Using concept hierarchies to improve calculation of patient similarity.

OBJECTIVE: We introduce a new distance measure that is better suited than traditional methods at detecting similarities in patient records by referring to a concept hierarchy. MATERIALS AND METHODS: The new distance measure improves on distance measures for categorical values by taking the path distance between concepts in a hierarchy into account. We evaluate and compare the new measure on a data set of 836 patients. RESULTS: The new measure shows marked improvements over the standard measures, both qualitatively and quantitatively. Using the new measure for clustering patient data reveals structure that is otherwise not visible. Statistical comparisons of distances within patient groups with similar diagnoses shows that the new measure is significantly better at detecting these similarities than the standard measures. CONCLUSION: The new distance measure is an improvement over the current standard whenever a hierarchical arrangement of categorical values is available.

cFinder: definition and quantification of multiple haplotypes in a mixed sample.

BACKGROUND: Next-generation sequencing allows for determining the genetic composition of a mixed sample. For instance, when performing resistance testing for BCR-ABL1 it is necessary to identify clones and define compound mutations; together with an exact quantification this may complement diagnosis and therapy decisions with additional information. Moreover, that applies not only to oncological issues but also determination of viral, bacterial or fungal infection. The efforts to retrieve multiple haplotypes (more than two) and proportion information from data with conventional software are difficult, cumbersome and demand multiple manual steps. RESULTS: Therefore, we developed a tool called cFinder that is capable of automatic detection of haplotypes and their accurate quantification within one sample. BCR-ABL1 samples containing multiple clones were used for testing and our cFinder could identify all previously found clones together with their abundance and even refine some results. Additionally, reads were simulated using GemSIM with multiple haplotypes, the detection was very close to linear (R(2) = 0.96). Our aim is not to deduce haploblocks over statistics, but to characterize one sample's composition precisely. As a result the cFinder reports the connections of variants (haplotypes) with their readcount and relative occurrence (percentage). Download is available at http://sourceforge.net/projects/cfinder/. CONCLUSIONS: Our cFinder is implemented in an efficient algorithm that can be run on a low-performance desktop computer. Furthermore, it considers paired-end information (if available) and is generally open for any current next-generation sequencing technology and alignment strategy. To our knowledge, this is the first software that enables researchers without extensive bioinformatic support to designate multiple haplotypes and how they constitute to a sample.

A prospective study of mobile phones for dermatology in a clinical setting.

We evaluated the accuracy of diagnoses made from pictures taken with the built-in cameras of mobile phones in a 'real-life' clinical setting. A total of 263 patients took part, who photographed their own lesions where possible, and provided clinical information via a questionnaire. After the teledermatology procedure, each patient was examined face-to-face and a gold standard diagnosis was made. The telemedicine data and pictures were diagnosed by 15 dermatologists. The 299 cases contained 1-22 clinical images each (median 3). Nine dermatologists finished all the cases and the remaining six completed some of them, thus providing 2893 decisions. Overall, 61% of all cases were rated as possible to diagnose and of those, 80% were correct in comparison with the face-to-face diagnosis. Image quality was evaluated and the median was 5 on a 10-point scale. There was a significant correlation between the correct diagnosis and the quality of the photographs taken (P < 0.001). In nearly two-thirds of all cases, a teledermatology diagnosis was possible; however, there was insufficient information to make a telemedicine diagnosis in about one-third of the cases. If applied carefully, mobile phones could be a powerful tool for people to optimize their health care status.

The CHOP postnatal weight gain, birth weight, and gestational age retinopathy of prematurity risk model.

OBJECTIVE: To develop a birth weight (BW), gestational age (GA), and postnatal-weight gain retinopathy of prematurity (ROP) prediction model in a cohort of infants meeting current screening guidelines. METHODS: Multivariate logistic regression was applied retrospectively to data from infants born with BW less than 1501 g or GA of 30 weeks or less at a single Philadelphia hospital between January 1, 2004, and December 31, 2009. In the model, BW, GA, and daily weight gain rate were used repeatedly each week to predict risk of Early Treatment of Retinopathy of Prematurity type 1 or 2 ROP. If risk was above a cut-point level, examinations would be indicated. RESULTS: Of 524 infants, 20 (4%) had type 1 ROP and received laser treatment; 28 (5%) had type 2 ROP. The model (Children's Hospital of Philadelphia [CHOP]) accurately predicted all infants with type 1 ROP; missed 1 infant with type 2 ROP, who did not require laser treatment; and would have reduced the number of infants requiring examinations by 49%. Raising the cut point to miss one type 1 ROP case would have reduced the need for examinations by 79%. Using daily weight measurements to calculate weight gain rate resulted in slightly higher examination reduction than weekly measurements. CONCLUSIONS: The BW-GA-weight gain CHOP ROP model demonstrated accurate ROP risk assessment and a large reduction in the number of ROP examinations compared with current screening guidelines. As a simple logistic equation, it can be calculated by hand or represented as a nomogram for easy clinical use. However, larger studies are needed to achieve a highly precise estimate of sensitivity prior to clinical application.

Differences in examination characteristics of pigmented skin lesions: results of an eye tracking study.

OBJECTIVE: To use computer-based eye tracking technology to record and evaluate examination characteristics of the diagnosis of pigmented skin lesions. METHODOLOGY: 16 study participants with varying levels of diagnostic expertise (little, intermediate, superior) were recorded while diagnosing a series of 28 digital images of pigmented skin lesions, obtained by non-invasive digital dermatoscopy, on a computer screen. Eye tracking hardware recorded the gaze track and fixations of the physicians while they examined the lesion images. Analysis of variance was used to test for differences in examination characteristics between physicians grouped according to expertise. RESULTS: There were no significant differences between physicians with little and intermediate levels of expertise in terms of average time until diagnosis (6.61 vs. 6.19s), gaze track length (6.65 vs. 6.15 kilopixels), number of fixations (23.1 vs. 19.1), and time in fixations (4.91 vs. 4.17s). The experts were significantly different with 3.17s time until diagnosis, 4.53 kilopixels gaze track length, 9.9 fixations, and 1.74s in fixations, respectively. Differentiation between benign and malignant lesions had no effect on examination measurements. CONCLUSION: The results show that experience level has a significant impact on the way in which lesion images are examined. This finding can be used to construct decision support systems that employ important diagnostic features identified by experts, and to optimize teaching for less experienced physicians.

Testing the calibration of classification models from first principles.

The accurate assessment of the calibration of classification models is severely limited by the fact that there is no easily available gold standard against which to compare a model's outputs. The usual procedures group expected and observed probabilities, and then perform a χ(2) goodness-of-fit test. We propose an entirely new approach to calibration testing that can be derived directly from the first principles of statistical hypothesis testing. The null hypothesis is that the model outputs are correct, i.e., that they are good estimates of the true unknown class membership probabilities. Our test calculates a p-value by checking how (im)probable the observed class labels are under the null hypothesis. We demonstrate by experiments that our proposed test performs comparable to, and sometimes even better than, the Hosmer-Lemeshow goodness-of-fit test, the de facto standard in calibration assessment.

A clinical prediction model to stratify retinopathy of prematurity risk using postnatal weight gain.

OBJECTIVE: To develop an efficient clinical prediction model that includes postnatal weight gain to identify infants at risk of developing severe retinopathy of prematurity (ROP). Under current birth weight (BW) and gestational age (GA) screening criteria, <5% of infants examined in countries with advanced neonatal care require treatment. PATIENTS AND METHODS: This study was a secondary analysis of prospective data from the Premature Infants in Need of Transfusion Study, which enrolled 451 infants with a BW < 1000 g at 10 centers. There were 367 infants who remained after excluding deaths (82) and missing weights (2). Multivariate logistic regression was used to predict severe ROP (stage 3 or treatment). RESULTS: Median BW was 800 g (445-995). There were 67 (18.3%) infants who had severe ROP. The model included GA, BW, and daily weight gain rate. Run weekly, an alarm that indicated need for eye examinations occurred when the predicted probability of severe ROP was >0.085. This identified 66 of 67 severe ROP infants (sensitivity of 99% [95% confidence interval: 94%-100%]), and all 33 infants requiring treatment. Median alarm-to-outcome time was 10.8 weeks (range: 1.9-17.6). There were 110 (30%) infants who had no alarm. Nomograms were developed to determine risk of severe ROP by BW, GA, and postnatal weight gain. CONCLUSION: In a high-risk cohort, a BW-GA-weight-gain model could have reduced the need for examinations by 30%, while still identifying all infants requiring laser surgery. Additional studies are required to determine whether including larger-BW, lower-risk infants would reduce examinations further and to validate the prediction model and nomograms before clinical use.

An evaluation of heuristics for rule ranking.

OBJECTIVE: To evaluate and compare the performance of different rule-ranking algorithms for rule-based classifiers on biomedical datasets. METHODOLOGY: Empirical evaluation of five rule ranking algorithms on two biomedical datasets, with performance evaluation based on ROC analysis and 5 × 2 cross-validation. RESULTS: On a lung cancer dataset, the area under the ROC curve (AUC) of, on average, 14267.1 rules was 0.862. Multi-rule ranking found 13.3 rules with an AUC of 0.852. Four single-rule ranking algorithms, using the same number of rules, achieved average AUC values of 0.830, 0.823, 0.823, and 0.822, respectively. On a prostate cancer dataset, an average of 339265.3 rules had an AUC of 0.934, while 9.4 rules obtained from multi-rule and single-rule rankings had average AUCs of 0.932, 0.926, 0.925, 0.902 and 0.902, respectively. CONCLUSION: Multi-variate rule ranking performs better than the single-rule ranking algorithms. Both single-rule and multi-rule methods are able to substantially reduce the number of rules while keeping classification performance at a level comparable to the full rule set.

Effect of data combination on predictive modeling: a study using gene expression data.

BACKGROUND: The quality of predictive modeling in biomedicine depends on the amount of data available for model building. OBJECTIVE: To study the effect of combining microarray data sets on feature selection and predictive modeling performance. METHODS: Empirical evaluation of stability of feature selection and discriminatory power of classifiers using three previously published gene expression data sets, analyzed both individually and in combination. RESULTS: Feature selection was not robust for the individual as well as for the combined data sets. The classification performance of models built on individual and combined data sets was heavily dependent on the data set from which the features were extracted. CONCLUSION: We identified volatility of feature selection as contributing factor to some of the problems faced by predictive modeling using microarray data.

Outlier Detection with One-Class SVMs: An Application to Melanoma Prognosis.

BACKGROUND: Medical diagnosis and prognosis using machine learning methods is usually represented as a supervised classification problem, where a model is built to distinguish "normal" from "abnormal" cases. If cases are available from only one class, this approach is not feasible. OBJECTIVE: To evaluate the performance of classification via outlier detection by one-class support vector machines (SVMs) as a means of identifying abnormal cases in the domain of melanoma prognosis. METHODS: Empirical evaluation of one-class SVMs on a data set for predicting the presence or absence of metastases in melanoma patients, and comparison with regular SVMs and artificial neural networks. RESULTS: One-class SVMs achieve an area under the ROC curve (AUC) of 0.71; two-class algorithms achieve AUCs between 0.5 and 0.84, depending on the available number of cases from the minority class. CONCLUSION: One-class SVMs offer a viable alternative to two-class classification algorithms if class distribution is heavily imbalanced.

Computer versus human diagnosis of melanoma: evaluation of the feasibility of an automated diagnostic system in a prospective clinical trial.

The aim of this study was to evaluate the accuracy of a computer-based system for the automated diagnosis of melanoma in the hands of nonexpert physicians. We performed a prospective comparison between nonexperts using computer assistance and experts without assistance in the setting of a tertiary referral center at a University hospital. Between February and November 2004 we enrolled 511 consecutive patients. Each patient was examined by two nonexpert physicians with low to moderate diagnostic skills who were allowed to use a neural network-based diagnostic system at their own discretion. Every patient was also examined by an expert dermatologist using standard dermatoscopy equipment. The nonexpert physicians used the automatic diagnostic system in 3827 pigmented skin lesions. In their hands, the system achieved a sensitivity of 72% and a specificity of 82%. The sensitivity was significantly lower than that of the expert physician (72 vs. 96%, P = 0.001), whereas the specificity was significantly higher (82 vs. 72%, P<0.01). Three melanomas were missed because the physicians who operated the system did not choose them for examination. The system as a stand-alone device had an average discriminatory power of 0.87, as measured by the area under the receiver operating characteristic curve, with optimal sensitivities and specificities of 75 and 84%, respectively. The diagnostic accuracy achieved in this clinical trial was lower than that achieved in a previous experimental trial of the same system. In total, the performance of a decision-support system for melanoma diagnosis under real-life conditions is lower than that expected from experimental data and depends upon the physicians who are using the system.

Improving calibration of logistic regression models by local estimates.

OBJECTIVE: To improve the calibration of logistic regression (LR) estimates using local information. BACKGROUND: Individualized risk assessment tools are increasingly being utilized. External validation of these tools often reveals poor model calibration. METHODS: We combine a clustering algorithm with an LR model to produce probability estimates that are close to the true probabilities for a particular case. The new method is compared to a standard LR model in terms of calibration, as measured by the sum of absolute differences (SAD) between model estimates and true probabilities, and discrimination, as measured by area under the ROC curve (AUC). RESULTS: We evaluate the new method on two synthetic data sets. SADs are significantly lower (p < 0.0001) in both data sets, and AUCs are significantly higher in one data set (p < 0.01). CONCLUSION: The results suggest that the proposed method may be useful to improve the calibration of LR models.

A new rule-based algorithm for identifying metabolic markers in prostate cancer using tandem mass spectrometry.

MOTIVATION: Prostate cancer is the most prevalent tumor in males and its incidence is expected to increase as the population ages. Prostate cancer is treatable by excision if detected at an early enough stage. The challenges of early diagnosis require the discovery of novel biomarkers and tools for prostate cancer management. RESULTS: We developed a novel feature selection algorithm termed as associative voting (AV) for identifying biomarker candidates in prostate cancer data measured via targeted metabolite profiling MS/MS analysis. We benchmarked our algorithm against two standard entropy-based and correlation-based feature selection methods [Information Gain (IG) and ReliefF (RF)] and observed that, on a variety of classification tasks in prostate cancer diagnosis, our algorithm identified subsets of biomarker candidates that are both smaller and show higher discriminatory power than the subsets identified by IG and RF. A literature study confirms that the highest ranked biomarker candidates identified by AV have independently been identified as important factors in prostate cancer development. AVAILABILITY: The algorithm can be downloaded from the following http://biomed.umit.at/page.cfm?pageid=516.

Applying a decision support system in clinical practice: results from melanoma diagnosis.

The work reported in this paper investigates the use of a decision-support tool for the diagnosis of pigmented skin lesions in a real-world clinical trial with 511 patients and 3827 lesion evaluations. We analyzed a number of outcomes of the trial, such as direct comparison of system performance in laboratory and clinical setting, the performance of physicians using the system compared to a control dermatologist without the system, and repeatability of system recommendations. The results show that system performance was significantly less in the real-world setting compared to the laboratory setting (c-index of 0.87 vs. 0.94, p = 0.01). Dermatologists using the system achieved a combined sensitivity of 85% and combined specificity of 95%. We also show that the process of acquiring lesion images using digital dermoscopy devices needs to be standardized before sufficiently high repeatability of measurements can be assured.

Approximation properties of haplotype tagging.

BACKGROUND: Single nucleotide polymorphisms (SNPs) are locations at which the genomic sequences of population members differ. Since these differences are known to follow patterns, disease association studies are facilitated by identifying SNPs that allow the unique identification of such patterns. This process, known as haplotype tagging, is formulated as a combinatorial optimization problem and analyzed in terms of complexity and approximation properties. RESULTS: It is shown that the tagging problem is NP-hard but approximable within 1 + ln((n2 - n)/2) for n haplotypes but not approximable within (1-epsilon) ln(n/2) for any epsilon > 0 unless NP subset DTIME(n(log log n)). A simple, very easily implementable algorithm that exhibits the above upper bound on solution quality is presented. This algorithm has running time O(np/2(2m-p+1)) < or = O(m(n2-n)/2) where p < or = min(n, m) for n haplotypes of size m. As we show that the approximation bound is asymptotically tight, the algorithm presented is optimal with respect to this asymptotic bound. CONCLUSION: The haplotype tagging problem is hard, but approachable with a fast, practical, and surprisingly simple algorithm that cannot be significantly improved upon on a single processor machine. Hence, significant improvement in computational efforts expended can only be expected if the computational effort is distributed and done in parallel.

Nomographic representation of logistic regression models: a case study using patient self-assessment data.

Logistic regression models are widely used in medicine, but difficult to apply without the aid of electronic devices. In this paper, we present a novel approach to represent logistic regression models as nomograms that can be evaluated by simple line drawings. As a case study, we show how data obtained from a questionnaire-based patient self-assessment study on the risks of developing melanoma can be used to first identify a subset of significant covariates, build a logistic regression model, and finally transform the model to a graphical format. The advantage of the nomogram is that it can easily be mass-produced, distributed and evaluated, while providing the same information as the logistic regression model it represents.

Do physicians value decision support? A look at the effect of decision support systems on physician opinion.

OBJECTIVE: Clinical decision support systems are on the verge of becoming routine software tools in clinical settings. We investigate the question of how physicians react when faced with decision support suggestions that contradict their own diagnoses. METHODOLOGY: We used a study design involving 52 volunteer dermatologists who each rated the malignancy of 25 lesion images on an ordinal scale and gave a dichotomous excise/no excise recommendation for each lesion image. After seeing the system's rating and excise suggestions, the physicians could revise their initial recommendations. RESULTS: We observed that in 24% of the cases in which the physicians' diagnoses did not match those of the decision support system, the physicians changed their diagnoses. There was a slight but significant negative correlation between susceptibility to change and experience level of the physicians. Physicians were significantly less likely to follow the decision system's recommendations when they were confident of their initial diagnoses. No differences between the physicians' inclinations to following excise versus no excise recommendations could be observed. CONCLUSION: These results indicate that physicians are quite susceptible to accepting the recommendations of decision support systems, and that quality assurance and validation of such systems is therefore of paramount importance.

Logistic regression and artificial neural network classification models: a methodology review.

Logistic regression and artificial neural networks are the models of choice in many medical data classification tasks. In this review, we summarize the differences and similarities of these models from a technical point of view, and compare them with other machine learning algorithms. We provide considerations useful for critically assessing the quality of the models and the results based on these models. Finally, we summarize our findings on how quality criteria for logistic regression and artificial neural network models are met in a sample of papers from the medical literature.