Improving personalized tumor growth predictions using a Bayesian combination of mechanistic modeling and machine learning

Abstract Background In clinical practice, a plethora of medical examinations are conducted to assess the state of a patient’s pathology producing a variety of clinical data. However, investigation of these data faces two major challenges. Firstly, we lack the knowledge of the mechanisms involved in regulating these data variables, and secondly, data collection is sparse in time since it relies on patient’s clinical presentation. The former limits the predictive accuracy of clinical outcomes for any mechanistic model. The latter restrains any machine learning algorithm to accurately infer the corresponding disease dynamics. Methods Here, we propose a novel method, based on the Bayesian coupling of mathematical modeling and machine learning, aiming at improving individualized predictions by addressing the aforementioned challenges. Results We evaluate the proposed method on a synthetic dataset for brain tumor growth and analyze its performance in predicting two relevant clinical outputs. The method results in improved predictions in almost all simulated patients, especially for those with a late clinical presentation (>95% patients show improvements compared to standard mathematical modeling). In addition, we test the methodology in two additional settings dealing with real patient cohorts. In both cases, namely cancer growth in chronic lymphocytic leukemia and ovarian cancer, predictions show excellent agreement with reported clinical outcomes (around 60% reduction of mean squared error). Conclusions We show that the combination of machine learning and mathematical modeling approaches can lead to accurate predictions of clinical outputs in the context of data sparsity and limited knowledge of disease mechanisms.

Download Full-text

Bayesian combination of mechanistic modeling and machine learning (BaM3): improving clinical tumor growth predictions

10.1101/2020.05.06.080242 ◽

2020 ◽

Author(s):

Pietro Mascheroni ◽

Symeon Savvopoulos ◽

Juan Carlos López Alfonso ◽

Michael Meyer-Hermann ◽

Haralampos Hatzikirou

Keyword(s):

Mathematical Modeling ◽

Machine Learning ◽

Tumor Growth ◽

Predictive Accuracy ◽

Tumor Burden ◽

Mechanistic Modeling ◽

Lymphocytic Leukemia ◽

Simulated Patients ◽

Small Subset ◽

Reported Data

AbstractBiomedical problems are highly complex and multidimensional. Commonly, only a small subset of the relevant variables can be modeled by virtue of mathematical modeling due to lack of knowledge of the involved phenomena. Although these models are effective in analyzing the approximate dynamics of the system, their predictive accuracy is generally limited. On the other hand, statistical learning methods are well-suited for quantitative reproduction of data, but they do not provide mechanistic understanding of the investigated problem. Herein, we propose a novel method, based on the Bayesian coupling of mathematical modeling and machine learning (BaM3). We evaluate the proposed BaM3 method on a synthetic dataset for brain tumor growth as a proof of concept and analyze its performance in predicting two major clinical outputs, namely tumor burden and infiltration. Combining these two approaches results in improved predictions in almost all simulated patients, especially for those with a late clinical presentation. In addition, we test the proposed methodology on a set of patients suffering from Chronic Lymphocytic Leukemia (CLL) and show excellent agreement with reported data.

Download Full-text

An Integrated Approach of Mechanistic-Modeling and Machine-Learning for Thickness Optimization of Frozen Microwaveable Foods

Foods ◽

10.3390/foods10040763 ◽

2021 ◽

Vol 10 (4) ◽

pp. 763

Author(s):

Ran Yang ◽

Zhenbo Wang ◽

Jiajia Chen

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

Food Product ◽

Integrated Approach ◽

Mechanistic Modeling ◽

Bayesian Optimization ◽

Initial Training ◽

Thickness Optimization ◽

Heating Uniformity ◽

Food Design

Mechanistic-modeling has been a useful tool to help food scientists in understanding complicated microwave-food interactions, but it cannot be directly used by the food developers for food design due to its resource-intensive characteristic. This study developed and validated an integrated approach that coupled mechanistic-modeling and machine-learning to achieve efficient food product design (thickness optimization) with better heating uniformity. The mechanistic-modeling that incorporated electromagnetics and heat transfer was previously developed and validated extensively and was used directly in this study. A Bayesian optimization machine-learning algorithm was developed and integrated with the mechanistic-modeling. The integrated approach was validated by comparing the optimization performance with a parametric sweep approach, which is solely based on mechanistic-modeling. The results showed that the integrated approach had the capability and robustness to optimize the thickness of different-shape products using different initial training datasets with higher efficiency (45.9% to 62.1% improvement) than the parametric sweep approach. Three rectangular-shape trays with one optimized thickness (1.56 cm) and two non-optimized thicknesses (1.20 and 2.00 cm) were 3-D printed and used in microwave heating experiments, which confirmed the feasibility of the integrated approach in thickness optimization. The integrated approach can be further developed and extended as a platform to efficiently design complicated microwavable foods with multiple-parameter optimization.

Download Full-text

Application of a Rough Set-Based Inductive Learning System

Fundamenta Informaticae ◽

10.3233/fi-1993-182-409 ◽

1993 ◽

Vol 18 (2-4) ◽

pp. 209-220

Author(s):

Michael Hadjimichael ◽

Anita Wasilewska

Keyword(s):

Machine Learning ◽

Rough Set ◽

Presidential Election ◽

Predictive Accuracy ◽

Learning Algorithm ◽

Inductive Learning ◽

Real Data ◽

Semantic Content ◽

Learning System ◽

Voter Preferences

We present here an application of Rough Set formalism to Machine Learning. The resulting Inductive Learning algorithm is described, and its application to a set of real data is examined. The data consists of a survey of voter preferences taken during the 1988 presidential election in the U.S.A. Results include an analysis of the predictive accuracy of the generated rules, and an analysis of the semantic content of the rules.

Download Full-text

Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks

Advances in Fuzzy Systems ◽

10.1155/2020/8581202 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Peter Appiahene ◽

Yaw Marfo Missah ◽

Ussiph Najim

Keyword(s):

Machine Learning ◽

Random Forest ◽

Decision Tree ◽

Banking Sector ◽

Banking Industry ◽

Predictive Accuracy ◽

Learning Algorithm ◽

Machine Learning Algorithms ◽

Machine Learning Algorithm ◽

And Performance

The financial crisis that hit Ghana from 2015 to 2018 has raised various issues with respect to the efficiency of banks and the safety of depositors’ in the banking industry. As part of measures to improve the banking sector and also restore customers’ confidence, efficiency and performance analysis in the banking industry has become a hot issue. This is because stakeholders have to detect the underlying causes of inefficiencies within the banking industry. Nonparametric methods such as Data Envelopment Analysis (DEA) have been suggested in the literature as a good measure of banks’ efficiency and performance. Machine learning algorithms have also been viewed as a good tool to estimate various nonparametric and nonlinear problems. This paper presents a combined DEA with three machine learning approaches in evaluating bank efficiency and performance using 444 Ghanaian bank branches, Decision Making Units (DMUs). The results were compared with the corresponding efficiency ratings obtained from the DEA. Finally, the prediction accuracies of the three machine learning algorithm models were compared. The results suggested that the decision tree (DT) and its C5.0 algorithm provided the best predictive model. It had 100% accuracy in predicting the 134 holdout sample dataset (30% banks) and a P value of 0.00. The DT was followed closely by random forest algorithm with a predictive accuracy of 98.5% and a P value of 0.00 and finally the neural network (86.6% accuracy) with a P value 0.66. The study concluded that banks in Ghana can use the result of this study to predict their respective efficiencies. All experiments were performed within a simulation environment and conducted in R studio using R codes.

Download Full-text

Amyloid PET-Positive Predictability of Machine Learning Algorithm Based on MDS-OAβ Levels

10.21203/rs.3.rs-578834/v1 ◽

2021 ◽

Author(s):

Young Chul Youn ◽

Jung-Min Pyun ◽

Hye Ryoun Kim ◽

Sungmin Kang ◽

Nayoung Ryoo ◽

...

Keyword(s):

Machine Learning ◽

Predictive Accuracy ◽

Learning Algorithm ◽

Detection System ◽

Amyloid Β ◽

Machine Learning Algorithms ◽

Amyloid Pet ◽

Amyloid Positron Emission Tomography ◽

Positron Emission ◽

Negative Findings

Abstract Background: The Multimer Detection System-Oligomeric amyloid-β (MDS-OAβ) level is a valuable blood-based biomarker for Alzheimer’s disease (AD). We used machine learning algorithms trained using multi-center datasets to examine whether blood MDS-OAβ values can predict AD-associated changes in the brain.Methods: A logistic regression model using TensorFlow (ver. 2.3.0) was applied to data obtained from 163 participants (amyloid positron emission tomography [PET]-positive and -negative findings in 102 and 61 participants, respectively). Algorithms with various combinations of features (MDS-OAβ levels, age, gender, and anticoagulant type) were tested 50 times on each dataset. Results: The predictive accuracy, sensitivity, and specificity values of blood MDS-OAβ levels for amyloid PET positivity were 78.16±4.97%, 83.87±9.40%, and 70.00±13.13%, respectively.Conclusions: The findings from this multi-center machine learning-based study suggest that MDS-OAβ values may be used to predict amyloid PET-positivity.

Download Full-text

Application of machine learning algorithm for predicting gestational diabetes mellitus in early pregnancy†

Frontiers of Nursing ◽

10.2478/fon-2021-0022 ◽

2021 ◽

Vol 8 (3) ◽

pp. 209-221

Author(s):

Li-Li Wei ◽

Yue-Shuai Pan ◽

Yan Zhang ◽

Kai Chen ◽

Hao-Yu Wang ◽

...

Keyword(s):

Diabetes Mellitus ◽

Machine Learning ◽

Random Forest ◽

Prediction Model ◽

Predictive Accuracy ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Random Forest Algorithm ◽

Random Forest Regression ◽

Data Set

Abstract Objective To study the application of a machine learning algorithm for predicting gestational diabetes mellitus (GDM) in early pregnancy. Methods This study identified indicators related to GDM through a literature review and expert discussion. Pregnant women who had attended medical institutions for an antenatal examination from November 2017 to August 2018 were selected for analysis, and the collected indicators were retrospectively analyzed. Based on Python, the indicators were classified and modeled using a random forest regression algorithm, and the performance of the prediction model was analyzed. Results We obtained 4806 analyzable data from 1625 pregnant women. Among these, 3265 samples with all 67 indicators were used to establish data set F1; 4806 samples with 38 identical indicators were used to establish data set F2. Each of F1 and F2 was used for training the random forest algorithm. The overall predictive accuracy of the F1 model was 93.10%, area under the receiver operating characteristic curve (AUC) was 0.66, and the predictive accuracy of GDM-positive cases was 37.10%. The corresponding values for the F2 model were 88.70%, 0.87, and 79.44%. The results thus showed that the F2 prediction model performed better than the F1 model. To explore the impact of sacrificial indicators on GDM prediction, the F3 data set was established using 3265 samples (F1) with 38 indicators (F2). After training, the overall predictive accuracy of the F3 model was 91.60%, AUC was 0.58, and the predictive accuracy of positive cases was 15.85%. Conclusions In this study, a model for predicting GDM with several input variables (e.g., physical examination, past history, personal history, family history, and laboratory indicators) was established using a random forest regression algorithm. The trained prediction model exhibited a good performance and is valuable as a reference for predicting GDM in women at an early stage of pregnancy. In addition, there are certain requirements for the proportions of negative and positive cases in sample data sets when the random forest algorithm is applied to the early prediction of GDM.

Download Full-text

Surgical skill assessment using machine learning algorithms

British Journal of Surgery ◽

10.1093/bjs/znab202.093 ◽

2021 ◽

Vol 108 (Supplement_4) ◽

Author(s):

J L Lavanchy ◽

J Zindel ◽

K Kirtac ◽

I Twick ◽

E Hosgor ◽

...

Keyword(s):

Machine Learning ◽

Clinical Outcomes ◽

Learning Algorithm ◽

Learning Algorithms ◽

Movement Patterns ◽

Surgical Skills ◽

Machine Learning Algorithms ◽

Skill Assessment ◽

Surgical Skill ◽

Surgical Skill Assessment

Abstract Objective Surgical skill is correlated with clinical outcomes. Therefore, the assessment of surgical skill is of major importance to improve clinical outcomes and increase patient safety. However, surgical skill assessment often lacks objectivity and reproducibility. Furthermore, it is time-consuming and expensive. Therefore, we developed an automated surgical skill assessment using machine learning algorithms. Methods Surgical skills were assessed in videos of laparoscopic cholecystectomy using a three-step machine learning algorithm. First, a three-dimensional convolutional neural network was trained to localize and classify the instruments within the videos. Second, movement patterns of the instruments were recorded over time and extracted. Third, the movement patterns were correlated with human surgical skill ratings using a linear regression model to predict surgical skill ratings automatically. Machine ratings were compared against human ratings of four board certified surgeons using a score ranging from 1 (poor skills) to 5 (excellent skills). Results Human raters and machine learning algorithms assessed surgical skills in 242 videos. Inter-rater reliability for human raters was excellent (79%, 95%CI 72-85%). Instrument detection showed an average precision of 78% and average recall of 82%. Machine learning algorithms showed an 87% accuracy in predicting good or poor surgical skills, when compared to human raters. Conclusion Machine learning algorithms can be trained to distinguish good and poor surgical skills with high accuracy. This work was published in Sci Rep 11, 5197 (2021). https://doi.org/10.1038/s41598-021-84295-6

Download Full-text

Predicting Tumor Growth and Ligand Dependence from mRNA by Combining Machine Learning with Mechanistic Modeling

10.1007/7653_2018_29 ◽

2018 ◽

Author(s):

Helge Hass ◽

Andreas Raue

Keyword(s):

Machine Learning ◽

Tumor Growth ◽

Mechanistic Modeling

Download Full-text

Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: a prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals

BMJ Health & Care Informatics ◽

10.1136/bmjhci-2019-100109 ◽

2020 ◽

Vol 27 (1) ◽

pp. e100109 ◽

Cited By ~ 1

Author(s):

Hoyt Burdick ◽

Eduardo Pino ◽

Denise Gabel-Comeau ◽

Andrea McCoy ◽

Carol Gu ◽

...

Keyword(s):

Machine Learning ◽

Severe Sepsis ◽

Length Of Stay ◽

Hospital Mortality ◽

Clinical Outcomes ◽

Real World ◽

Learning Algorithm ◽

Hospital Length ◽

Hospital Length Of Stay ◽

Machine Learning Algorithm

BackgroundSevere sepsis and septic shock are among the leading causes of death in the USA. While early prediction of severe sepsis can reduce adverse patient outcomes, sepsis remains one of the most expensive conditions to diagnose and treat.ObjectiveThe purpose of this study was to evaluate the effect of a machine learning algorithm for severe sepsis prediction on in-hospital mortality, hospital length of stay and 30-day readmission.DesignProspective clinical outcomes evaluation.SettingEvaluation was performed on a multiyear, multicentre clinical data set of real-world data containing 75 147 patient encounters from nine hospitals across the continental USA, ranging from community hospitals to large academic medical centres.ParticipantsAnalyses were performed for 17 758 adult patients who met two or more systemic inflammatory response syndrome criteria at any point during their stay (‘sepsis-related’ patients).InterventionsMachine learning algorithm for severe sepsis prediction.Outcome measuresIn-hospital mortality, length of stay and 30-day readmission rates.ResultsHospitals saw an average 39.5% reduction of in-hospital mortality, a 32.3% reduction in hospital length of stay and a 22.7% reduction in 30-day readmission rate for sepsis-related patient stays when using the machine learning algorithm in clinical outcomes analysis.ConclusionsReductions of in-hospital mortality, hospital length of stay and 30-day readmissions were observed in real-world clinical use of the machine learning-based algorithm. The predictive algorithm may be successfully used to improve sepsis-related outcomes in live clinical settings.Trial registration numberNCT03960203

Download Full-text

Iterative Reweighted Noninteger Norm Regularizing SVM for Gene Expression Data Classification

Computational and Mathematical Methods in Medicine ◽

10.1155/2013/768404 ◽

2013 ◽

Vol 2013 ◽

pp. 1-10 ◽

Cited By ~ 5

Author(s):

Jianwei Liu ◽

Shuang Cheng Li ◽

Xionglin Luo

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Adaptive Learning ◽

Predictive Accuracy ◽

Learning Algorithm ◽

Training Dataset ◽

Support Vector ◽

Data Set ◽

Cancer Data ◽

Public Data

Support vector machine is an effective classification and regression method that uses machine learning theory to maximize the predictive accuracy while avoiding overfitting of data.L2regularization has been commonly used. If the training dataset contains many noise variables,L1regularization SVM will provide a better performance. However, bothL1andL2are not the optimal regularization method when handing a large number of redundant values and only a small amount of data points is useful for machine learning. We have therefore proposed an adaptive learning algorithm using the iterative reweightedp-norm regularization support vector machine for 0 <p≤ 2. A simulated data set was created to evaluate the algorithm. It was shown that apvalue of 0.8 was able to produce better feature selection rate with high accuracy. Four cancer data sets from public data banks were used also for the evaluation. All four evaluations show that the new adaptive algorithm was able to achieve the optimal prediction error using apvalue less thanL1norm. Moreover, we observe that the proposedLppenalty is more robust to noise variables than theL1andL2penalties.

Download Full-text