+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Developing and evaluating an automated appendicitis risk stratification algorithm for pediatric patients in the emergency department


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.



          To evaluate a proposed natural language processing (NLP) and machine-learning based automated method to risk stratify abdominal pain patients by analyzing the content of the electronic health record (EHR).


          We analyzed the EHRs of a random sample of 2100 pediatric emergency department (ED) patients with abdominal pain, including all with a final diagnosis of appendicitis. We developed an automated system to extract relevant elements from ED physician notes and lab values and to automatically assign a risk category for acute appendicitis (high, equivocal, or low), based on the Pediatric Appendicitis Score. We evaluated the performance of the system against a manually created gold standard (chart reviews by ED physicians) for recall, specificity, and precision.


          The system achieved an average F-measure of 0.867 (0.869 recall and 0.863 precision) for risk classification, which was comparable to physician experts. Recall/precision were 0.897/0.952 in the low-risk category, 0.855/0.886 in the high-risk category, and 0.854/0.766 in the equivocal-risk category. The information that the system required as input to achieve high F-measure was available within the first 4 h of the ED visit.


          Automated appendicitis risk categorization based on EHR content, including information from clinical notes, shows comparable performance to physician chart reviewers as measured by their inter-annotator agreement and represents a promising new approach for computerized decision support to promote application of evidence-based medicine at the point of care.

          Related collections

          Most cited references 22

          • Record: found
          • Abstract: found
          • Article: not found

          Systematic review: impact of health information technology on quality, efficiency, and costs of medical care.

          Experts consider health information technology key to improving efficiency and quality of health care. To systematically review evidence on the effect of health information technology on quality, efficiency, and costs of health care. The authors systematically searched the English-language literature indexed in MEDLINE (1995 to January 2004), the Cochrane Central Register of Controlled Trials, the Cochrane Database of Abstracts of Reviews of Effects, and the Periodical Abstracts Database. We also added studies identified by experts up to April 2005. Descriptive and comparative studies and systematic reviews of health information technology. Two reviewers independently extracted information on system capabilities, design, effects on quality, system acquisition, implementation context, and costs. 257 studies met the inclusion criteria. Most studies addressed decision support systems or electronic health records. Approximately 25% of the studies were from 4 academic institutions that implemented internally developed systems; only 9 studies evaluated multifunctional, commercially developed systems. Three major benefits on quality were demonstrated: increased adherence to guideline-based care, enhanced surveillance and monitoring, and decreased medication errors. The primary domain of improvement was preventive health. The major efficiency benefit shown was decreased utilization of care. Data on another efficiency measure, time utilization, were mixed. Empirical cost data were limited. Available quantitative research was limited and was done by a small number of institutions. Systems were heterogeneous and sometimes incompletely described. Available financial and contextual data were limited. Four benchmark institutions have demonstrated the efficacy of health information technologies in improving quality and efficiency. Whether and how other institutions can achieve similar benefits, and at what costs, are unclear.
            • Record: found
            • Abstract: found
            • Article: not found

            Estimated risks of radiation-induced fatal cancer from pediatric CT.

            In light of the rapidly increasing frequency of pediatric CT examinations, the purpose of our study was to assess the lifetime cancer mortality risks attributable to radiation from pediatric CT. Organ doses as a function of age-at-diagnosis were estimated for common CT examinations, and estimated attributable lifetime cancer mortality risks (per unit dose) for different organ sites were applied. Standard models that assume a linear extrapolation of risks from intermediate to low doses were applied. On the basis of current standard practice, the same exposures (milliampere-seconds) were assumed, independent of age. The larger doses and increased lifetime radiation risks in children produce a sharp increase, relative to adults, in estimated risk from CT. Estimated lifetime cancer mortality risks attributable to the radiation exposure from a CT in a 1-year-old are 0.18% (abdominal) and 0.07% (head)-an order of magnitude higher than for adults-although those figures still represent a small increase in cancer mortality over the natrual background rate. In the United States, of approximately 600,000 abdominal and head CT examinations annually performed in children under the age of 15 years, a rough estimate is that 500 of these individuals might ultimately die from cancer attributable to the CT radiation. The best available risk estimates suggest that pediatric CT will result in significantly increased lifetime radiation risk over adult CT, both because of the increased dose per milliampere-second, and the increased lifetime risk per unit dose. Lower milliampere-second settings can be used for children without significant loss of information. Although the risk-benefit balance is still strongly tilted toward benefit, because the frequency of pediatric CT examinations is rapidly increasing, estimates that quantitative lifetime radiation risks for children undergoing CT are not negligible may stimulate more active reduction of CT exposure settings in pediatric patients.
              • Record: found
              • Abstract: found
              • Article: not found

              Pediatric appendicitis score.

               Madan Samuel (2002)
              Morbidity in children treated with appendicitis results either from late diagnosis or negative appendectomy. A Prospective analysis of efficacy of Pediatric Appendicitis Score for early diagnosis of appendicitis in children was conducted. In the last 5 years, 1,170 children aged 4 to 15 years with abdominal pain suggestive of acute appendicitis were evaluated prospectively. Group 1 (734) were patients with appendicitis and group 2 (436) nonappendicitis. Multiple linear logistic regression analysis of all clinical and investigative parameters was performed for a model comprising 8 variables to form a diagnostic score. Logistic regression analysis yielded a model comprising 8 variables, all statistically significant, P <.001. These variables in order of their diagnostic index were (1) cough/percussion/hopping tenderness in the right lower quadrant of the abdomen (0.96), (2) anorexia (0.88), (3) pyrexia (0.87), (4) nausea/emesis (0.86), (5) tenderness over the right iliac fossa (0.84), (6) leukocytosis (0.81), (7) polymorphonuclear neutrophilia (0.80) and (8) migration of pain (0.80). Each of these variables was assigned a score of 1, except for physical signs (1 and 5), which were scored 2 to obtain a total of 10. The Pediatric Appendicitis Score had a sensitivity of 1, specificity of 0.92, positive predictive value of 0.96, and negative predictive value of 0.99. Pediatric appendicitis score is a simple, relatively accurate diagnostic tool for accessing an acute abdomen and diagnosing appendicitis in children. Copyright 2002, Elsevier Science (USA). All rights reserved.

                Author and article information

                J Am Med Inform Assoc
                J Am Med Inform Assoc
                Journal of the American Medical Informatics Association : JAMIA
                BMJ Publishing Group (BMA House, Tavistock Square, London, WC1H 9JR )
                December 2013
                15 October 2013
                15 October 2013
                : 20
                : e2
                : e212-e220
                [1 ]Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center , Cincinnati, Ohio, USA
                [2 ]Division of Emergency Medicine, Cincinnati Children's Hospital Medical Center , Cincinnati, Ohio, USA
                [3 ]Division of Hospital Medicine, Cincinnati Children's Hospital Medical Center , Cincinnati, Ohio, USA
                [4 ]James M. Anderson Center for Health Systems Excellence , Cincinnati Children's Hospital Medical Center , Cincinnati, Ohio, USA
                Author notes
                [Correspondence to ] Dr Imre Solti, Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, MLC 7024, Cincinnati, OH 45229-3039, USA; imre.solti@ 123456cchmc.org
                Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions

                This is an Open Access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 3.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/3.0/

                Research and Applications
                Custom metadata


                Comment on this article