APHRO Ontology for managing patient health records Suela Maxhelakua, Jonida Shehua and Endri Xhinaa a University of Tirana, Faculty of Natural Sciences, Computer Science Department, Zogu I Boulevard, Tirana, 1001, Albania Abstract This paper presents an overview of the Albanian Patient Healthcare Records Ontology with regards to the main medical services in "Mother Teresa" University Hospital Center in Albania, patients demographics, common vital signs of the patient, risk factors, patient visits and several diseases of the cardiovascular diseases, chronic respiratory diseases, diabetes and cancer. APHRO ontology will provide data of different patients and offer the opportunity to integrate patient records within different sectors in the hospital through mapping of ontology concepts to the SNOMED CT. Keywords 1 Ontology, Healthcare, Integration 1. Introduction computable knowledge extraction by applications [4] and an important facilitator for unambiguous definitions and data exchange Commonly the different HIS (Hospital [5]. In addition, ontologies provide implicit Information System) components are designed semantics that enable the derivation of new and implemented by different software information from existing ones, a key element developers without explicitly focusing on the to procure interoperability among different interoperability of the different HIS systems [6]. components, resulting into practical problems In this paper we propose the APHRO of interfacing and transferring data to each (Albanian Patient Healthcare Records other [1]. Beside of that, it is not the volume of Ontology) ontology in Albania in order to keep data that makes medicine significantly records of main patient’s healthcare data like challenging, but the challenges arising from demographics data, vital signs, risk factors, extracting useful information from different patient visits, different diseases and the main sectors in medicine [2]. In order to gain medical services in University Hospital Center knowledge and exchange data from different "Mother Teresa", Tirana, Albania. This healthcare providers or components in different ontology will provide an approach in offering Health Information Systems there is a need in interoperability of patient’s data through the interoperability in Healthcare. use of Systematized Nomenclature of Medicine According to the report of the Regional Clinical Terms (SNOMED CT). Office for Europe of the World Health Also the concepts (when it is possible) will Organization for the conditions in the primary be mapped to the SNOMED CT in order to health care in Albania, it is stated that there is offer interoperability between different health no integrated national information system nor information systems in the near future. electronic medical records [3]. SNOMED CT is the most comprehensive Ontologies are used as a source of multilingual clinical healthcare terminology vocabulary standardization and integration, as a Proccedings of RTA-CSIT 2021, May 2021, Tirana, Albania EMAIL:suela.maxhelaku@fshn.edu.al; jonida.shehu@fshn.edu.al; endri.xhina@fshn.edu.al ©️ 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (CEUR-WS.org) that it is used in electronic health record sensors ontologies and personal profile systems to facilitate clinical documentation and ontologies. reporting and to retrieve and analyze clinical Currently in our knowledge there is no an data [7]. ontology integrating medical services in The paper is organized as follows. In Albania and the related SNOMED CT Section 2 are examines some related works terminology, code and concepts for focusing on ontologies and interoperability in interoperability in healthcare. While in other healthcare domain. Section 3 presents the domains, OntoAL ontology is developed in methodology in creating the ontology in public E-Government Services domain in healthcare, while the section 4 describes the Albania [14]. APHRO (Albanian Patient Healthcare Records Ontology) Ontology using the main medical 3. Methodology services in University Hospital Center "Mother Teresa" and mapping patient’s data to SNOMED CT terminology. Finally, First of all, we have conducted research in ontologies developed in the Albanian conclusions and future steps are present in healthcare system and we have found no Section 5. ontology being used with medical services that are offered in Albania in different sectors and 2. Related Work in the same time providing interoperability using SNOMED CT terminology. So beside of Ontologies have been implemented in that, the APHRO Ontology will also record the different sectors of healthcare like primary patients’ data according to their demographics healthcare, emergency services, public data, risk factors, vital signs, diseases and visit healthcare, diseases healthcare, etc. [8]. data. The authors in [9] have presented a In the process of designing the Albanian perspective in integrating SNOMED-CT Patient Healthcare Records Ontology we have concepts for clinical data representation in the followed the tasks according to [15]. In this Health Information System through regard we have: implementation of standard codes, free-text 1. Specified the domain of the Patient entry and configurable forms. Healthcare Records Ontology; The proposed tool in [10] is used for the 2. Identified the key terms, concepts, and extraction and integration of medical their relations in the Albanian Patient information from heterogeneous sources using Healthcare Records Ontology; SNOMED-CT terminology and also exports 3. Established the rules and axioms matched data according to the HL7 format. according to the structural properties of the Also in order to ease patient understanding and domain in our ontology; facilitating the analysis of health data the 4. Represented the APHRO ontology by authors in [11] designed interactive using representation languages which visualization in reporting medical history and support the ontology such as RDF, RDFS or symptoms of the patients. OWL; Also the authors in [1] designed the HoPro 5. Combined the constructed ontologies (Hospital Process Ontology) Ontology in order with existing ontologies like SNOMED CT; to describe the business processes and every 6. Evaluated the constructed ontologies day functions and different interactions of the by using generic and specific evaluation hospital. metrics [15]. The Chronic Obstructive Pulmonary Disease ontology [12] designs concepts of the In order to offer the interoperability of the disease, environment, equipment, patient data patient records we will use SNOMEC CT, and treatment. because it is very important to map the concepts The research work in [13] presents from different components of the Health Do_Care, an ontology reasoning - based Information System to the SNOMED CT. For healthcare monitoring system that integrates example, from the proposed system in [16] for different ontologies like medicine ontologies, recording patient data in the Radiology Service Department at Mother Teresa Hospital in Tirana, Albania we will construct the ontology classes, object properties, individuals, data with the patient data and in order to offer properties, rules, axioms, etc. are detailed in the interoperability we will map some of the patient following paragraphs. data to the relevant SNOMED CT concepts and code. The following figure illustrates the mapping process from the concepts used in [16] to SNOMED CT concepts and codes using sameAs axiom in Protégé. Figure 2: Overview of the main classes of the APHCDO Ontology In order to offer interoperability between the health care systems the Demographics Data of the Patients, diseases and vital signs will have their relevant prefLabel, altLabel and code Figure 1: Mapping Concept from HIS to (URI) according to SNOMED CT that can be SNOMED CT accessed on [21] or [22]. The demographics data of the patient are designed at the ontology Also, the APHRO ontology will include using data properties with their relevant Patient some of the concepts from HL7 FHIR (FHIR is Demographics Domain and their relevant the standard for exchanging health care data, Range according to the patient information. In published by HL7 [17]) in accordance with the the table below are illustrated some of the domain of the APHRO ontology. patient demographics data and their relevant Risk factors, common diseases, medical code in SNOMED CT [21]. services and Vital Signs of the patients are the main classes in the APHRO Ontology in order Table 1 to offer scientifically rigorous, consistent and Patient Demographics extensible controlled vocabulary to facilitate Patient Data SNOMED CT data exchange and annotation in applications SSN 398093005 where a reference of their terms are required First Name 184095009 [18]. Last Name 184096005 Gender 184100006 Date of Birth 184099003 4. Proposed Ontology Address 184097001 City 433178008 The ontology is designed using the Protégé tool [19]. Protégé is one of the most popular ontology tools that is capable of defining The Medical Services in University Hospital classes and hierarchies, attribute relationships Center "Mother Teresa" are designed in the and attribute-value constraints, and the ontology according to [23] in 5 main sectors: relationships between classes and attributes  Medical Activity Sector (13 services); [20].  Diagnostic Activity Sector (6 services);  Neuro-Psychiatric Activity Sector (4 The main concepts of the APHRO services); (Albanian Patient Healthcare Records  Pediatrics Activity Sector (8 services); Ontology) are Person (Patient/Doctor),  Surgical Activity Sector (11 services). HealthCare Provider, Medical Services, Diseases, Common Vital Signs, Patient Visit, Vital signs from FHIR [24] will be used in Risk Factors and Visit Types. the Albanian Patient Healthcare Records The main classes of the APHRO ontology, Ontology to describe the common vital signs of are illustrated in the Figure 2 while other the patient. Each of the classes of the Vital the class Diseases and the Range is the class Signs have the preferred Label, alternative RiskFactors. The Domain and Range are Labels and the SNOMED CT code according to defined for all the object properties like the SNOMED CT that can be accessed on [21] has_Sign, has_Visit and has_Type. Specifying [22]. The above figure illustrates the FHIR vital these axioms is relevant for the reasoner in signs used in the APHRO ontology. order to discover new inferences in our ontology. In the following figure are illustrated some of the risk factors related to Heart Attacks (Cardiovascular Disease). Figure 3: Vital Signs The APHRO ontology has four common diseases like Cardiovascular diseases, Cancers, Chronic Respiratory Diseases and Diabetes, Figure 5: Risk factors related to Heart Attacks their relevant risk factors according to [25], and the Modifiable Risk factors for Diabetes The patient’s records can be inserted in the according to [26]. In Protégé according to [25] ontology according to the patient are designed instances of diseases for example, demographics, type of visit of the patient, the Heart attacks, Heart Failure, Cerebrovascular healthcare provider, etc. Disease, etc. are Cardiovascular diseases. Each The overall APHRO Ontology metrics of the diseases will have prefLabel, altLabel according to Protégé is described in the Table and SNOMED CT URI accessed on [21] or in 2. the BioPortal [22]. In the figure below are shown some of the Risk Factors in APHRO Table 2 Ontology. Ontology Metrics Metrics No. Axiom 537 Logical axiom Count 227 Declaration axioms No. 156 Class count 74 Object property count 12 Data property count 26 Individual count 43 Annotation Prop. Count 5 SubClassOf 66 Figure 4: Risk Factors It is very important that each of the diseases could be related with the relevant risk factors. 5. Conclusions and Future Work Meanwhile, we can save information about the risk factors according to the patient data and In this paper is designed the Albanian analyze the possible diseases and situation of Patient Healthcare Records Ontology, which the patient. Having information of social includes the patient records, vital signs, risk history and risk factors would give better factors, several diseases, patient visits and some information about the status of the patient and of the medical services in "Mother Teresa" provide better health care for the patient while University Hospital Center in Tirana, Albania. the patient has a visit in the hospital. Also, when it is possible the term in APHRO The diseases are related to the Risk Factor will have its relevant code, concepts in according to [25], using has_Risk object SNOMED CT. property. The Domain of has_Risk property is This ontology can be used in order to gain M., Koch C., Beetz J. (eds) Building knowledge, keep information of the patient Information Modeling. Springer, Cham, records and their visits in different medical 2018. doi:https://doi.org/10.1007/978-3- sectors. Also, APHRO provides the opportunity 319-92862-3_8. to enable interoperability between different [6] C. Villalonga, M. A. Razzaq, W. A. Khan, services, healthcare providers and patient visits H. Pomares, I. Rojas, S. Lee & O. Banos, in order to facilitate the process of the Ontology-Based High-Level Context exchanging health data within them. Inference for Human Behavior In the near future we will integrate Identification. Sensors (Basel, additional concepts in the ontology such as Switzerland), 16 (10), 1617, 2016. family history, services, roles, diseases, doi:https://doi.org/10.3390/s16101617. diagnoses, tests/scans according to the [7] T. Benson, G. Grieve G, Principles of healthcare providers. health interoperability FHRI, HL7 and SNOMED CT. 4rd ed., Springer Nature 6. References Switzerland AG 2021 (Health Information Technology Standards), 2021. doi:https://doi.org/10.1007/978-3-030- [1] V. A. Keramaris, K. Danas, The 56883-2_13. Development of Medical Ontology [8] T.L. Mokgetse, Need of Ontology‐Based “HoPRO” (Hospital PRocess Ontology) Systems in Healthcare System, in V. Jain, and the Role of Ontologies in R. Wason, J.M. Chatterjee and D.‐N. Le Multimethodological SAD Frameworks, (Ed.), Ontology‐Based Information In: Kyriacou E., Christofides S., Pattichis Retrieval for Healthcare Systems, C. (eds) XIV Mediterranean Conference Scrivener Publishing LLC, Wiley, 2020. on Medical and Biological Engineering doi:https://doi.org/10.1002/97811196413 and Computing 2016. IFMBE 91.ch12 Proceedings, volume 57, Springer, Cham, [9] P. Sharma, S. Soman and P. K. Srivastava, (2016). doi: https://doi.org/10.1007/978- An Approach for Implementation of 3-319-32703-7_157. SNOMED-CT in Healthcare Information [2] M. v. d. Schaar, Building next-generation Systems, 2017 14th IEEE INDICON, healthcare systems using distributed (2017) 1-6, doi: machine learning. In International 10.1109/INDICON.2017.8487867. Conference on Distributed Computing and [10] A. Longheu, V. Carchiolo, M. Malgeri, Networking 2021 (ICDCN '21). Medical Data Integration with SNOMED- Association for Computing Machinery, CT and HL7, in: Rocha A., Correia A., New York, NY, USA, 4, (2021). Costanzo S., Reis L. (Ed.), New doi:https://doi.org/10.1145/3427796.3433 Contributions in Information Systems and 935. Technologies. Advances in Intelligent [3] WHO Regional Office for Europe, Systems and Computing, volume 353. Primary health care in Albania: rapid Springer, Cham, 2015. assessment, 2018. URL: doi:https://doi.org/10.1007/978-3-319- https://www.euro.who.int/__data/assets/p 16486-1_115. df_file/0011/373718/alb-phc-ra-eng.pdf [11] A. A. Barrera-Machuca, N. Calderon, A. [4] N. Muro et al., Hygehos Ontology for Anwar, R. Fraser and B. Fisher, Graphical Electronic Health Records. In: Chen YW., Mapping of a Data Ontology for Tanaka S., Howlett R., Jain L. (eds) Descriptive Patient Data, 2019 IEEE Innovation in Medicine and Healthcare Workshop on Visual Analytics in 2016. InMed 2016. Smart Innovation, Healthcare (VAHC), 2019, pp. 48-49, doi: Systems and Technologies, vol 60. 10.1109/VAHC47919.2019.8945031. Springer, Cham. 2016. [12] H. Ajami, H. Mcheick, Ontology-Based doi:https://doi.org/10.1007/978-3-319- Model to Support Ubiquitous Healthcare 39687-3_30. Systems for COPD Patients, Electronics [5] J. Beetz, Structured Vocabularies in 2018, 7, 371, 2018. Construction: Classifications, Taxonomies doi:https://doi.org/10.3390/electronics712 and Ontologies. In: Borrmann A., König 0371. [13] H. B. Elhadj, F. Sallabi, A. Henaien, L. software applications, Nucleic Acids Chaari, K. Shuaib, M. A. Thawadi, Do- Research, volume 39, Issue suppl_2, 1 July Care: A dynamic ontology reasoning 2011, pp. W541–W545. based healthcare monitoring system, doi:https://doi.org/10.1093/nar/gkr469. Future Generation Computer Systems, URL:https://bioportal.bioontology.org/. volume 118, 2021, pp 417-431, ISSN [23] QSUT, 2021. 0167-739X, URL:http://www.qsut.gov.al/. doi:https://doi.org/10.1016/j.future.2021.0 [24] HL7 FHIR, 2021. 1.001. URL:https://www.hl7.org/fhir/observatio [14] J. Shehu, E.Xhina, Modeling an ontology n-vitalsigns.html. for public E-Government Services in [25] World Health Organization, NCDnet, Albania, in International Academic 2021. Conference on Research in Engineering URL:https://www.who.int/ncdnet/about/s and Technology, Barcelona, Spain, 2019. ummary_sheets/en/#. [15] F. N. Al-Aswadi, H. Y. Chan, & K. H. [26] N. Hernandez-Gress and D. Canales, Gan, Automatic ontology construction Socio-Demographic Factors and Data from text: a review from shallow to deep Science Methodologies in Type 2 Diabetes learning trend. Artif Intell Rev 53, pp. Mellitus Analysis," 2016 International 3901–3928, 2020. Conference on Computational Science and doi:https://doi.org/10.1007/s10462-019- Computational Intelligence (CSCI), 2016, 09782-9. pp. 1380-1381. [16] S. Maxhelaku and A. Kika, doi:10.1109/CSCI.2016.0259. Implementation of SPA in Radiology Information System," 2020 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), 2020, pp. 1-5, doi: 10.1109/EAIS48028.2020.9122761. [17] HL7 FHIR, 2021. URL:https://www.hl7.org/fhir/index.html. [18] A. Goldfain, B. Smith, S. Arabandi, M. Brochhausen, W. R. Hogan, Vital Sign Ontology, Proceedings of the Workshop on Bio-Ontologies, ISMB, Vienna, June 2011, pp.71-71. [19] Protégé, 2021. URL:https://protege.stanford.edu/. [20] X. Hu and J. Liu, Orthogonal Defect Classification-based Ontology Construction and Application of Software- hardware Integrated Error Pattern of Software-intensive Systems, 2021 23rd International Conference on Advanced Communication Technology (ICACT), 2021, pp. 1286-1298. doi:10.23919/ICACT51234.2021.937074 7. [21] SNOMED International SNOMED CT Browser, 2021. URL:https://browser.ihtsdotools.org/. [22] P. L. Whetzel, N. F. Noy, N. H. Shah, P. R. Alexander, C. Nyulas, T. Tudorache, M. A. Musen, BioPortal: enhanced functionality via new Web services from the National Center for Biomedical Ontology to access and use ontologies in