Access the full text.
Sign up today, get DeepDyve free for 14 days.
Background: The authors developed a computerized program designed to diagnose primary headache based on international classification of headache disorders, 2nd edition (ICHD-II) criteria for use by physicians. Methods: An appropriate questionnaire was designed according to the ICHD-II criteria for all types of primary headaches and the computerized system provided diagnosis based on the criteria. The software was tested by analyzing 80 patients, recruited from an outpatient headache clinic, affected by primary headache. Each patient with a unique card number was interviewed up to 15 minutes. At the end of each day, software and neurologist diagnoses were evaluated for each patient. Results: Of 80 patients, the software was able to come up with correct results in 78 cases. The age of the patients ranged from 30 to 80 years old. Migraine headache accounted for 71 cases, five patients had tension type headache, and 2 had cluster headaches; all were correctly diagnosed by software. Two cases were not concordant with the neurologist’s diagnosis. The neurologist diagnosed these two cases as “Medical overuse syndrome headache” and “cluster headache”, which our software was not able to diagnosis them. Conclusions: This software permitted the diagnosis of more than 97% of the patients similar to the physician's. We hope this questionnaire and applying the software to diagnose headache based on ICHD could be of help to better the diagnosis of headaches. Keywords: Headache diagnosis, Software, International classification of headache disorder (ICHD-II) Introduction 2nd edition (ICHD-II) are the best available criteria to Headache is one of the most common complaints during precisely diagnose the type of headache (2nd Edition of life (Stang & Osterhaus 1993). During one year, 90% of The International Headache Classification (ICHD-2) 2004. people suffer from headaches, and over 10% have at least However, it is complicated for practitioners to memorize one migraine headache (Schwartz et al. 1998). all ICHD-II criteria for the diagnosis of headaches which Although considerable advances are seen in the therapy is about 150 pages long. On the other hand, the workload of headache, it still remains underdiagnosed (Lipton et al. of practitioners obliges them to minimize the length of 2001). In the clinical setting, there are no possible imaging visits, therefore, making it often impossible to take a or laboratory tools to diagnose different types of primary complete history and diagnose the headache as it should headaches. However, the recently revised diagnostic cri- be in which case as a result, limits the quality of thera- teria of International Classification of Headache Disorders, peutic choices. For this reason, we developed a computerized program designed for use by physicians in populated headache * Correspondence: firstname.lastname@example.org clinics. This easy-to-use system provides an assisted Neurology ward, Sina Hospital, Tehran University of Medical Sciences, diagnosis according to ICHD-II criteria for all types of Tehran, Iran Iranian Center of Neurological Researches, Tehran, Iran primary headaches including migraine, tension-type Full list of author information is available at the end of the article © 2013 Eslami et al.; licensee Springer. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Eslami et al. SpringerPlus 2013, 2:199 Page 2 of 4 http://www.springerplus.com/content/2/1/199 headache, cluster headache and other trigeminal auto- December 2012. Of them, 80 patients with primary nomic cephalalgias, as well as other primary headaches headache were evaluated. The patients were which are overall 61 types. Similar to other computer- recruited from an outpatient headache clinic, ized programs (De Simone et al. 2007), this software can affiliated to Tehran University of Medical Sciences. be used by operators with basic computer experience By entering the study, each patient received a card without increasing the time length of visits. with a unique number on it. The patients were primarily interviewed by the researchers. Each Method interview lasted up to 15 minutes. The data were collected from patients to fulfill the software’s entry. a. Software preparation The questions were instructed based on ICHD-II. The software has 5 main parts including the The software output described the proposed descriptive page, disclaimer page, patient’s diagnosis. The software’s diagnosis was recorded for registration page, headache questions, and the final the card number each patient had. Next, in the same decision with the explanation of it, which are all visit, the patients were interviewed by a neurologist prepared in Persian language (Additional file 1). The in another room. The neurologist and the researcher disclaimer page emphasizes that this software is made were not aware of each others’ diagnosis. The to facilitate and increase the accuracy of diagnosis. patient was not informed of the software output The criteria were extracted from primary headaches. either. The neurologists’ final diagnosis was Then, based on these criteria, questions were separately recorded for the card number each designed to approach all these criteria. Questions patient had. The neurologist was asked to define the would be asked based on responses, which take final first-ranked diagnosis by choices in between 5 to 15 minutes depending on the answers. concordance with ICHD-II classification. At the end For example, if the patient has visual problem of each day, software and neurologist diagnoses were during a headache attack, further questions such as evaluated for each patient. the association of headache with scotoma, flickering, scintillation, visual loss, diplopia, and bilateral/ unilateral visual disturbances, and also the Ethical approval maximum duration of these symptoms would be The approval of local research ethics committee of Tehran asked. The system will get into conclusion based on University of Medical Sciences and verbal consents from all criteria of ICHD-II and explain how headache all patients were obtained before any evaluation. The pa- was approached and possible diagnosis was made. tients were informed that no-participation would in no An essential feature of the program is to report “No way affect their care. diagnosis was made based on these data”, which can also find certain unclassifiable headaches. Furthermore, all demographic information and Result characteristics of the patients' headache, previously A total of 80 patients, over 18 years of age, were in- inserted in the program, are saved, allowing the cluded in the study. Female patients outnumbered male creation of a complete database in Access software patients (female patients n = 62). The age of patients which would be an invaluable tool for more headache ranged from 30 to 80 years old. The software was able researches such as further modifications of ICHD-II. to come up with correct results in 78 out of 80 cases. Another feature of this software is that each patient Migraine headache accounted for 71 cases, five patients has a profile, which can be updated at each had tension type headache, and 2 had cluster headaches; successive follow-up. The profile is accessible to all were correctly diagnosed by software. Two cases were record the diagnosis, the recommended therapy and not concordant with the neurologist’s diagnosis. The any further comments. Those who help the patient neurologist diagnosed these two cases as “Medical over- to answer the questions should not necessarily know use syndrome headache” and “cluster headache”, which the whole terminology of the words, since each our software was not able to diagnosis them. terminology is simply explained by informative notes and explanations indicated by moving the pointer of the mouse over it. Discussion b. Evaluating the software This computerized system uses simple human-like algo- We conducted a validation field-test to approve the rithmic logic to determine the most appropriate type of accuracy of the software. In all, 95 consecutive headache. However, similar to other medical software, patients were enrolled in our study from October to the accuracy of diagnosis depends on the accuracy of Eslami et al. SpringerPlus 2013, 2:199 Page 3 of 4 http://www.springerplus.com/content/2/1/199 patient responses. Also, the interviewer has an invalu- Additional file able role to obtain accurate responses in comparison Additional file 1: The mock-up translated screenshots of the software. with a computer program. In our evaluation, 2 patients had different diagnoses by the computer and the physician. The reason was inaccur- Competing interests The authors declare that they have no competing interests. ate and different responses of these 2 patients to the inter- viewer and physician. Different computerized headache Authors’ contributions programs are designed for use by general practitioners VE was the designer of this software. He developed the first idea. Also, he (Mainardi et al. 2005) to neurologists (Sarchielli et al. partially drafted the manuscript and performed submission and final 2005). Maizel et al. (2008), in their study using a comput- approval of the article. He performed parts of the data analysis. SR-E was the software developer. He managed the operation of the software. He erized headache assessment tool, correctly identified 100% performed transferring of the database from access to the SPSS and other of the patients with episodic migraine and 85.7% with data analysis as well as upgrading the system and translating to English. transformed migraine. Also, it correctly categorized all Also, he partially drafted the manuscript and performed submission and final approval of the article. NH-N cooperated in the evaluation of the software patients with tension-type headache, and cluster headache. and managing 80 patients. He participated in software analysis as well as Sarchielli et al. (2007), in their study using a computerized finding the bugs of the system. He also had role on changing the article system, permitted correct diagnosis in 78% of 200 head- from letter to original article. Also, he partially drafted the manuscript and performed submission and final approval of the article. FR participated in ache patients. evaluation of the software on more than 80 patients. Also, he partially As these criteria are under change over time (Olesen drafted the manuscript and performed submission and final approval of the 2011; Bigal et al. 2007; Olesen 2006), we hope that article. He performed the literature review and changing the article format from letter to original article. SA participated in the software designation. applying the software to diagnose headache based on Developing the first idea and also solving problems using ICHD-II criteria. ICHD could be of help for modifying the current diag- Also, he partially drafted the manuscript and performed submission and final nostic criteria, finding the answer to issues which need approval of the article. MT was the leader of the team, managed the patients for software evaluation, visited the patients in the clinic and diagnosed to be studied more in the ICHD-II guideline. However, them, as well as, parts of design of the study. Also, she partially drafted the in a clinical practice, we face a large number of patients manuscript. She performed submission and final approval of the article. All who do not qualify for any defined criteria. As an authors read and approved the final manuscript. example, a few criteria include a response to a particular Acknowledgements drug. A marked overlap exists among criteria. On the The authors thank Dr. Faeze Dehghan (occupationalist at Aja university other hand, the patients cannot fit their responses to the of Medical Sciences) for her helpful comments, also Mrs. Bita Pourmand algorithm that any software undertakes. These all should (Sina Hospital, Research Development Center) for her careful editing of the manuscript. be addressed before considering such type of design. Yet still, an expert neurologists’ diagnosis is the standard for Funding comparing such software. For the same purpose, we The designing of the software was supported by the AJA University of conducted our validation survey in the neurologist’s Medical Sciences, Tehran, Iran [grant number 990158]. clinic. However, this may result in further limitations. Author details Many of the patients in such clinics are referred from Sina Trauma and Surgery Research Center, Tehran University of Medical other clinics due to the complicated nature of their Sciences, Tehran, Iran. Neurology Department, AJA University of Medical headache or inconclusive diagnosis. They may have Sciences, Tehran, Iran. Neurology ward, Sina Hospital, Tehran University of Medical Sciences, Tehran, Iran. Iranian Center of Neurological Researches, received different medications which might have altered 5 6 Tehran, Iran. Foolad Institute of Technology, Foolad-Shahr, Iran. Shariati the pattern of their headache, as well. For instance, one Hospital, Tehran University of Medical Sciences, Tehran, Iran. would have had one sided throbbing headache in the Received: 30 September 2012 Accepted: 22 April 2013 beginning, but recently has experienced both sided Published: 30 April 2013 compression-like headache. Yet though, the software needs a definite input. We used the primary pattern of References the headache as the input. Without the precise import 2nd Edition of The International Headache Classification (ICHD-2) (2004) Available of the specified inputs, the software would come up at: http://ihs-classification.org/en/. Accessed 01_15_13 Bigal ME, Rapoport AM, Sheftell FD, Tepper SJ, Lipton RB (2007) The International with a number of diagnoses including different types of Classification of Headache Disorders revised criteria for chronic migraine-field headache. However, an expert neurologist can handle testing in a headache specialty clinic. Cephalalgia 27(3):230–234. doi:10.1111/ such situations through history taking and proper j.1468-2982.2006.01274.x De Simone R, Coppola G, Ranieri A, Bussone G, Cortelli P, D’Amico D, D’Onofrio F, weighting of differential diagnoses. Also, patient’swill- Manzoni GC, Marano E, Perini F, Torelli P, Beneduce L, Ciccarelli G, Mea E, ingness to cooperate and trust this method is another Penza P, Ripa P, Sancisi E, Bonavita V (2007) Validation of AIDA Cefalee, a limitation to be mentioned. Finally, we recommend computer-assisted diagnosis database for the management of headache patients. Neurol Sci 28(Suppl 2):S213–S216. doi:10.1007/s10072-007-0779-z using such software to promote diagnosis in settings Lipton RB, Diamond S, Reed M, Diamond ML, Stewart WF (2001) Migraine like general day clinics instead of sub-specialized neur- diagnosis and treatment: results from the American migraine study II. ology clinics. Headache 41(7):638–645 Eslami et al. SpringerPlus 2013, 2:199 Page 4 of 4 http://www.springerplus.com/content/2/1/199 Mainardi F, Maggioni F, Dainese F, Zanchin G (2005) Development of a ICHD-II based computerised system for the general practitioner. J Headache Pain 6 (4):211–212. doi:10.1007/s10194-005-0187-9 Maizels M, Wolfe WJ (2008) An expert system for headache diagnosis: the Computerized Headache Assessment tool (CHAT). Headache 48(1):72–78. doi:10.1111/j.1526-4610.2007.00918.x Olesen J (2006) International Classification of Headache Disorders, Second Edition (ICHD-2): current status and future revisions. Cephalalgia 26(12):1409–1410. doi:10.1111/j.1468-2982.2006.01214.x Olesen J (2011) New plans for headache classification: ICHD-3. Cephalalgia 31(1):4–5. doi:10.1177/0333102410375628 Sarchielli P, Pedini M, Alberti A, Rossi C, Baldi A, Corbelli I, Calabresi P (2005) Application of ICHD 2nd edition criteria for primary headaches with the aid of a computerised, structured medical record for the specialist. J Headache Pain 6(4):205–210. doi:10.1007/s10194-005-0186-x Sarchielli P, Pedini M, Coppola F, Rossi C, Baldi A, Corbelli I, Mancini ML, Calabresi P (2007) Application of the ICHD-II criteria to the diagnosis of primary chronic headaches via a computerized structured record. Headache 47(1):38–44. doi:10.1111/j.1526-4610.2007.00651.x Schwartz BS, Stewart WF, Simon D, Lipton RB (1998) Epidemiology of tension-type headache. JAMA 279(5):381–383 Stang PE, Osterhaus JT (1993) Impact of migraine in the United States: data from the National Health Interview Survey. Headache 33(1):29–35 doi:10.1186/2193-1801-2-199 Cite this article as: Eslami et al.: A computerized expert system for diagnosing primary headache based on International Classification of Headache Disorder (ICHD-II). SpringerPlus 2013 2:199. Submit your manuscript to a journal and beneﬁ t from: 7 Convenient online submission 7 Rigorous peer review 7 Immediate publication on acceptance 7 Open access: articles freely available online 7 High visibility within the ﬁ eld 7 Retaining the copyright to your article Submit your next manuscript at 7 springeropen.com
SpringerPlus – Springer Journals
Published: Apr 30, 2013
Access the full text.
Sign up today, get DeepDyve free for 14 days.