Classification and Disease Prediction Via Mathematical Programming

Lee, Eva K.; Wu, Tsung-Lin

doi:10.1007/978-0-387-09770-1_12

Cited by 13 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Incorporating medically significant risk factors has been a major challenge because the improvement of risk prediction has to be assessed and quantified appropriately 8 . Data mining techniques 9 10 and mathematical programming 11 have been used to discover predictive rules from medical and biological data to improve disease prediction. In addition, artificial neural networks have been used to predict osteoporosis 12 and cancer 13 .…”

mentioning

confidence: 99%

Predictability Bounds of Electronic Health Records

Dahlem

Maniloff

Ratti

2015

Sci Rep

View full text Add to dashboard Cite

The ability to intervene in disease progression given a person’s disease history has the potential to solve one of society’s most pressing issues: advancing health care delivery and reducing its cost. Controlling disease progression is inherently associated with the ability to predict possible future diseases given a patient’s medical history. We invoke an information-theoretic methodology to quantify the level of predictability inherent in disease histories of a large electronic health records dataset with over half a million patients. In our analysis, we progress from zeroth order through temporal informed statistics, both from an individual patient’s standpoint and also considering the collective effects. Our findings confirm our intuition that knowledge of common disease progressions results in higher predictability bounds than treating disease histories independently. We complement this result by showing the point at which the temporal dependence structure vanishes with increasing orders of the time-correlated statistic. Surprisingly, we also show that shuffling individual disease histories only marginally degrades the predictability bounds. This apparent contradiction with respect to the importance of time-ordered information is indicative of the complexities involved in capturing the health-care process and the difficulties associated with utilising this information in universal prediction algorithms.

show abstract

mentioning

confidence: 99%

Predictability Bounds of Electronic Health Records

Dahlem

Maniloff

Ratti

2015

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The recent work of Ayer et al (2012) begins to explore personalizing testing schedules incorporating risk factors and history of tests similarly to our work. Lee and Wu (2009) develop disease classification and prediction approaches using math programming.…”

Section: Current State Of Literaturementioning

confidence: 99%

Dynamic Forecasting and Control Algorithms of Glaucoma Progression for Clinician Decision Support

Helm

Lavieri

Oyen

et al. 2015

Operations Research

View full text Add to dashboard Cite

In managing chronic diseases such as glaucoma, the timing of periodic examinations is crucial, as it may significantly impact patients' outcomes. We address the question of when to monitor a glaucoma patient by integrating a dynamic, stochastic state space system model of disease evolution with novel optimization approaches to predict the likelihood of progression at any future time. Information about each patient's disease state is learned sequentially through a series of noisy medical tests. This information is used to determine the best time to next test based on each patient's individual disease trajectory as well as population information. We develop closed-form solutions and study structural properties of our algorithm. While some have proposed that fixed-interval monitoring can be improved upon, our methodology validates a sophisticated model-based approach to doing so. Based on data from two large-scale, 10+ years clinical trials, we show that our methods significantly outperform fixed-interval schedules and age-based threshold policies by achieving greater accuracy of identifying progression with fewer examinations. Although this work is motivated by our collaboration with glaucoma specialists, the methodology developed is applicable to a variety of chronic diseases.

show abstract

“…The focus of pattern classification is to recognize similarities in the data, categorizing them in di↵erent subsets [9,10,29]. In many fields, such as the financial and the medical ones [19,22], classification of data (samples in Machine Learning language) is useful for analysis or diagnosis purposes.…”

mentioning

confidence: 99%

“…the results of four di↵erent 97.22 6.00 9.00 92.00 92.00 92.00 96.74 97 22. 5.97 9.00 90.00 90.00 90.00 PIMA 76.30 77.62 8.30 26.25 100.00 100.00 100.00 76.30 77.62 8.30 26.25 100.00 100.00 100.00 HEART 84.37 86.83 7.27 12.31 100.00 100.00 100.00 84.37 86.83 7.27 12.31 100.00 100.00 100.00 IONO 88.91 95.46 43.35 50.29 93.82 93.82 93.82 88.90 95.43 43.28 50.00 89.71 89.71 89.71 LIVER 72.58 74.39 5.14 48.00 100.00 100.00 100.00 72.58 74.39 5.14 48.00 100.00 100.00 100.00 .80 9.00 80.00 80.00 80.00 96.42 97.14 5.73 17.00 68.00 68.00 68.00 PIMA 76.30 77.60 8.27 26.25 96.25 96.25 96.25 75.86 77.26 7.74 26.25 78.75 78.75 78.75 HEART 83.95 86.88 7.33 13.07 98.46 98.46 98.46 83.95 86.97 5.16 9.23 58.46 58.46 58.46 IONO 88.59 95.46 42.13 49.71 80.30 80.30 80.30 88.28 94.61 27.06 36.18 45.30 45.30 45.30 LIVER 72.58 74.39 5.14 48.00 98.00 98.00 98.00 71.10 74.05 4.45 52.00 68.00 68.00 68.00Table 4.4…”

mentioning

confidence: 99%

Lagrangian relaxation for SVM feature selection

Gaudioso

Gorgone

Labbé

et al. 2017

Computers & Operations Research

View full text Add to dashboard Cite

We discuss a Lagrangian-relaxation-based heuristics for dealing with feature selection in the Support Vector Machine (SVM) framework for binary classification. In particular we embed into our objective function a weighted combination of the L1 and L0 norm of the normal to the separating hyperplane. We come out with a Mixed Binary Linear Programming problem which is suitable for a Lagrangian relaxation approach. Based on a property of the optimal multiplier setting, we apply a consolidated nonsmooth optimization ascent algorithm to solve the resulting Lagrangian dual. In the proposed approach we get, at every ascent step, both a lower bound on the optimal solution as well as a feasible solution at low computational cost. We present the results of our numerical experiments on some benchmark datasets

show abstract

Classification and Disease Prediction Via Mathematical Programming

Cited by 13 publications

References 0 publications

Predictability Bounds of Electronic Health Records

Predictability Bounds of Electronic Health Records

Dynamic Forecasting and Control Algorithms of Glaucoma Progression for Clinician Decision Support

Lagrangian relaxation for SVM feature selection

Contact Info

Product

Resources

About