety. We develop a finite-horizon discrete-time Markov decision process (MDP) model that may help radiologists make patient-management decisions to maximize a patient's total expected quality-adjusted life years. We use clinical data to find the policies recommended by the MDP model and also compare them to decisions made by radiologists at a large mammography practice. We also derive the structural properties of the MDP model, including sufficiency conditions that ensure the existence of a double control-limit type policy.