Skip to main content
Indian Journal of Ophthalmology logoLink to Indian Journal of Ophthalmology
. 2020 Feb 14;68(3):427–432. doi: 10.4103/ijo.IJO_710_19

Big data and the eyeSmart electronic medical record system - An 8-year experience from a three-tier eye care network in India

Anthony Vipin Das 1,, Priyanka Kammari 1, Ranganath Vadapalli 1, Sayan Basu 1
PMCID: PMC7043185  PMID: 32056994

Abstract

Purpose:

To assess the demographic details and distribution of ocular disorders in patients presenting to a three-tier eye care network in India using electronic medical record (EMR) systems across an 8-year period using big data analytics.

Methods:

An 8-year retrospective review of all the patients who presented across the three-tier eye care network of L.V. Prasad Eye Institute was performed from August 2010 to August 2018. Data were retrieved using an in-house eyeSmart EMR system. The demographic details and clinical presentation and ocular disease profile of all the patients were analyzed in detail.

Results:

In an 8-year period, a total of 2,270,584 patients were captured on the EMR system with 4,730,221 consultations. More than half of the patients presented at tertiary centers (n = 1,174,643, 51.73%), a quarter at the secondary centers (n = 564,251, 24.85%) followed by the vision centers (n = 531,690, 23.42%). The ratio of males and females was 1.18:1. Most common states of presentation were Andhra Pradesh (n = 1,103,733, 48.61%) and Telangana (n = 661,969, 29.15%). In total, 3,721,051 ocular diagnosis instances were documented in the patients. Most common ocular disorders were related to cornea and anterior segment (n = 1,347,754, 36.22%) followed by refractive error (n = 1,133,078, 30.45%).

Conclusion:

This study depicts the demographic details and distribution of various ocular disorders in a very large cohort of patients. There is a need to adopt digitization in geographies that cater to large populations to enable insightful research. The implementation of EMR systems enables structured data for research purposes and the development of real-time analytics for the same.

Keywords: Analytics, big data, electronic medical records, ocular diseases


The earliest mention of a medical record dates back to 1600 BC of an Egyptian case report from a papyrus text on surgery.[1] Case records of Hippocrates from the 5th BC were instrumental in describing the natural causes and the clinical course of illness.[2] The progress of science and understanding of the human body through the centuries further reinforced the need to document new knowledge to be passed down from generation to generation. A precursor to modern medical records first appeared by early 19th century in the form of loose paper files in major centers, such as Berlin and Paris.[3] The medical record continued to evolve over the 19th century to include patient history, clinical examination, treatment instructions, and investigations. A major innovation in 1907 was the introduction of the medical record number to patients at St Mary's Hospital and the Mayo Clinic.[4] Electronic medical record (EMR) systems are increasingly replacing paper-based records with benefits in increasing efficiency and standardizing quality while reducing costs of health care.[5] Today with the rapid adoption of different technologies impacting people's lives, there is an exciting potential for clinical research to embrace the same. However, the use of digital systems differs between the western and eastern hemispheres of the world. There is a lack of adequate data from the eastern part of the world detailing the use of EMR systems to describe the distribution of ocular disorders and its effect on population health. Research done by reviewing paper records is not only cumbersome but also prone to human errors. The amount of time taken to retrieve and analyze the large volumes of data from the EMR is minimal. The EMR system can collect large datasets (“big data”) that are characterized by the four 'V's - volume, variety, velocity, and veracity.[6] Given the challenges of connectivity, power and volume, digitization of hospitals in India is limited and evolving. The aim of this study was to evaluate the demographic details and distribution of ocular disorders from an indigenously developed EMR system (eyeSmart™) of a large three-tier eye care network in India and to describe the possibility of real-time analytics from the structured datasets.

Methods

An 8-year retrospective review of all the patients who presented across the three-tier eye care network of L.V. Prasad Eye Institute (LVPEI) was performed from August 2010 to August 2018. The patient data were retrieved using the information captured through the in-house EMR system eyeSmart™. The study was approved by LVPEI's Institutional Review Board on 11.9.2018 with reference number of LEC 09-18-150 and adhered to the tenets of Declaration of Helsinki. A standard consent form for electronic data privacy was filled by the patient or their parents or guardians at the time of registration.

The three-tier eye care model of LVPEI includes 176 Vision Centers that provide primary care in the districts and villages of Andhra Pradesh, Telangana, Odisha, and Karnataka. These are linked to 18 Secondary Eye Care Centers, which are, in turn, linked to LVPEI Tertiary Centers in Visakhapatnam, Vijayawada, and Bhubaneswar. LVPEI's Center of Excellence at Hyderabad is at the apex of the Eye Care Pyramid. The medical records of all patients who presented to any of these Centers during August 2010 to August 2018 were reviewed retrospectively using the eyeSmart EMR database.

In total, 2,270,584 patients were captured on the EMR system and their total consultations were 4,730,221 in this 8-year period. All the patients who were registered onto the EMR system were included in the study. The variables in the collected data include age, gender, geographical location, laterality of eye affected, and ocular diagnosis. The geographical location and country as reported by the patients at the time of registration were documented in the EMR system and were included in the study.

Each eye of the patients was diagnosed separately, and each individual diagnosis was considered cumulatively for the analysis. The LVPEI coding diagnosis developed in-house was used for the patients, which includes a comprehensive list of ocular disorders, and the ICD-11 coding was automatically mapped to the relevant diagnosis. The ocular diagnosis made were categorized into different ocular disorders, such as amblyopia, cataract, cornea, and anterior segment disorders, glaucoma, neuro-ophthalmology, ocular trauma, refractive error, retina, uvea, and strabismus.

The age, gender distribution, demographic details, and proportion of ocular disorders were calculated through an SQL query written to extract information from all the databases of the centers across the network during the 8-year period. The individual numbers and percentages of the parameters to be studied were calculated through the query and exported to an excel sheet for further analysis. A detailed representation of the process is provided in the supplementary material. No identifiable information of the patient was used for analytical purposes. The de-identified information was replicated into another database from where analytics were visualized using tools for the same in real time. “eyeSmart EMR” is an indigenously built EMR system at the LVPEI, India. This system was developed in-house by using open source tools such as PHP (Zend Technologies, Cupertino, CA, USA) for programming and MySQL (Oracle Corporation, Redwood City, CA, USA) for database management. The eyeSmart App was developed on the Android platform (Google LLC, Menlo Park, CA, USA). The system allows the documentation of clinical information of patients significantly in a structured format that allows analysis for research purposes, and unstructured information is also captured. The information from the database was analyzed to provide a real-time overview. All tables for age, gender, location, and diagnosis category were drawn by using Microsoft Excel.

Results

In total, 2,270,584 patients were captured on the EMR system and their total consultations were 4,730,221 in the 8-year period.

Age

The age of the patients ranged from 0 to > 100 years. Based on the age category, pediatric population (≤16 years) presented were N = 304,100 (13.39%) and the adult population (>16 years) were N = 1,966,484 (86.61%). The most common age group of the patients who presented were between 51 and 60 years (n = 372,571, 16.41%) and followed by 41 and 50 years (n = 364,298, 16.04%). The detailed distribution of the age category is shown in Table 1.

Table 1.

Age distribution of the patients based on level of care

Age Category (Year) Tertiary Center % Secondary Center % Vision Center % Total Count %
0-10 104,800 71.1 25,773 17.5 16,773 11.4 147,346 6.5
11-20 132,181 49 50,909 18.9 86,404 32.1 269,493 11.9
21-30 183,125 54.6 56,551 16.9 95,738 28.5 335,415 14.8
31-40 145,123 47.8 64,835 21.4 93,280 30.8 303,238 13.4
41-50 185,768 51 87,391 24 91,139 25 364,298 16.0
51-60 192,350 51.6 103,233 27.7 76,988 20.7 372,571 16.4
61-70 162,235 47 126,540 36.6 56,472 16.4 345,248 15.2
71-80 58,235 51.6 41,662 37 12,907 11.4 112,803 5.0
81-90 10,138 53.9 6,875 36.6 1,783 9.5 18,796 0.8
91-100 661 52.6 456 36.3 141 11.1 1,257 0.1
>100 27 22.7 26 22.7 65 54.6 119 0.0
Grand total 1,174,643 51.7 564,251 24.9 531,690 23.4 2,270,584 100.0

Gender

The ratio of males (n = 1,228,538, 54.11%) and females (n = 1,042,046, 45.89%) presenting to the network was 1.18:1. Table 2 details the distribution of patients as per gender on EMR across various levels of the LVPEI eye care network.

Table 2.

Gender distribution of the patients based on level of care

Gender Tertiary Center % Secondary Center % Vision Center % Total Count %
Male 666,803 54.3 272,817 22.2 288,918 23.5 1,228,538 54.1
Female 507,840 48.7 291,434 28 242,772 23.3 1,042,046 45.9
Grand total 1,174,643 51.7 564,251 24.9 531,690 23.4 2,270,584 100.0

Patient distribution according to level of care

More than half of the patients presented at tertiary centers (n = 1,174,643, 51.73%), a quarter at the secondary centers (n = 564,251, 24.85%) followed by the vision centers (n = 531,690, 23.42%).

Ocular diagnosis

In total, 3,721,051 ocular diagnosis instances were documented in the patients. The two most common ocular disorders were from the following categories of cornea and anterior segment (n = 1,347,754, 36.22%) followed by refractive error (n = 1,133,078, 30.45%), respectively. Table 3 details the ocular disorder distribution captured through EMR. A significant proportion of diagnosis was made in both eyes (n = 1,985,373, 53.36%) followed by right eye (n = 810,132, 21.77%) and left eye (n = 784,725, 21.09%).

Table 3.

Distribution of ocular disorders based on level of care

Ocular Diagnosis Tertiary Center % Secondary Center % Vision Center % Total Count %
Cornea and anterior segment 612,301 45.4 467,398 34.7 268,055 19.9 1,347,754 36.2
Refractive error 609,569 53.8 242,355 21.4 281,154 24.8 1,133,078 30.5
Cataract 261,219 44.7 253,500 43.4 69,104 11.8 583,823 15.7
Retina 204,025 88 26,719 11.5 1,197 0.5 231,941 6.2
Glaucoma 130,663 85.6 20,213 13.2 1,821 1.2 152,697 4.1
Oculoplasty 74,541 78.3 18,139 19 2,562 2.7 95,242 2.6
Neuro ophthalmology 41,859 85.8 6,493 13.3 445 0.9 48,797 1.3
Ocular trauma 28,296 64 10,626 24 5,312 12 44,234 1.2
Strabismus 35,195 85.5 4,119 10 1,836 4.5 41,150 1.1
Amblyopia 22,795 83 4,113 15 540 2 27,448 0.7
Uvea 11,388 84.9 1,966 14.6 67 0.5 13,421 0.4
Paediatric ophthalmology 1,345 91.8 121 8.2 0 0 1,466 <1
Grand total 2,033,196 54.6 1,055,762 28.4 632,093 17 3,721,051 100

Geographical distribution

Patients presented from 109 countries to the LVPEI eye care network in the 8-year period. The highest number of patients presented from India (n = 2,264,230, 99.72%) followed by Bangladesh (n = 1608, 0.07%) and Oman (n = 1189, 0.05%). Table 4 provides details of geographical distribution of patients from around the world.

Table 4.

Distribution of the gender and age categories based on the geographical location (country)

Country Total patients % Male % Female % <16 Years % >16 Years %
India 2,264,230 99.7 1,224,550 54.1 1,039,681 45.9 303,258 13.4 1,960,972 86.6
Bangladesh 1,608 0.1 1,066 66.3 542 33.7 325 20.2 1,283 79.8
Oman 1,189 0.1 736 61.9 453 38.1 112 9.4 1,077 90.6
Somalia 1,127 <1 605 53.7 522 46.3 79 7 1,048 93
Yemen 578 <1 416 72 162 28 77 13.3 501 86.7
Sudan 240 <1 151 62.9 89 37.1 29 12.1 211 87.9
United Arab Emirates 198 <1 116 58.6 82 41.4 36 18.2 162 81.8
Kenya 186 <1 105 56.5 81 43.5 22 11.8 164 88.2
Nepal 117 <1 78 66.7 39 33.3 17 14.5 100 85.5
United States of America 118 <1 65 55.1 53 44.9 18 15.3 100 84.7
Ethiopia 114 <1 65 57 49 43.0 8 7 106 93
Afghanistan 79 <1 72 91.1 7 8.9 9 11.4 70 88.6
Nigeria 71 <1 41 57.7 30 42.3 16 22.5 55 77.5
Tanzania 57 <1 32 56.1 25 43.9 4 7 53 93
Liberia 12 <1 11 91.7 1 8.3 2 16.7 10 83.3
Others 660 <1 429 65 231 35 88 13.3 572 86.7
Grand total 2,270,584 100 1,228,538 54.1 1,042,046 45.9 304,100 13.4 1,966,484 86.6

Others indicates the cumulative count of the rest of the countries

The patients presented from 33 different states of India and the most common states of presentation were Andhra Pradesh (n = 1,103,733, 48.61%) followed by Telangana (n = 661,969, 29.15%). The least number of patients presented from the union territory of Daman and Diu (n = 3; 0.00%). Table 5 provides details of the geographical distribution of patients from India.

Table 5.

Distribution of gender and age categories based on the geographical locations of India

State Total patients % Male % Female % <16 Years % >16 Years %
Andhra Pradesh 1,103,733 48.6 578,383 52.4 525,351 47.6 130,291 11.8 97,3442 88.2
Telangana 661,969 29.2 349,431 52.8 312,538 47.2 97,593 14.7 56,4376 85.3
Odisha 286,501 12.6 171,002 59.7 115,500 40.3 46,292 16.2 240,209 83.8
Maharashtra 40,032 1.8 24,782 61.9 15,250 38.1 6,683 16.7 33,349 83.3
Karnataka 37,992 1.7 20,291 53.4 17,701 46.6 4,176 11 33,816 89
West Bengal 47,017 2.1 29,929 63.7 17,088 36.3 5,586 11.9 41,431 88.1
Not Applicable* 22,524 1 13,205 58.6 9,318 41.4 3,599 16 18,925 84
Orissa 33,530 1.5 17,212 51.3 16,318 48.7 4,521 13.5 29,009 86.5
Jharkand 5,290 0.2 3,407 64.4 1,883 35.6 715 13.5 4,575 86.5
Chhattisgarh 5,369 0.2 3,339 62.2 2,030 37.8 817 15.2 4,552 84.8
Madhya Pradesh 4,612 0.2 3,126 67.8 1,486 32.2 752 16.3 3,860 83.7
Uttar Pradesh 4,052 0.2 2,736 67.5 1,316 32.5 623 15.4 3,429 84.6
Bihar 3,933 0.2 2,653 67.5 1,280 32.5 528 13.4 3,405 86.6
Assam 4,753 0.2 3,072 64.6 1,681 35.4 535 11.3 4,218 88.7
Rajasthan 1,804 0.1 1,240 68.7 564 31.3 305 16.9 1,499 83.1
Tripura 2,128 0.1 1,375 64.6 753 35.4 220 10.3 1,908 89.7
Gujarat 1,152 0.1 757 65.7 395 34.3 244 21.2 908 78.8
Delhi 854 <1 526 61.6 328 38.4 109 12.8 745 87.2
Kerala 531 <1 340 64.0 191 36.0 98 18.5 433 81.5
Tamil Nadu 671 <1 424 63.2 247 36.8 70 10.4 601 89.6
Jammu and Kashmir 367 <1 261 71.1 106 28.9 78 21.3 289 78.7
Haryana 485 <1 298 61.4 187 38.6 97 20.0 388 80.0
Punjab 266 <1 166 62.4 100 37.6 42 15.8 224 84.2
Goa 164 <1 96 58.5 68 41.5 31 18.9 133 81.1
Uttarakhand 208 <1 139 66.8 69 33.2 21 10.1 187 89.9
Meghalaya 127 <1 70 55.1 57 44.9 13 10.2 114 89.8
Manipur 105 <1 57 54.3 48 45.7 7 6.7 98 93.3
Himachal Pradesh 95 <1 56 58.9 39 41.1 11 11.6 84 88.4
Arunachal Pradesh 96 <1 43 44.8 53 55.2 13 13.5 83 86.5
Pondicherry 70 <1 48 68.6 22 31.4 12 17.1 58 82.9
Sikkim 70 <1 36 51.4 34 48.6 8 11.4 62 88.6
Nagaland 47 <1 23 48.9 24 51.1 6 12.8 41 87.2
Mizoram 34 <1 13 38.2 21 61.8 3 8.8 31 91.2
Daman & Diu 3 <1 2 66.7 1 33.3 1 33.3 2 66.7
Grand total 2,270,584 100 1,228,538 54.1 1,042,046 45.9 304,100 13.4 1,966,484 86.6

*Not Applicable is for patients who do not have a State classification

Further a real-time dash-board of the demographic details and ocular disorders of patient presenting to the LVPEI network from August 2010 on the EMR system was developed using the data and can now be accessed at the following link – http://www.lvpei.org/aeye/eyesmart.html.

Discussion

This study has demonstrated the demographic and ocular disorders' distribution in a large cohort of patients presenting to a three-tier eye care network in India. Gender predisposition was not noted in the presentation of patients with an equitable distribution accessing eye care services. A significant proportion of ocular disorders were in both eyes and there was no predisposition to laterality in either of them. It is of utmost importance to digitize clinical information to uniformly capture the data and assess the burden of ocular disease. In our study, we found that the cornea and anterior segment disorders and refractive error constituted about two-thirds of the ocular disorders seen in the network. The scope of this study was to provide an overview of the ocular disorders and other similar studies from the eyeSmart EMR system have reported them in detail as in dacryology and dry eye.[7,8]

Ophthalmology is particularly conducive for data science in medicine due to structured quantifiable outcome measures that are significantly numeric and image based. This information allows us to perform big data analytics that have now evolved from the hundreds and thousands to millions and billions of data points. eyeSmart™ EMR is an indigenously developed EMR system at the LVPEI. The project that began in August 2010 has now completed the digitization of the 198 centers of the LVPEI network, which comprises of 1 Center of Excellence, 3 Tertiary Centers, 18 Secondary Centers, and 176 Vision Centers across the states of Telangana, Andhra Pradesh, Odisha, and Karnataka. It has facilitated about 4.7 million consultations since its inception. The system allows the documentation of clinical information in structured forms and images, which are stored in the database of the respective centers. All information from various centers is synced to a central database that allows the real-time analysis of the entire network.

The process of digitization poses different challenges in any large organization. Scholl et al. described the experience of the implementation of EMR in a large hospital in India.[9] The successful adoption of digital systems in complex organizations requires an alignment between the working protocols and needs of the organization and the functionality of the system. The various reasons that effect successful implementation include dynamic design strategies, user-friendly work flows, and demonstration of benefit for easy reporting of statistics. In our experience, demonstration of successful pilots at each level of the LVPEI pyramid was the most crucial step before expansion of eyeSmart™ in 198 centers across different geographies. Replication of the system across each level of Tertiary, Secondary, and Vision Center level was then achieved in a phase wise manner. Sharing of best practice patterns of utilization of EMR by different groups across the network provided the motivation to adopt the system. Time is a crucial component in the implementation strategy and the 176 rural vision centers were digitized in 90 days. Rapid implementation also provides rapid feedback that can be utilized positively to refine the application for the users.

The use of EMRs in population health management holds promise. Cavallo P et al. conducted a retrospective study of 14,958 patients and 1,728,736 prescriptions obtained from family doctors to understand the associations of comorbidities in the general population.[10] The network analysis extracted information from the prescriptions generating insights impacting both clinical practice and health system policy making. The various applications of EMR assisting population health management include quantifying treatment outcomes,[11] quantify and stratify the severity of disease,[12,13] collect patient-reported outcomes,[14] document lifestyle patterns,[15] and potential to guide medicines regulation.[16] The use of large datasets helps to understand factors influencing health such as geographical location, nutrition, lifestyle, and their temporal evolution. The application of artificial intelligence in public health is also increasing.[17]

The population of India is 1.3 billion people. Access to health care is a challenge and nonavailability of information at scale in real time across geographies can limit policy planning. Big data analytics are a key to understanding distribution of ocular diseases in India. The ability to understand the burden of disease is very crucial to plan strategies to combat avoidable blindness. A real-time dash-board of the demographic details and ocular disorders of patients presenting to the LVPEI network from August 2010 on the EMR system can be accessed at the following link – http://www.lvpei.org/aeye/eyesmart.html.

The limitations of this study include the lack of population data, patient referral bias to a tertiary care in emerging economies, and reflection solely based of the distribution of ocular disorders and not their management. Patient duplication was also assessed as a limitation in the respective tertiary centers and was found to be negligible (0.28%) across the network. However, the strengths of the study include a very large cohort of patients and focused study of demographics and distribution of ocular disorders in patients seeking eye care in a large three-tier hospital network in India across 8 years.

Conclusion

To the best of our knowledge, this is the first description of a large cohort of patients using EMRs in a large multi-tier ophthalmology network in India. In conclusion, this study lists out the detailed demographic distribution and distribution of ocular disorders in patient seeking eye care and demonstrates the potential for real-time analytics using EMR systems.

Declaration of patient consent

The authors certify that they have obtained all appropriate patient consent forms. In the form the patient(s) has/have given his/her/their consent for his/her/their images and other clinical information to be reported in the journal. The patients understand that their names and initials will not be published and due efforts will be made to conceal their identity, but anonymity cannot be guaranteed.

Financial support and sponsorship

Nil.

Conflicts of interest

There are no conflicts of interest.

Acknowledgements

The authors wish to acknowledge the support of our Department of eyeSmart EMR & AEye team specially Mr. Mohammad Pasha and Mr. Yasaswi Leela Ram and all the programmers who have helped develop the EMR system over the years.

References

  • 1.Al-Awqati Q. How to write a case report: Lessons from 1600 B.C. Kidney Int. 2006;69:2113–4. doi: 10.1038/sj.ki.5001592. [DOI] [PubMed] [Google Scholar]
  • 2.Reiser SJ. The clinical record in medicine. Part 1: Learning from cases. Ann Intern Med. 1991;114:902–7. doi: 10.7326/0003-4819-114-10-902. [DOI] [PubMed] [Google Scholar]
  • 3.Hess V. Formalizing observation: The emergence of the modern patient record exemplified by Berlin and Paris medicine, 1725-1830. Medizinhist J. 2010;45:293–340. [PubMed] [Google Scholar]
  • 4.Camp CL, Smoot RL, Kolettis TN, Groenewald CB, Greenlee SM, Farley DR. Patient records at Mayo Clinic: Lessons learned from the first 100 patients in Dr Henry S.Plummer's dossier model. Mayo Clin Proc. 2008;83:1396–9. doi: 10.1016/S0025-6196(11)60790-8. [DOI] [PubMed] [Google Scholar]
  • 5.Chaudhry B, Wang J, Wu S, Maglione M, Mojica W, Roth E, et al. Systematic review: Impact of health information technology on quality, efficiency, and costs of medical care. Ann Intern Med. 2006;144:742–52. doi: 10.7326/0003-4819-144-10-200605160-00125. [DOI] [PubMed] [Google Scholar]
  • 6.IBM Big Data & Analytics Hub. United States. [Last accessed on 2019 May 30]. Available from: https://www.ibmbigdatahub.com/infographic/four-vs-big-data .
  • 7.Donthineni PR, Kammari P, Shanbhag SS, Singh V, Das AV, Basu S. Incidence, demographics, types and risk factors of dry eye disease in India: Electronic medical records driven big data analytics report I. Ocul Surf. 2019;17:250–6. doi: 10.1016/j.jtos.2019.02.007. [DOI] [PubMed] [Google Scholar]
  • 8.Das AV, Rath S, Naik MN, Ali MJ. The incidence of lacrimal drainage disorders across a tertiary eye care network: Customization of an indigenously developed electronic medical record system-eyeSmart. Ophthalmic Plast Reconstr Surg. 2019;35:354–6. doi: 10.1097/IOP.0000000000001257. [DOI] [PubMed] [Google Scholar]
  • 9.Scholl J, Syed-Abdul S, Ahmed LA. A case study of an EMR system at a large hospital in India: Challenges and strategies for successful adoption. J Biomed Inform. 2011;44:958–67. doi: 10.1016/j.jbi.2011.07.008. [DOI] [PubMed] [Google Scholar]
  • 10.Cavallo P, Pagano S, De Santis M, Capobianco E. General practitioners records are epidemiological predictors of comorbidities: An analytical cross-sectional 10-year retrospective study. J Clin Med. 2018:7. doi: 10.3390/jcm7080184. doi: 103390/jcm7080184. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 11.Armstrong AW, Foster SA, Comer BS, Lin CY, Malatestinic W, Burge R, et al. Real-world health outcomes in adults with moderate-to-severe psoriasis in the United States: A population study using electronic health records to examine patient-perceived treatment effectiveness, medication use, and healthcare resource utilization. BMC Dermatol. 2018;18:4. doi: 10.1186/s12895-018-0072-2. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 12.Eggleston EM, Klompas M. Rational use of electronic health records for diabetes population management. Curr Diab Rep. 2014;14:479. doi: 10.1007/s11892-014-0479-z. [DOI] [PubMed] [Google Scholar]
  • 13.Zghebi SS, Rutter MK, Ashcroft DM, Salisbury C, Mallen C, Chew-Graham CA, et al. Using electronic health records to quantify and stratify the severity of type 2 diabetes in primary care in England: Rationale and cohort study design. BMJ Open. 2018;8:e020926. doi: 10.1136/bmjopen-2017-020926. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 14.Franklin P, Chenok K, Lavalee D, Love R, Paxton L, Segal C, et al. Framework to guide the collection and use of patient-reported outcome measures in the learning healthcare system. EGEMS (Wash DC) 2017;5:17. doi: 10.5334/egems.227. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 15.Lewis KH, Skelton JA, Hsu FC, Ezouah P, Taveras EM, Block JP. Implementing a novel electronic health record approach to track child sugar-sweetened beverage consumption. Prev Med Rep. 2018;11:169–75. doi: 10.1016/j.pmedr.2018.06.007. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 16.Pacurariu A, Plueschke K, McGettigan P, Morales DR, Slattery J, Vogl D, et al. Electronic healthcare databases in Europe: Descriptive analysis of characteristics and potential for use in medicines regulation. BMJ Open. 2018;8:e023090. doi: 10.1136/bmjopen-2018-023090. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 17.Thiebaut R, Thiessard F. Artificial intelligence in public health and epidemiology. Yearb Med Inform. 2018;27:207–10. doi: 10.1055/s-0038-1667082. [DOI] [PMC free article] [PubMed] [Google Scholar]

Articles from Indian Journal of Ophthalmology are provided here courtesy of Wolters Kluwer -- Medknow Publications

RESOURCES