Characterization of Telemedicine Patients to Discover Patient

Journeys Using Process Mining

Matías Cornejo T.

, Sebastián Valderrama

and Eric Rojas C.

3,4 c

Faculty of Medicine, Universidad de Chile, Santiago, Chile

Department of Internal Medicina, School of Medicine, Pontificia Universidad Católica de Chile, 7820436, Santiago, Chile

Institute for Biological and Medical Engineering, Schools of Engineering, Medicine and Biological Sciences, Pontificia

Universidad Católica de Chile, Santiago, Chile

Department of Clinical Laboratories, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile

Keywords: Telemedicine, Patient Journey, Patient Profile, Process Mining.

Abstract: Process mining has established itself as a highly valuable tool in healthcare and demonstrated its effectiveness

in process discovery, compliance verification and workflow optimization across a variety of clinical settings.

However, its application in the analysis of telemedicine medical care has not been explored in depth. The

present paper introduces the first stage of the research “Improving the patient journey in telemedicine using

process mining” which aims to optimize the care process in telemedicine. In this initial stage, the

characterization of patients who utilize this model of care in a hospital network in Chile between 2020 and

2023 is conducted. Accordingly, statistical information from the Red de Salud UC-Christus healthcare

network is used to determine the most frequent characteristics of patients in socio-demographic, health-

insurance and clinical terms. Profiles of typical patients who have received treatment via telemedicine will

then be constructed. The preliminary results presented herein will serve as a basis for selecting the type(s) of

patients who are of particular interest to institutional authorities. In the latter stages of the project, information

from the electronic clinical records of the selected patient profiles will be used to build event logs and thereby

construct patient journeys through process mining.

1 INTRODUCTION

Telemedicine has become an important tool with

which to bring healthcare closer to the general

population (World Health Organization [WHO],

2019; Welsh, 2002). Its use has reduced care costs,

improved clinical outcomes and increased user

satisfaction (Manocchia, 2020). Moreover, the

COVID-19 pandemic has given rise to significant

interest in this type of care and has, moreover,

become a public health necessity (Zheng Wong et al.,

2021). Therefore, a more in-depth analysis of its

implementation is required in order to ensure that

health system users continue to receive quality care.

Data science has been an extremely useful

resource in the study of new implementations in

medicine. One of these is process mining, which has

https://orcid.org/0009-0005-2905-1842

https://orcid.org/0000-0003-3913-6661

https://orcid.org/0000-0002-2570-1861

proven to be highly effective in several lines of

research. Therefore, the present study proposes the

use of this discipline in the construction of the patient

journey with telemedicine. This first stage of the

project focuses on the characterization of

telemedicine patients in a private hospital network in

Chile, with the aim of determining the most

appropriate patients to whom this novel technique can

be applied.

This paper first outlines the background of the

topic and the current context of telemedicine in Chile,

in Section 2. Section 3 introduces the objective of this

first stage of the research. Section 4 details the

methodology used in the analysis of the available

information and the subsequent construction of the

patient profiles by the private hospital network.

Section 5 discusses the results obtained. Finally,

T., M., Valderrama, S. and C., E.

Characterization of Telemedicine Patients to Discover Patient Journeys Using Process Mining.

DOI: 10.5220/0012460300003657

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) - Volume 2, pages 723-730

ISBN: 978-989-758-688-0; ISSN: 2184-4305

723

section 6 presents a brief conclusion of the results and

the possible future implications of these findings.

2 BACKGROUND

2.1 Telemedicine

Telehealth encompasses a wide range of tools that use

telecommunication systems for medical purposes

(Welsh, 2002). Among these tools, telemedicine is

defined as the use of information and communication

technologies for the exchange of valid information to

ensure diagnosis, treatment and prevention of

diseases (WHO, 2019).

The use of telemedicine has multiple benefits,

with Mendoza-Alonso et al. (2021) listing these as:

saving time and money, reducing patient absences,

improving health outcomes, decreasing the likelihood

of infections, offering personalized care, and

lowering costs for providers and insurers. However,

the same authors state that telemedicine still faces

certain challenges regarding its correct

implementation, particularly in terms of access to

stable communication networks that are necessary for

its appropriate implementation.

The COVID-19 pandemic had such a profound

impact on the global healthcare system that it

prompted a growth in demand for remote medical

care around the world (Zheng Wong et al., 2021).

With that in mind, telemedicine has been effective in

increasing access to health and medical information

for both patients and physicians since its inception

(WHO, 2019). Chile has been no exception to this

reality, and the Chilean State has set several related

objectives, including to decongest health systems,

improve access to health services, and address the

main challenges involved in implementing this model

(Universidad de Desarrollo [UDD] et al., 2020). In

addition, certain strategies have been proposed to

bring telemedicine closer to the population (Centro

Nacional de Sistemas de Información en Salud

[CENS], 2022). These include guidelines, protocols

and laws that have expanded their use in health

services. (UDD et al., 2020; Mendoza-Alonzo et al.,

2021; Chilean Law No. 21.541, 2023).

2.2 Patient Trajectories

The patient journey is defined as the time series of

encounters with healthcare facilities, healthcare

professionals, a hospital unit or a home health agency

(Beleffi et al., 2020). The patient journey study has

been used as a tool to assess patient satisfaction with

the care process, clinical outcomes, and even to

ensure patient safety during a hospital stay.

Several tools can be used to describe the patient

journey, one of which is process mining (Andrews et

al., 2020; Dahlin et al., 2019, Abo-Hamad, 2018).

Process mining is the bridge between traditional

model-based process analysis and contemporary data

analysis techniques, such as data mining and machine

learning (van der Aalst, 2016). Unlike other process

modeling tools, process mining uses data as empirical

evidence to build process models. It enables

institutions to optimize their workflows from

different perspectives. This is achieved through three

core activities that lie at the heart of process mining:

discovery, conformance checking, and optimization

(van der Aalst, 2016).

To perform these tasks, process mining needs an

event log as its means of input (van de Aalst, 2016).

The event log corresponds to a table that stores data

related to the activities performed in a single process.

The information stored in this table must contain at

least a case ID, the name of the activity and a

timestamp (van der Aalst, 2016). This information

allows for the activities performed for a process to be

traced in each of the cases. In this way, a process

diagram of the workflow of the institution in question

can then be constructed (Imran et al., 2022; Kratsch,

2021).

Process mining has been applied in distinct

industries and has achieved positive results across the

board (Ito et al., 2020). The healthcare sphere has

been no exception, and several studies have

demonstrated the benefits of its use in the medical

field (Kusuma et al., 2021). In particular, the review

conducted by Rojas et al. (2016) demonstrates the

utility of this technique in healthcare. The healthcare

system benefits from the application of process

mining because clinical practice requires a detailed

record of the activities performed by healthcare

personnel on the patient. Additionally, electronic

clinical records facilitate the traceability of events

(Rojas et al., 2016, Kusuma et al., 2021). Crucially,

the information contained within electronic clinical

records can be used to build event logs for process

mining (Arias et al., 2020, Munoz-Gama et al., 2022).

A particular use of process mining in healthcare is

its ability to discover the patient journey throughout

the care process (Andrews et al., 2020; Dahlin et al.,

2019, Abo-Hamad, 2018). Event logs help to identify

the steps patients follow through the different

departments of a hospital (Yang & Su, 2014; Rojas et

al., 2017). Patient pathway analysis allows

inefficiencies in the system to be uncovered (Sulis et

al., 2022) so that institutions can take steps to improve

HEALTHINF 2024 - 17th International Conference on Health Informatics

724

their use of resources and increase patient safety and

satisfaction (Sulis, 2022; Munoz-Gama et al., 2022).

Although data science is widely used in healthcare

(Su et al., 2022; Sarriegi, 2021; Liu, 2020), few

studies have investigated the use of process mining in

telemedicine (Kampeera, 2023; Corallo et al., 2021).

This is important because process mining is quite

flexible and can be adapted to different environments,

taking advantage of the data available for workflow

analysis (van der Aalst, 2016). It therefore has

tremendous potential to analyze the patient journey

and help to identify patterns that facilitate a more in-

depth understanding of that journey.

With that in mind, this project aims to use process

mining to construct the telemedicine patient journey,

and subsequently compare this trajectory with that of

patients who receive face-to-face treatment. The

objective is to determine whether telemedicine is

equivalent to the traditional care model with respect

to clinical and administrative aspects of the care

process.

In this first stage of the project, the data contained

in the information system of a private hospital

network will be analyzed to characterize the patients

who have received medical and non-medical care via

telemedicine. To undertake this characterization,

socio-demographic (sex, age, area of residence),

health insurance (publicly or privately financed) and

clinical (medical specialty) aspects will be

considered.

3 OBJECTIVES

The objectives of the present study are to characterize

the patients who receive telemedicine care according

to their socio-demographic realities and the medical

specialty sought via this model, to subsequently

discover patient journeys using process mining.

The purpose is to determine the benefits and

drawbacks of using process mining in the analysis of

patient trajectories in different clinical settings,

particularly in telemedicine and face-to-face care.

4 METHODOLOGY

First, an exploration of the available information will

be carried out to identify the types of patients who

choose either telemedicine or face-to-face care. For

the present study, the patient database of the Red de

Salud UC-Christus network in Santiago de Chile will

be used. In particular, the commercial database of the

Red de Salud UC-Christus network is analyzed,

which contains not only socio-demographic

information on patients, but also data regarding the

clinical specialties in which this model of care is

available, in addition to the type of financing the

institution receives from these patients. The use of

anonymized data has the approval of Scientific

Ethical Committee of Health Sciences of the

Pontificia Universidad Católica de Chile.

Second, the most relevant patient characteristics

will be defined. Specifically, analysis will be

undertaken of sex, age, district and region of

residence, financing, number of patients and number

of consultations for each of the health specialties that

provide telemedicine care.

Third, the characteristics will be explored

according to the interest of the clinical experts of the

Red de Salud UC-Christus network. First, the total

number of patients and consultations undertaken will

be made for both sexes between 1

June 2020 and 1

June 2023. Subsequently, a similar analysis will be

conducted over three one-year periods. The number

of patients and consultations related to each of the

specialties accessed during the three years will then

undergo analysis. The place of residence of the

patients will also be considered for all specialties.

Once this information has been aggregated, the

patient profiles related to the telemedicine model will

be created. To do so, the most frequently attending

sex will be analyzed first, followed by their most

likely place of residence (the most common district),

the most demanded specialty, and finally the most

commonly used type of health insurance. Analysis of

the other sex will then take place according to the

same order. Subsequently, a profile will be devised

which considers the second and third most common

place of residence. This characterization will help to

provide a more in-depth understanding of the

population that chooses the telemedicine model of

care, to focus the subsequent phases of the project on

more precise data.

Finally, the criteria with which to determine the

type of patient whose journey is to be discovered will

be defined. Clinical and administrative characteristics

of interest to clinical experts will be considered, as

well as institutional interests related to the growth of

the Red de Salud UC-Christus network.

In future research, a quality control of the data

extracted from the electronic clinical records of the

healthcare institution will be performed, followed by

the construction of the necessary event log to model

the patient journey through process mining.

Subsequently, process discovery algorithms will be

applied to this event log to obtain the patient journey.

Characterization of Telemedicine Patients to Discover Patient Journeys Using Process Mining

725

In the final analysis, the patient journeys obtained in

the previous step will be compared, in conjunction

with clinical experts, who will guide the work

according to the requirements of the institution’s

medical team.

5 RESULTS

5.1 Characterization

The present study analyzed data related to patients

from the Red de Salud UC-Christus network who

received telemedicine care during the three-year

period studied, from 1

June 2020 to 1

June 2023.

The data was obtained from the commercial statistics

belonging to the hospital network, which includes

information on age, sex, place of residence, health

insurance, number of patients, number of

consultations and specialties.

A total of 152,422 patients and 354,660

consultations were obtained, of which 52.6% of

patients are female and 30.8% are male, with the

remainder failing to disclose information on their sex.

The average age of the patients is 39.3 years for

females and 38.4 years for males. Figure 1 shows the

distribution of patients by sex and age.

Regarding medical specialties, 92 were analyzed

in total. The most sought specialties were adult

psychiatry, general medicine, and adult neurology,

with more than 13,000 patients accessing each one

during the three-year period studied. Figure 2 shows

the top ten specialties in terms of overall patient

numbers.

Figure 1: Distribution by sex and age of patients using

telemedicine in the Red de Salud UC-Christus network

between 1

June 2020 and 1

June 2023. Patients from the

30-40 age range are the most active users of telemedicine.

Regarding the geographical location of the

patients, it was found that of the 16 regions that

constitute Chile, the Metropolitan Region accounted

for 62.5% of all telemedicine care recieved, followed

by the Los Lagos Region with 8.3%. No other region

accounts for more than 8.3% of the national total. The

municipalities with the highest number of

consultations were Santiago, Las Condes, Ñuñoa and

Antofagasta.

Figure 2: No. of patients accessing each specialty across the

country between 1

June 2020 and 1

June 2023, in relation

to the ten most commonly accessed specialities.

Regarding distribution within the regions, it was

found that the population that uses the Red de Salud

UC-Christus network telemedicine the most lives in

the largest cities and that the number of patients

decreases in more peripheral areas near those cities.

For example, in the metropolitan region, which has

62% of the patients, most of them are in the city of

Santiago, where the UC-Christus Network is located,

while the outlying cities have fewer patients.

In addition, the data was analyzed over three 12-

month periods in order to observe the evolving

behavior of patients as the COVID-19 pandemic

progressed. Specifically, the following periods were

determined: 1

June 2020 to 31

May 2021 (20-21);

Figure 3: Number of patients and consultations for the 20-

21, 21-22 and 22-23 periods. A gradual drop in both

parameters is observed year-on-year.

HEALTHINF 2024 - 17th International Conference on Health Informatics

726

June 2021 to 31

May 2022 (21-22); and 1

June

2022 to 1

June 2023 (22-23). Figure 3 shows the

decrease in patients and consultations in the periods

described. The number of patients is shown in blue

and the number of consultations in yellow. The

number of patients decreased by 11.7% between 20-

21 and 21-22, and by 22.6% between 21-22 and 22-

23. Furthermore, consultations fell by 17.3% between

20-21 and 21-22 and by 20.43% between 21-22 and

22-23.

Subsequently, patients were analyzed according

to their sex and type of health insurance scheme held.

Chilean healthcare operates with a mixed financing

system that includes privately financed and

administered companies (the majority of insurers),

privately financed State-owned companies, and

public institutions with mixed public-private

contributions and State administration. Table 1 shows

the number of patients by sex for each type of

insurance held in the period 2020-2023. Note that the

discrepancy between the number of patients listed in

Table 1 compared to the number listed on the

healthcare network’s general database is due to the

fact this more detailed data is not necessarily

available for all patients.

The largest single group of patients (49,931, or

38.35%) financed their telemedicine care through

‘Other financing’, i.e., by means of another type of

insurance or private payment. The second largest

group of patients are beneficiaries of Fonasa, the main

public insurance provider in the country (19,527

patients), representing 15.00%. Private financing

reaches 45.84% (59,694 patients) and only one type

exceeds the total number of Fonasa patients

(Colmena). State-owned companies constituted only

1,020 patients, representing just 0.78%.

Table 1: Number and sex of patients who received

telemedicine care in the Red de Salud UC-Christus network

between 1

June 2020 and 1

June 2023 by health insurance

type.

5.2 Patient Profiles

This data can then be utilized to compile profiles of

patients who receive telemedicine care from the

hospital network. The patient profile consists of the

characteristics most likely to be found in any patient

of the healthcare institution, and considers each

characteristic as the most common for each profile,

based on sex and geographic location:

Sex: Female

Approximate age: 35-39 years old

Residence: Santiago,

Metropolitan Region

Specialty: Psychiatry

Financing: Convenio/Particular

(Medical contract/Private)

Sex: Male

Approximate age: 34-38 years old

Residence: Las Condes,

Metropolitan Region

Specialty: General Medicine

Financing: Convenio/Particular

(Medical contract/Private)

Sex: Female

Approximate age: 35-39 years old

Residence: Viña del Mar,

Valparaiso Region

Specialty: Neurology

Financing: Fonasa

The methodology proposed for data analysis and

patient profiling can be replicated in other institutions

with detailed socio-demographic information such as

that presented in this article.

5.3 Preparing Event Logs to Discover

Project Trajectories

To prepare the event logs, it is necessary to determine

the minimum data characteristics that will be

required. As described by van der Aalst (2016), event

logs store activity information, including case

identification data, activity identification and a

timestamp that allows for the differentiation of each

activity in the flow and ensures the traceability of

activities.

In conjunction with the clinical experts, the most

relevant profiles will be selected. Subsequently, the

event data stored in the electronic clinical record of

the Red de Salud UC-Christus network will be

extracted. To reiterate, the electronic clinical register

already functions based on a structure that allows

users to identify the minimum requirements for the

Characterization of Telemedicine Patients to Discover Patient Journeys Using Process Mining

727

construction of an event log. Table 2 provides an

example of what an event log would look like for the

patients.

Table 2: Example of an event log with clinical data.

Case ID Activity Timestamp Doctor

001 First consultation 2020/06/03 12:05:54 Dr Q.

002 Laboratory test 2021/10/05 11:58:06 Dr M.

004 Radiology test 2020/08/06 15:26:34 Dr Q.

001 Referral to specialty 2021/25/06 14:15:23 Dr L.

003 2nd consultation 2022/04/12 16:03:56 Dr X.

004 Referral to specialty 2020/08/07 15:06:05 Dr Q.

6 DISCUSSION

Preliminary results show that a diverse population of

patients is accessing telemedicine care from the Red

de Salud UC-Christus network. Yet, it is possible to

identify common characteristics that increase the

likelihood of finding one type of patient profile over

another. For example, the typical telemedicine patient

in the network is generally an adult, lives in the

Metropolitan Region, and is most likely female. In

addition, the data demonstrates that this typical

telemedicine patient finances their care privately.

The main specialties requested in telemedicine are

psychiatry, neurology and nutrition, which may be

due to the fact that these types of consultations are

easier to adapt to telemedicine than those requiring

physical analysis. However, the field of general

medicine is noteworthy because it represents the

second most requested type of consultation, in terms

of total number of patients. This is explained by the

fact that patients first consult in general medicine and

are then referred to a specialist.

When analyzing the geographic location of the

patients, it is observed that they are mainly

concentrated in large cities. This can be explained by

the fact that cities have larger populations than small

and remote towns. However, it is worth deliberating

whether the goal of telemedicine to bring healthcare

systems closer to remote populations is still being

met, as evidence shows that people with better access

to healthcare are those who use this model of care the

most.

When analyzing the number of patients and

consultations by period, an increasing drop in the

number of patients and consultations year-on-year

can be observed. There are two possible explanations

for this phenomenon: first, the end of the COVID-19

pandemic has resulted in patients preferring face-to-

face care once more; and second, patients have

decided to seek care in other healthcare centers.

Either way, greater amounts of data are required to

identify the reasons for the drop in patient numbers.

Since the patient profiles compiled in the present

study are based on statistics from the healthcare

institution rather than the electronic health record, a

more in-depth analysis is required to develop a more

detailed profile of users of the health services

provided by this hospital network. However, the

characterizations herein will allow clinical experts to

be consulted on a selection of the patient profiles that

are of particular interest to them and the healthcare

provider itself.

Another limitation of this project is that the study

is carried out in a single health institution. However,

the methodology proposed for the characterization

can be used in other centers that have this type of

registry. This allows for a multicenter comparison of

the results.

It should be noted that in the development of this

research, challenges related to data quality will arise.

To address this issue, the guidelines set out in

ISO/IEC 25012 will be followed and the relevance of

all data will be discussed with clinical experts.

In addition, it should be mentioned that, when

dealing with personal data, the correct use of sensitive

information will have to be considered to keep the

identity and integrity of users protected. In this same

sense, anonymized data will be used with the

approval of the Scientific Ethical Committee of

Health Sciences of the Pontificia Universidad

Católica de Chile.

Another challenge is that the data will not allow

traceability of events. This will be addressed by

working directly with the administrators of the

information systems to ensure that the time stamp of

each event is included.

7 CONCLUSIONS AND FUTURE

WORK

These preliminary results provide an improved

understanding of the universe of patients who use the

telemedicine service provided by the Red de Salud

UC-Christus network. Moving forward, it will be

possible to conduct a more rigorous analysis of how

telemedicine care is implemented across the network.

Such analysis will give rise to greater clarity on the

requirements needed to build an event log with which

to identify patient journeys.

Future efforts will involve a more thorough

analysis to establish an event log for identifying

patient journeys. Further work includes a literature

HEALTHINF 2024 - 17th International Conference on Health Informatics

728

review for additional patient characterization

methods, a study on the pros and cons of using

process mining in telemedicine research and

extracting patient data for journey discovery. The

subsequent comparison of telemedicine and face-to-

face care journeys aims to identify differences across

patient types, specialties, and diagnoses, offering

insights for improvement and informed decision-

making in patient care.

ACKNOWLEDGEMENTS

We thank the Red de Salud UC-Christus for their

collaboration in the execution of this project. We

thank the Universidad de Chile and the Pontificia

Universidad Católica de Chile for their support to this

research and the academia. Additionally, we thank

FONDECYT for their support of this research and

their ongoing assistance to the scientists of Chile.

This project is part of the FONDECYT

project #11230708 “Improving the Patient Journey in

Telemedicine using Process Mining”.

REFERENCES

World Health Organization. (2019). Recommendations on

Digital Interventions for Health System Strengthening

edition. WHO.

Welsh, T. (2002). Organizational structure of telehealth

care: an examination of four types of telemedicine

systems four types of telemedicine systems. PhD diss.,

University of Tennessee.

Manocchia, A. (2020). Telehealth: Enhancing Care through

Technology. Rode Island Medical Journal, 103(1), 18-

20. pubmed.ncbi.nlm.nih.gov/32013298

Mark Yu Zheng Wong, Dinesh Visva Gunasekeran, Simon

Nusinovici, Charumathi Sabanayagam, Khung Keong

Yeo, Ching-Yu Cheng, and Yih-Chung Tham. (2021).

Telehealth demand trends during the covid19 pandemic

in the top 50 most affected countries: Infodemiological

evaluation. Journal of Medical Internet Research

Public Health and Surveillance, 7(2):e24445, 2021

Universidad del Desarrollo, Universidad de Concepción, &

UC. Davis Chile Life Sciences Innovation Center.

(2020). Fundamentos para los Lineamientos para el

Desarrollo de la Telemedicina y Telesalud en Chile (2°

Edición)[PDF]. Extracted on October 19

, 2023 from

lineamientostelesalud.cl/2021/01/segunda-edicion-de-

los-fundamentospara-los-lineamientos-para-la-

telemedicina-y-telesalud-en-chile

Centro Nacional de Sistemas de Información en Salud.

(2022) Propuesta Colaborativa para Implementar la

Telemedicina en Chile [PDF]. Extracted on October

, 2023, from https://cens.cl/wp-

content/uploads/2022/07/Propuesta-Telemedicina-

jul2022.pdf

Mendoza-Alonzo, P., Mendoza-Alonzo, J. (2021).

Telemedicine: expected challenges in Chile based on

the experience in the United States during the

pandemic. Revista Médica de Chile, 149(8).

Modifica la normativa que indica para autorizar a los

Prestadores de Salud a efectuar atenciones mediante

Telemedicina. Ley N° 21.541. March 3

, 2023 (Chile).

van der Aalst, W. (2016). Data Science in Action. In:

Process Mining. Springer, Berlin, Heidelberg.

Imran, M., Maizatul, I., Hamid, S., Nizam, M. (2022).

Complex Process Modeling in Process Mining: A

Systematic Review. IEEE Access. 10.

Kratsch, W. (2021). Data-driven Management of

Interconnected Business Processes - Contributions to

Predictive and Prescriptive Process Mining. EPub

Bayeruth. epub.uni-bayreuth.de/id/eprint/5329/

Ito, S., Vymětal, D., & Šperka, R. (2020). Process mining

approach to formal business process modelling and

verification: a case study. Journal of Modelling in

Management, 16(2), 602-622.

Rojas, E., Munoz-Gama, J., Sepulveda, M., Capurro, D.

(2016). Process mining in healthcare: A literature

review. Journal of Biomedical Informatics 61.224–236.

Kusuma, G. P., Kurniati, A. P., Rojas, E., Mcinerney, C.,

Gale, C. P., & Johnson, O. A. (2021). Process Mining

of Disease Trajectories: A Literature Review. IOS

Press eBooks.

Arias, M., Rojas, E., Aguirre, S., Cornejo, F., Munoz-

Gama, J., Sepúlveda, M., Capurro, D. Mapping the

Patient’s Journey in Healthcare through Process

Mining. Int. J. Environ. Res. Public Health 2020, 17.

Munoz-Gama, J., Martin, N. D., Fernandez-Llatas, C.,

Johnson, O. A., Sepúlveda, M., . . . Zerbato, F. (2022).

Process mining for healthcare: Characteristics and

challenges. Journal of Biomedical Informatics, 127,

103994.

Yang, W., & Su, Q. (2014). Process mining for clinical

pathway: Literature review and future directions.

(2014). In 11th International Conference on Service

Systems and Service Management (ICSSSM), Beijing,

China, 2014, pp. 1-5.

Rojas, E., Sepúlveda, M., Munoz-Gama, J., Capurro, D.,

Traver, V., Fernandez-Llatas, C. (2017). Question-

Drive Methodology for Analyzing Emergency Room

Processes Using Process Mining. Applied Science,

7(3):302.

Guzzo, A., Rullo, A., & Vocaturo, E. (2022). Process

mining applications in the healthcare domain: A

comprehensive review. Wiley Interdisciplinary

Reviews: Data Mining and Knowledge Discovery,

12(2), e1442.

Erdogan, T. and Tarhan, A., Systematic Mapping of

Process Mining Studies in Healthcare, IEEE Access, 6,

pp. 24543-24567, 2018.

Rinner, C.; Helm, E.; Dunkl, R.; Kittler, H.; Rinderle-Ma,

S. (2018). Process Mining and Conformance Checking

of Long Running Processes in the Context of

Characterization of Telemedicine Patients to Discover Patient Journeys Using Process Mining

729

Melanoma Surveillance. International Journal of

Environmental Research and Public Health, 15, 2809.

Andrews R, Wynn MT, Vallmuur K, ter Hofstede AHM,

Bosley E. (2020). A Comparative Process Mining

Analysis of Road Trauma Patient Pathways.

International Journal of Environmental Research and

Public Health. 17(10):3426.

Dahlin S, Eriksson H, Raharjo H. (2019). Process Mining

for Quality Improv: Propositions for Practice and

Research. Quality Management in Health Care.

28(1):8-14.

Abo-Hamad W. (2018) Patient Pathways Discovery and

Analysis Using Process Mining Techniques: An

Emergency Department Case Study. In: Cappanera, P.,

Li, J., Matta, A., Sahin, E., Vandaele, N., Visintin, F.

(eds) Health Care Systems Engineering. ICHCSE 2017.

Springer Proceedings in Mathematics & Statistics, vol

210. Springer, Cham.

Beleffi, E., Mosconi, P., & Sheridan, S. E. (2020). The

patient journey. Springer eBooks (pp. 117-127).

Sulis, E., Amantea, I. A., Aldinucci, M., Boella, G.,

Marinello, R., Grosso, M., Platter, P., & Ambrosini, S.

(2022). An ambient assisted living architecture for

hospital at home coupled with a process-oriented

perspective. Journal of Ambient Intelligence and

Humanized Computing.

Su, J., Zhang, Y., Ke, Q., Su, J., & Yang, Q. (2022).

Mobilizing artificial intelligence to cardiac

telerehabilitation. Reviews in Cardiovascular

Medicine, 23(2), 045.

Sarriegi, J. K., Beristain, A., Sánchez, R. H., Graña, M.,

Rebescher, K. M., … Konstantinidis, E. I. (2021).

COLAEVA: Visual Analytics and Data Mining Web-

Based Tool for Virtual Coaching of Older Adult

Populations. Sensors, 21(23), 7991.

Liu, J., Zhang, W., Jiang, X., & Zhou, Y. (2020). Data

Mining of the Reviews from Online Private Doctors.

Telemedicine Journal and E-health, 26(9), 1157-1166.

Extraído de:doi.org/10.1089/tmj.2019.0159

Kampeera, W. (2023). The implementation of telemedicine

to reduce doctor visits in the social medicine clinic at

Hatyai hospital. Journal of the Thai Medical Informatic

Association, 9(1), 42-51.

Angelo Corallo, Mariangela Lazoi, Roberto Paiano, and

Fabrizio Striani. (2021). Application of Process Mining

in Teleconsultation Healthcare: Case study of Puglia

Hospital. In Proceedings of the 10th International

Conference on Information Systems and Technologies

(ICIST '20). Association for Computing Machinery,

New York, NY, USA, Article 32, 1–13.

International Organization for Standardization. (2008).

Software engineering -- Software product Quality

Requirements and Evaluation (SQuaRE) -- Data quality

model (ISO/IEC Standard No. 25012). Retrieved from

https://www.iso.org/standard/35736.html

HEALTHINF 2024 - 17th International Conference on Health Informatics

730