• Users Online: 285
  • Print this page
  • Email this page

 Table of Contents  
Year : 2021  |  Volume : 9  |  Issue : 3  |  Page : 116-121

Automated interactive patient history-taking system: A review

1 Department of Medical Affairs, Intellimed Healthcare Solutions, Mumbai, Maharashtra, India
2 Department of Pharmacy Practice, SRM College of Pharmacy, Kanchipuram, Tamil Nadu, India

Date of Submission25-Aug-2020
Date of Decision13-Dec-2021
Date of Acceptance09-Oct-2020
Date of Web Publication11-May-2022

Correspondence Address:
Anish Desai
D-110 Kanakia Zillion, BKC Annexe, LBS-CST Road, Kurla, Mumbai, Maharashtra - 400 070
Login to access the Email id

Source of Support: None, Conflict of Interest: None

DOI: 10.4103/dypj.dypj_4_20

Rights and Permissions

The process of history-taking has been challenging for India due to its booming population and severe scarcity of doctors. Inadequate patient history could lead to medication errors, adverse drug reactions, and medication noncompliance. Innovations in health information technology have great potential for improving the practice of medicine. Automated patient history is collected with the help of a computer. Physicians can use artificial intelligence to help with documentation, analysis of patient data while increasing the precision, productivity, and efficacy of the physician. Health-care providers are looking for regulatory compliant and efficient software for automated patient history taking. In telemedicine, automated history taking before the consultation can save physician‘s time, have more accurate history which will improve the telemedicine experience for the patient, especially in times of a pandemic like coronavirus disease 2019.

Keywords: Artificial intelligence, automated, digital technology, patient history, software, telemedicine

How to cite this article:
Desai A, Anand SS, Mathew SE. Automated interactive patient history-taking system: A review. D Y Patil J Health Sci 2021;9:116-21

How to cite this URL:
Desai A, Anand SS, Mathew SE. Automated interactive patient history-taking system: A review. D Y Patil J Health Sci [serial online] 2021 [cited 2022 May 27];9:116-21. Available from: http://www.dypatiljhs.com/text.asp?2021/9/3/116/345101

  Introduction Top

A convergence of the science and the art of medicine, the patient’’ history is still the most important tool for making an accurate diagnosis. Regardless of how many new diagnostic tests are available, eliciting information verbally from patients is unsurpassed in diagnostic efficacy. Collecting important information from the patient is essential for effective for making clinical decisions including diagnosis, treatment options, laboratory tests, and further therapy plan. An almost accurate patient history can result in correct diagnosis in 70% of the cases. The process of history-taking has been challenging for India due to its booming population and severe scarcity of doctors.[1] The WHO recommends minimum doctor-to-patient ratio as 1:1000. However, according to the 2017 edition in the Indian Journal of Public Health, India had just 4.8 doctors per 10,000 people.[2] According to the 2015 Global Strategy Report on Human Resources for health, by 2030 resource-limited countries will face a significant imbalance in the healthcare workers to patient ratio.[3] Innovations in health information technology have great potential for improving the practice of medicine. In theory, greater and faster information availability could allow physicians more time to thoroughly explain diagnoses and treatments or address patient concerns.

Gathering information that is crucial to guide patient care is known as history-taking. It includes the patient’s medical history, social history, allergies, past medication history, and current medications.[4] Conventionally, patient history is gathered during the consultation where the doctor asks the patient-specific questions and then documents the responses in written form or electronic format. Later, detailed scrutiny of the information gathered is done and a diagnostic conclusion is made. A comprehensive and detailed history of the patient is very crucial to make a diagnosis.

Some of the major factors that hinder appreciable history-taking in developing countries are overcrowding clinics, inadequate doctor-to-patient ratio, and low pay scales of healthcare professionals [Figure 1].
Figure 1: Challenges in history-taking

Click here to view

As per an observational study titled “4 min for a patient, 20 s for a relative” carried out in the Medical University Centre of Freiburg (Germany), approximately 11.4% of a physician’s working time is spent on the communication about diagnosis, therapy and psychosocial issues with the patient.[5] Language barriers can lead to insufficient collection of the medical history of the patient. Such communication gaps may lead to unnecessary medical readmission, incorrect diagnosis, and treatment plans.[6]

One of the most time-consuming activities of a physician is the taking of a patient’s medical history. Many physicians believe that this method of gathering information is not highly effective. This is owed by many reasons. First, a physician’s busy schedule does not provide him ample time to explore a patient in detail. From the patient’s point of view, the physician’s inability to listen to all his problems may negatively affect the rapport. Second, patients vaguely remember their family history, medication history, or medical history. Sometimes, questions of personal nature could be embarrassing for the patient to answer and he may resort to lying about his history. Such questions can be stressful for the patient and the embarrassment involved could act as a major hindrance toward gathering an effective patient history.[7]

Importance of history-taking

The patient history directs the physician towards the important elements to be analyzed during physical examination. Subsequently, this allows for distinguishing the most relevant problems of the patient from the subsidiary ones. A comprehensive and organized clinical history can help lead to the most accurate clinical decision.

  • Past medical history provides a baseline for the identification of the drug and disease-related problems

  • Social history helps identify if the habits, substance abuse, relationship, and hobbies

  • Family history helps assort patients who may have a genetic predisposition toward particular diseases

  • Medication history is important to prevent the occurrence of any drug–drug interactions.

  • All these bits of information put together help in making a diagnostic conclusion.

    Evidence demonstrating the need of detailed medical history

    A literature search conducted by Römer et al. showed that careful history-taking and clinical examination play an important role in the selection of the right contraceptive for women. The reason being some combined hormonal contraceptives are contraindicated in women with real factors such as a predisposition to thrombophilia, hypertension, headache, epilepsy, hepatic tumors, diabetes mellitus, nicotine abuse, or age over 35.[8] A case report by Cui et al. revealed that patient history plays a significant role in the diagnosis of foreign body aspiration in children. The report highlights two pediatric cases that were misdiagnosed due to unclear aspiration history. Later with the help of targeted questions, the authors were able to identify the problem and administer treatment for the same.[9]

    A case report by Ghosh and Karunaratne showed how a case of neuropathy was misdiagnosed as stroke and how a comprehensive focused history helps reveal such an important bit of information.[10] A case report by Jo Fitz-Henry and Riley illustrated the importance of a complete patient history through their case. The case elaborates the incident of a 26-year-old man arriving at the ED after a motorcycle accident. The patient was treated for infection and yet signs of infection did not seem to subside. On suspicions of thyrotoxicosis, his family was interrogated. The enquiry led to the revelation of the patient showing signs of hyperthyroidism before the trauma. The case highlights how a detailed history would have helped make the right diagnosis.[11]

    A cross-sectional study performed by Arora et al. evaluated the satisfaction of patients who used a self-administered automated medical history-taking device in the emergency department (ED). The study results proved that patients were highly satisfied with all aspects of the device and felt that it helped them communicate better with the doctor.[12]

    Average time taken for history-taking by physicians

    According to Sabin et al., the mean time required by a doctor to take a history and perform physical examination is 20 min (standard deviation [SD] 5 min). The components in a consultation, which required the greatest amount of time were: Documentation (41%), history and physical examination (31%) and communication with relatives (19%).[13] In a study conducted by Wald et al., patient history was collected with the help of a computerized interview. Patients had to take the interview before they met their physicians. On average, a completed interview took 27 min. The mean total interview time was 25 min for the younger patients and 37 min for the older ones.[14]

    The impact of inadequate history

    Medication errors

    Lau et al. concluded their prospective study by stating that the medication history contained in the medical records of the hospital was incomplete as 67% of all the study patients had one or more medications that were either not used but recorded or recorded but not used.[15] According to a study conducted by Frydenberg and Brekke among 30 patients that used a total of 250 drugs, 50 medication errors were found that affected 18 of the patients. Twenty-seven errors were potentially harmful. These errors were the result of poor collection of patient medication history.[16] A systematic review performed by Tam et al. illustrates with evidence that the incidence of incorrect and inadequate medication history collection at the time of hospital admission is extremely high. They found that up to 54% of patient files had a minimum of one medication history error and approximately 19%–75% of them were accidental errors.[17]

    Adverse drug reactions

    According to a survey done by Shenfield et al.; out of the 117 patients surveyed, 50 patients had a total of 81 previous adverse reactions; but only 75% were recorded on medication charts and 64% were recorded in the nursing notes. This shows that adverse drug reactions are usually poorly recorded which can result in patient harm.[18] Negligence while recording other herbal or over-the-counter medications the patient may be taking at admission can lead to disastrous consequences. Constable et al. reported the case of a 77-year-old woman who was taking St. Johns Wort and Ginseng at the time of admission. These herbal remedies were not recorded on the patient’s medication history as a result of which she developed an upper gastrointestinal hemorrhage when she was administered lansoprazole.[19]

    Medication noncompliance

    Few of the reasons for lack of compliance to medications include misconceptions or a belief held by patients regarding the treatment, poor patient-physician relationship, poor health literacy, and insufficient knowledge of patients about their disease or treatment. Among few patients that were administered treatment for asthma, the main reason for nonadherence was their belief that the condition was not severe enough to be treated daily.[20] In a study that assessed the impact of the doctor-patient relationship, participants who felt that their physicians listened to their concerns more were more likely to adhere to their medications.[21]

    Available approaches for history-taking

    Standard form

    The standard form of history-taking involves the physician who gathers relevant information from the patient in a written format during the consultation.

    Electronic medical history

    It is very similar to the standard form of history-taking as information is gathered from the patient. Data gathered are entered into the system in an electronic format. Electronic records help reduce the number of medical error occurrences and improve the quality of care. However, some disadvantages of electronic medical records are change in the normal workflow of doctors, loss of productivity, privacy, and security concerns.[22]

    Computer-assisted history-taking system

    Digital tools help gather history from the patient before consultation, aid in diagnosis and treatment plan.

    Integrated artificial intelligence for automated patient history

    Automated patient history is collected with the help of a computer. The patient sits at a computer terminal and answers the questions presented to him by the computer. At the end of the session, a summary of the patient’s answers are printed by the computer for the use of the physician.[23] Most history-taking systems employ such terminals that display a set of questions that can have only two or more possible answers. The patient’s response is fed into the computer by pushing the respective buttons that indicate their answer. This kind of system uses the branching technique.[24] Some of the broad applications of AI in healthcare include: drug development, disease diagnostics, health monitoring, analysis of health plans, digital consultation, surgical treatments, management of medical data, medical treatment, and personalized treatment. Computers can diagnose a patient using AI via two techniques: flowchart-based approach and database approach. First, in the flowchart-based approach, the computer arrives at a probable diagnosis by combining the various symptoms presented. Second, the database approach works by utilizing the principle of deep learning.

    Evolution of automated patient history taking

    Scientific literature has been growing ever since published information on the first online computer history-taking system he had developed in Wisconsin.[25] Since then, other groups have developed computer-linked systems through which patients can report historic information including Barnett and Grossman at the Massachusetts General Hospital, and Mayne at the Mayo Clinic.[23],[24] The Automated Medical History System questionnaire designed by Lahey Clinic sends an E-mail to patients prior to their visit. The results of this questionnaire are then used by the clinic to schedule patients to the appropriate specialists. A printed copy of the questionnaire is then used to aid the physician in history taking.[7]

    The Automated Patient History Intake Device (APHID) developed by the Portland Veterans Affairs Medical Center in 2009 to enhance the accuracy and sustainability of ambulatory medication reconciliation is a self-check-in kiosk and reconciliation tool for the ambulatory care setting. The goals of APHID were first, to improve the accuracy of the medication history by showing patients digital pictures of their medications on record, and secondly, to integrate APHID into current business processes to promote the use and minimize interruptions to workflow. Around 8170 of a potential 17,275 patients (47%) checked-in using APHID. Patients who used the electronic kiosk were able to complete their medication history as the inclusion of pill pictures improved patient recall. They concluded that consumer-based kiosk offers a feasible model to align the safety and efficiency needs of a health system.[26]

    A study was conducted to assess the factors that influence automated patient history systems. Patient age, number of complaints, and the time required to complete the instructional portion of the interview showed a positive correlation with overall interview time. There was a negative correlation between the patient’s years of formal education and interview duration. The patients who interacted directly with a small online computer (LINC-8) took an average time of 24.1 min (SD 8.2 min) with a range of 13–51 min for the completion of the interview. There was a positive correlation between age and interview time (r = 0.27./P < 0.005). There was a negative correlation between education and interview time as expected (r = −0.39, 11 < 0.005). The correlation of the number of presenting complaints with interview time was positive (r = 0.47, 1) <0.025). When criteria such as those discussed here indicate that the patient will perform slowly or at a low level of accuracy, the interview question sequence could be altered.[27]

    A self-administered, computer-based questionnaire was tested in another study. 60 mothers completed a mean of 102 questions in a mean time of 35 min. The computer consistently detected more abnormal symptoms than were recorded in the physician’s history; on rechecking these were found to be valid. This proved that computer-based history taking will prove to be a very powerful aid in gathering, storing, and retrieving pediatric clinical information.[25]

    Patient Touch™ is an innovative, hand-held touch-screen tablet developed by Humantouch Inc. A study was conducted among ambulatory ED patients. The objective was to allow ambulatory ED patients to use the device to self-administer a clinical history (detailed chief complaint history, comprehensive past medical history, medication history and review of symptoms) and determine patient perceptions of the physical characteristics of the device, time required to complete the session, appropriateness and detail of the questions, potential impact and overall satisfaction. Out of 173 participants that used Patient Touch™, 93.6% of them felt the physical product was easy to use; 97.1% felt the questions could help describe their condition; 97.8% felt using Patient Touch™ would help them organize their thoughts and communicate better with their physician, 94.8% thought it would increase the quality of healthcare, and 97.1% (94.6%–99.6%) would like to use the product again in the future. The study was conducted at a largely Hispanic county ED and involved only patients with 1 of 6 predetermined chief complaints. A control group was not included. The results of this pilot study revealed that patients were highly satisfied with all aspects of the Patient Touch™ self-administered, hand-held, touch-screen tablet. Importantly, subjects felt it would help them better communicate with their doctor, would improve their overall quality of care and overwhelmingly increased their desire to use it in the future.[12]

    Automated medical history–taking devices (AMHTDs) are novel history-taking methods that provide physicians with the complete history of the patient with an added advantage of differential diagnosis. A study was conducted to assess the effectiveness of an AMHTD in obtaining accurate differential diagnoses in outpatient service. A pilot study involving 59 patients presenting to the emergency outpatient department and suffering from various conditions affecting the limbs, the back, and the chest wall were included. Physicians were randomized into two groups, one used the AMHTD and one didn’t use the device. For each patient, physicians were asked to make a comprehensive differential diagnosis based on the history and clinical examination. In the intervention group, physicians read the AMHTD report before laying out the final diagnosis. In both groups, a senior physician had to give a differential diagnosis that was the gold standard. The results showed that the differential diagnosis accuracy was higher in the intervention group (AMHTD) than in the control. The novel AMHTD was able to determine 73% of correct differential diagnoses. Patients were satisfied and considered that they were able to accurately describe their symptoms. It was evident that the AMHTD helped physicians in making accurate differential diagnoses, particularly in complex cases. This could be explained not only by the ability of the AMHTD to make the right diagnoses but also by the exhaustive anamnesis provided.[28]

    Computer-assisted Instruction programs are being extensively used in history-taking programs. A pilot study was carried out that studied the feasibility of using the computer as a screening device in child psychiatry. Mothers were asked to answer questions regarding their child’s behavior. The procedure was generally acceptable to the mothers, and the data proved useful in distinguishing normal controls from a patient group. The authors conclude that this is indeed a feasible use of the computer.[29]

    CLEOS® is an automated history-taking tool that merges laboratory data; analyzes the clinical significance of the data collected; sends reports to physicians for findings, diagnoses, prevention, follow-up; gives recommendations for diagnosis and treatment. A study was conducted in dyslipidemic patients where patients answered questions regarding themselves using the CLEOS® program. The program collected data of present illness, past medical history, current medications, social history, and family history. A total of 213 medical records and CLEOS® interviews for the same set of 213 unselected patients were compared to evaluate the performance of these tasks by physicians and the CLEOS® program. Patients (n = 81) at high risk for a coronary event were identified based on history by CLEOS®. A computerized history-taking program together with automated analysis of clinical data collected by self-interview of patients can outperform routine medical care for categorizing risk for coronary events, for identifying treatment targets, identifying patients with risk of hypercholesterolemia, and for identifying past and present statin-induced adverse drug effects.[30]

    Arintra is the first assistive AI solution in India for comprehensive history taking and machine-learned provisional diagnosis generation. It is a novel AI-based diagnosis decision-support system that assists doctors and medical assistants capture a patient’s comprehensive and chronological history and in generating a provisional diagnosis. The different tasks performed by AI in Arintra are clinical history-taking, clinical natural language processing, and medical diagnostics. The tool saves 5 min of doctor’s time per patient. Data is securely encrypted and made anonymized at the source. The tool can provide a patient history before the consultation even begins. This tool flags drug-drug interactions automatically generates preliminary draft of discharge summary and improves patient retention. Currently, there are 20 pilots running in major corporate and private hospitals, SHCOs and independent clinics in Andhra Pradesh, Telangana, and Kerala.

    Future outlook

    In the coming years, patients will seek more telemedicine services as coronavirus disease 2019 has already uplifted its usage and acceptance worldwide. Rapidly changing regulations for healthcare IT in India could be challenging in deploying such technology in the healthcare setup. The solution lies within the advent of the National Digital Health Blueprint. The trend of digitizing patient records in India is growing amid demand for standardization of operations in medical care. Healthcare providers are looking for regulatory compliant and efficient software.

    In telemedicine, as patient clinical information is collected before consultation, doctors need not worry about missing important patient information and can consequently communicate effectively with them. This technology enables focused and personalized interaction with the patient lending more time for counseling too.

      Conclusion Top

    With the help of AI-enable computerized interactive history-taking applications, patient history-taking becomes a seamless and hassle-free process. The vision is to provide good quality healthcare in India and other developing countries. It is essential to focus on improved efficiency and accuracy of the patient-doctor information that helps reduce medical errors and improve patient safety.

    Financial support and sponsorship


    Conflicts of interest

    There are no conflicts of interest.

      References Top

    Deo MG Doctor population ratio for India – The reality. Indian J Med Res 2013;137:632-5.  Back to cited text no. 1
    Potnuru B Aggregate availability of doctors in India: 2014–2030. Indian J Public Health 2017;61:182.  Back to cited text no. 2
    Towards a Global Strategy on Human Resources for Health; 2015. Available from: https://www.who.int/about/licensing/copyright_form/en/index.html. [Last accessed on 2020 Jul 14].  Back to cited text no. 3
    Fragiskos FD Medical history. In: Oral Surgery. Berlin Heidelberg: Springer; 2007. p. 1-20. Available from: https://www.ncbi.nlm.nih.gov/books/NBK534249/. [Last accessed on 2020 Jul 16].  Back to cited text no. 4
    Becker G, Kempf DE, Xander CJ, Momm F, Olschewski M, Blum HE Four minutes for a patient, twenty seconds for a relative – An observational study at a university hospital. BMC Health Serv Res 2010;10:94.  Back to cited text no. 5
    Furaijat G, Kleinert E, Simmenroth A, Müller F Implementing a digital communication assistance tool to collect the medical history of refugee patients: DICTUM Friedland – An action-oriented mixed methods study protocol. BMC Health Serv Res 2019;19:103.  Back to cited text no. 6
    Rockart JF, McLean ER, Hershberg PI, Bell GO An automated medical history system. Experience of the Lahey Clinic Foundation with computer-processed medical histories. Arch Intern Med 1973;132:348-58.  Back to cited text no. 7
    Römer T Kontrazeption bei patientinnen mit risikokonstellation. Dtsch Arztebl Int 2019;116:764-74.  Back to cited text no. 8
    Cui Y, Cui X, Yu T, Zhu Z, Wang X Importance of patient history in diagnosis of foreign body aspiration in children: Two case reports. Medicine (Baltimore) 2019;98:e15326.  Back to cited text no. 9
    Ghosh D, Karunaratne P The importance of good history taking: A case report. J Med Case Rep 2015;9:97.  Back to cited text no. 10
    Fitz-Henry J, Riley B Thyrotoxicosis in a patient with multiple trauma: Value of “AMPLE” history taking. BMJ 1996;313:997-8.  Back to cited text no. 11
    Arora S, Goldberg AD, Menchine M Patient impression and satisfaction of a self-administered, automated medical history-taking device in the Emergency Department. West J Emerg Med 2014;15:35-40.  Back to cited text no. 12
    Sabin J, Khan W, Subbe CP, Franklin M, Abulela I, Khan A, et al. “The time it Takes…” How doctors spend their time admitting a patient during the acute medical take. Clin Med J R Coll Physicians London 2016;16:320-4.  Back to cited text no. 13
    Wald JS, Rind D, Safran C, Kowaloff H, Barker R, Slack WV Patient entries in the electronic medical record: An interactive interview used in primary care. In: Proceedings of the Annual Symposium on Computer Application in Medical Care; 1995. American Medical Informatics Association. p. 147.  Back to cited text no. 14
    Lau HS, Florax C, Porsius AJ, De Boer A The completeness of medication histories in hospital medical records of patients admitted to general internal medicine wards. Br J Clin Pharmacol 2000;49:597-603.  Back to cited text no. 15
    Frydenberg K, Brekke M Poor communication on patients’ medication across health care levels leads to potentially harmful medication errors. Scand J Prim Health Care 2012;30:234-40.  Back to cited text no. 16
    Tam VC, Knowles SR, Cornish PL, Fine N, Marchesano R, Etchells EE Frequency, type and clinical importance of medication history errors at admission to hospital: A systematic review. CMAJ 2005;173:510-5.  Back to cited text no. 17
    Shenfield GM, Robb T, Duguid M Recording previous adverse drug reactions – A gap in the system. Br J Clin Pharmacol 2001;51:623-6.  Back to cited text no. 18
    Constable S, Ham A, Pirmohamed M Herbal medicines and acute medical emergency admissions to hospital. Br J Clin Pharmacol 2007;63:247-8.  Back to cited text no. 19
    Lin J, Sklar GE, Min Sen Oh V, Li SC Factors affecting therapeutic compliance: A review from the patient’s perspective. Ther Clin Risk Manag 2008;4:269-86.  Back to cited text no. 20
    Moore PJ, Sickel AE, Malat J, Williams D, Jackson J, Adler NE Psychosocial factors in medical and psychological treatment avoidance: The role of the doctor-patient relationship. Health Psychol 2004;9:421-33.  Back to cited text no. 21
    Menachemi N, Collum TH Benefits and drawbacks of electronic health record systems. Risk Manag Healthc Policy 2011;4:47-55.  Back to cited text no. 22
    Rockhart JF Some experience with an automated medical history questionnaire. 1971.  Back to cited text no. 23
    Haessler HA, Holland T, Elshtain EL Evolution of an automated database history. Arch Intern Med 1974;134:586-91.  Back to cited text no. 24
    Lesselroth BJ, Felder RS, Adams SM, Cauthers PD, Dorr DA, Wong GJ, et al. Design and implementation of a medication reconciliation kiosk: The Automated Patient History Intake Device (APHID). J Am Med Inform Assoc 2009;16:300-4.  Back to cited text no. 25
    Coombs GJ, Murray WR, Krahn DW Automated medical histories: Factors determining patient performance. Comput Biomed Res 1970;3:178-81.  Back to cited text no. 26
    Mauger DC Experience with automated history taking in paediatrics. Aust Paediatr J 1975;11:201-3.  Back to cited text no. 27
    Schwitzguebel AJ, Jeckelmann C, Gavinio R, Levallois C, Benaïm C, Spechbach H Differential diagnosis assessment in ambulatory care with an automated medical history-taking device: Pilot randomized controlled trial. JMIR Med Inform 2019;7:e14044.  Back to cited text no. 28
    Coddington RD, King TL Automated history taking in child psychiatry. Am J Psychiatry 1972;129:276-82.  Back to cited text no. 29
    Zakim D, Fritz C, Braun N, Fritz P, Alscher MD Computerized history-taking as a tool to manage dyslipidemia. Vasc Health Risk Manag 2010;6:1039-46.  Back to cited text no. 30


      [Figure 1]


    Similar in PUBMED
       Search Pubmed for
       Search in Google Scholar for
     Related articles
    Access Statistics
    Email Alert *
    Add to My List *
    * Registration required (free)

      In this article
       Article Figures

     Article Access Statistics
        PDF Downloaded11    
        Comments [Add]    

    Recommend this journal