Dataset Information

Using patients like my patient for clinical decision support: institution-specific probability of celiac disease diagnosis using simplified near-neighbor classification.

ABSTRACT:

Background

Interpretation of a diagnostic test result requires knowing what proportion of patients with a "similar" result has the condition in question. This information is often not readily available from the medical literature, or may be based on different clinical populations that make it nonapplicable. In certain settings, where correlated screening parameters and diagnostic data are available in electronic medical records, a representation of diagnostic test performance on "patients like my patient" can be obtained.

Objective

We sought to integrate patient demographic and physician practice information using a simplified nearest neighbor algorithm. We used this method to illustrate the relationship between tTG IgA test result and duodenal biopsy for celiac disease in a local diagnostic context.

Participants

We used a data set of 1,461 paired tissue transglutaminase (tTG) IgA and definitive duodenal biopsy results from Intermountain Healthcare with data on patient age and ordering physician specialty. This was split into a discovery set of 1,000 and a validation set of 461 paired results.

Main measures

Accuracy of the local discovery data set in predicting probability of positive duodenal biopsy and confidence intervals around predicted probability in the test data compared to probabilities of positive biopsy implied from published logistic regression and from published sensitivity and specificity studies.

Key results

The near-neighbor method could estimate probability of clinical outcomes with predictive performance equivalent to other methods while adjusting probability estimates and confidence intervals to fit specific clinical situations.

Conclusions

Data from clinical encounters obtained from electronic medical records can yield prediction estimates that are tailored to the individual patient, local population, and healthcare delivery processes. Local analysis of diagnostic probability may be more clinically meaningful than probabilities inferred from published studies. This local utility may come at the expense of external validity and generalizability.

SUBMITTER: Shirts BH

PROVIDER: S-EPMC3832711 | biostudies-literature | 2013 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using patients like my patient for clinical decision support: institution-specific probability of celiac disease diagnosis using simplified near-neighbor classification.

Shirts Brian H BH Bennett Sterling T ST Jackson Brian R BR

Journal of general internal medicine 20130504 12

<h4>Background</h4>Interpretation of a diagnostic test result requires knowing what proportion of patients with a "similar" result has the condition in question. This information is often not readily available from the medical literature, or may be based on different clinical populations that make it nonapplicable. In certain settings, where correlated screening parameters and diagnostic data are available in electronic medical records, a representation of diagnostic test performance on "patient ...[more]

PMID: 23645451

Similar Datasets

Project description:BackgroundMetagenomics, or the sequencing and analysis of collective genomes (metagenomes) of microorganisms isolated from an environment, promises direct access to the "unculturable majority". This emerging field offers the potential to lay solid basis on our understanding of the entire living world. However, the taxonomic classification is an essential task in the analysis of metagenomics data sets that it is still far from being solved. We present a novel strategy to predict the taxonomic origin of environmental genomic fragments. The proposed classifier combines the idea of the k-nearest neighbor with strategies from kernel-based learning.ResultsOur novel strategy was extensively evaluated using the leave-one-out cross validation strategy on fragments of variable length (800 bp - 50 Kbp) from 373 completely sequenced genomes. TACOA is able to classify genomic fragments of length 800 bp and 1 Kbp with high accuracy until rank class. For longer fragments > or = 3 Kbp accurate predictions are made at even deeper taxonomic ranks (order and genus). Remarkably, TACOA also produces reliable results when the taxonomic origin of a fragment is not represented in the reference set, thus classifying such fragments to its known broader taxonomic class or simply as "unknown". We compared the classification accuracy of TACOA with the latest intrinsic classifier PhyloPythia using 63 recently published complete genomes. For fragments of length 800 bp and 1 Kbp the overall accuracy of TACOA is higher than that obtained by PhyloPythia at all taxonomic ranks. For all fragment lengths, both methods achieved comparable high specificity results up to rank class and low false negative rates are also obtained.ConclusionAn accurate multi-class taxonomic classifier was developed for environmental genomic fragments. TACOA can predict with high reliability the taxonomic origin of genomic fragments as short as 800 bp. The proposed method is transparent, fast, accurate and the reference set can be easily updated as newly sequenced genomes become available. Moreover, the method demonstrated to be competitive when compared to the most current classifier PhyloPythia and has the advantage that it can be locally installed and the reference set can be kept up-to-date.

Project description:BackgroundProcrastination and lack of attention may often hinder the implementation of preemptive actions necessary to mitigate the spread of COVID-19 like washing hands, covering nose and mouth with a mask, and keeping social distance. It is in such "easy" tasks that people (mistakenly) believe that they are better than others. In this paper we test for overconfidence bias in COVID-19 preventive behaviors in Latin America.MethodsUsing a phone survey in nationally representative samples from 10 Latin American countries where randomly, half of the sample in each country was asked about self-reported compliance to COVID-19 guidelines, and half about preventive behavior of fellow citizens compared to them; we tested: if the proportion of individuals claiming that others comply with a certain measure "Always more frequent than me" is higher than those stating that they "Never" or "Sometimes" comply with the same measure (i.e. people believe they are better at doing something than what they actually are).ResultsOver 90% of Latin-Americans claim to always wear a mask and sanitize their hands and more than 80% state to always keep social distance. We also find evidence of overconfidence in every behavior - except for keeping distance in public transportation. Moreover, the magnitude of such overconfidence is higher for behaviors such as wearing masks in public or washing hands than for those regarding keeping the 2-m distance.ConclusionsTo our knowledge, this is the first study to measure overconfidence in COVID-19 preventive behaviors in Latin America. Results show that more effort is needed to encourage people to comply with the regulation when it does not only depend on them: a better organization of closed stores and public transportation are, for instance, crucial to allow social distancing. It also suggests that a reinforcement of basic measures is essential, as individuals report to be performing them more frequently than when they have to think about such behaviors compared to others.

Dataset Information

Using patients like my patient for clinical decision support: institution-specific probability of celiac disease diagnosis using simplified near-neighbor classification.

Background

Objective

Participants

Main measures

Key results

Conclusions

Publications

Using patients like my patient for clinical decision support: institution-specific probability of celiac disease diagnosis using simplified near-neighbor classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets