This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Rehabilitation and Assistive Technology, is properly cited. The complete bibliographic information, a link to the original publication on http://rehab.jmir.org/, as well as this copyright and license information must be included.
Advanced sensor, measurement, and analytics technologies are enabling entirely new ways to deliver health care. The increased availability of digital data can be used for data-driven personalization of care. Data-driven personalization can complement expert-driven personalization by providing support for decision making or even by automating some parts of decision making in relation to the care process.
The aim of this study was to analyze how digital data acquired from posture scanning can enhance physiotherapy services and enable more personalized delivery of physiotherapy.
A case study was conducted with a company that designed a posture scan recording system (PSRS), which is an information system that can digitally record, measure, and report human movement for use in physiotherapy. Data were collected through interviews with different stakeholders, such as health care professionals, health care users, and the information system provider, and were analyzed thematically.
Based on the results of our thematic analysis, we propose three different types of support that posture scanning data can provide to enhance and enable more personalized delivery of physiotherapy: 1) modeling the condition, in which the posture scanning data are used to detect and understand the health care user’s condition and the root cause of the possible pain; 2) visualization for shared understanding, in which the posture scanning data are used to provide information to the health care user and involve them in more collaborative decision-making regarding their care; and 3) evaluating the impact of the intervention, in which the posture scanning data are used to evaluate the care progress and impact of the intervention.
The adoption of digital tools in physiotherapy has remained low. Physiotherapy has also lacked digital tools and means to inform and involve the health care user in their care in a person-centered manner. In this study, we gathered insights from different stakeholders to provide understanding of how the availability of digital posture scanning data can enhance and enable personalized physiotherapy services.
Health care is becoming increasingly data-driven [
Researchers have envisioned that in this form of participatory health care, the role of the health care professional is to complement the health care user’s own resources in managing their health so that the combined resources of these stakeholders will lead to the most optimal decisions regarding care [
In health care, personalization often takes place in the interactions between the stakeholders; it involves the collective use of different health care technologies and the health care service system where the service is delivered [
Many studies have concluded that adoption of digital tools to support rehabilitation practice remains low, even though physiotherapists see potential in digitally supported rehabilitation [
Service design is a set of design methods which integrate the possibilities and means to design and deliver a service while keeping the stakeholders, context, and other service development challenges at its heart [
In this study, we aimed to investigate how the availability of a new set of digital data, namely posture scanning data, can enhance and enable more personalized delivery of physiotherapy. The research question we asked is:
To answer our research question, we conducted a case study. Case studies are useful when there is a need to understand a complex social phenomenon that occurs in a real-world setting [
The study was conducted as part of a development and research project involving four partners in three countries: Finland, Sweden, and the Netherlands. The PSRS was designed by the Swedish company Qinematic AB, has been commercially available since 2017, and has been continuously developed since then. The data collection and analysis were led by the University of Oulu in Finland in collaboration with the Swedish research institute RISE SICS and Bright Cape. Interviews with Qinematic personnel and the health care users were conducted in Sweden. Interviews with the health care professionals were conducted in the Netherlands.
The PSRS is an information system solution that can be used in physiotherapy to record, measure, analyze, and report a health care user’s movement and posture at the point of care. This functionality is expected to increase the personalization of care by providing a more accurate understanding of the physiology of a specific health care user, better communication of the user’s medical condition and the effectiveness of care, and better targeting of care. The PSRS consists of two main information system components: Qinematic Posture Scan and Qinematic Movement Lab. The first component, PSRS Posture Scan, is used by the health care professional to objectively assess the health care user’s movement through an image processing system. The second component, the PSRS Movement Lab, is used as a communication and reporting tool between the health care professional and the health care user. Health care professionals can use this system to create a therapy training plan that includes rehabilitation-related exercises (type, interval, and frequency of exercise), administer questionnaires, and schedule follow-up physiotherapy assessments. Health care users can report their exercise adherence and respond to prompted questionnaires (eg, to report pain).
At the time of the interviews, the PSRS Posture Scan was fully developed and in use, whereas the PSRS Movement Lab was still under development. Therefore, as no functional software for the PSRS Movement Lab existed at the time, a paper prototype [
A storyboard is a narration that describes the stakeholders’ activities when using a service [
Storyboard depicting the use of posture scanning in the physiotherapy care pathway.
The storyboard starts by presenting Michael, a sedentary worker who suffers from pain and decreased movement (A). Michael consults a health care professional; after providing certain information, such as gender, age, body weight, a discomfort report with International Classification of Disease, Tenth Revision (ICD-10) comfort pain areas, and a fall report as a potential indicator of inability to perform the movements to be scanned, he is scanned by the Posture Scan at the point of care (B). The Posture Scan uses machine learning algorithms to analyze Michael’s movement levels (C). Once the scan is completed successfully, a report about Michael’s movement is generated for Michael and the health care professional. The health care professional analyzes the aggregated data (D) and discusses the results with Michael (E) to create a personal training plan for Michael using Movement Lab. Michael can see the therapy training using the Movement Lab application and commits to performing the prescribed exercises at home (F). Michael reports his progress to the health care professional using Movement Lab (G). After some time, Michael’s posture may improve (H), and the improvement will become visible in a new Posture Scan. Between the initial posture scan and the possible improvement of Michael’s posture, Michael and the therapist may be in contact via the PSRS Movement Lab and may have physical meetings to evaluate the effects of the exercises and adjust them if necessary.
The interviews represent our primary data. The data were collected between February and May 2018. The participants were informed of the nature of the study and signed an informed consent form. The stakeholders interviewed were Qinematic staff, healthy individuals who represented health care users, and health care professionals in the physical therapy domain. In the interviews, we followed a protocol where one researcher always led the conversation while a second researcher took field notes. All interviews were audio-recorded and transcribed. Interviews with Qinematic staff and health care users were conducted in English, while the interviews with health care professionals were conducted in Dutch. Dutch to English translation was performed by AB, who conducted the interviews with the health care professionals and is a native Dutch speaker.
Qinematic staff: We conducted a group interview (90 minutes) with a service designer and a human movement scientist. The aim was to gain a general understanding of the design and development of the PSRS, the role of the PSRS in health care, and the challenges and decision-making process regarding personalization. We also asked about the role of the PSRS in supporting the health care professional and the health care user in personalization.
Health care users: We conducted seven semistructured interviews (average 45 min) with healthy individuals (all adult volunteers) who were recruited for the user study to collect user experiences and expectations regarding the use of the PSRS. Personalization was a theme in the interview. The interviewees were asked to consider how the PSRS could ideally be integrated with their needs, what value this could create, and what type of personalization they would expect to receive while using the PSRS. As the interviewees did not have prior experience with the PSRS or with any other form of human movement analysis system, they each underwent a Posture Scan (at the Swedish research institute) and had a discussion with the health care professional before the interview.
Health care professionals: We conducted two group interviews and nine semistructured interviews (average length: 45 minutes) with 13 health care professionals (5 general physiotherapists, 2 personal trainers, 3 occupational physiotherapists, 1 movement therapist, and 2 manual therapists) who worked with health services in physiotherapy. Interview themes concerned the role and use of information systems as part of health service delivery and the professionals’ work practices in general, with more focused questions about the support that the PSRS can provide for the health care professional to treat the individual health care user. As only one health care professional had prior experience with the PSRS, we demonstrated the Posture Scan and reporting procedure of the Movement Lab with paper prototypes before the interviews.
The collected data were analyzed thematically [
Based on our data analysis, we identified three different types of support that posture scanning can provide to enhance and enable a more personalized delivery of physiotherapy: 1) Modeling the condition, in which the posture scanning data are used to understand the health care user’s current condition and the root cause of the possible problem or pain; 2) visualization for a shared understanding, which includes themes about the use of posture scanning data to enable health care users to be more informed about and involved in their care decisions; and 3) evaluating the impact of intervention, which includes themes related to the use of posture scanning data as a new means for the stakeholders to monitor and evaluate the impact of the intervention. An overview of the three types of support is shown in
Three types of support posture scanning can provide for data-driven personalization of physiotherapy.
The first type of support concerns the use of posture scanning data to model the current movement levels and condition of the individual health care user who is seeking help. As the health care user consults the health care professional (Screen A in the storyboard) and verbally expresses discomfort, the posture scanning data can provide information to complement the health care user’s verbal description. However, the actual root cause of the problem may be a dysfunction that is challenging for the health care user to verbally describe. With vague descriptions, the evaluation of the health care user’s current condition may take longer; however, the data can support the health care professional in understanding the condition and the possible root cause of the pain (Screen B):
(If the health care user has pain in the knee) the health care professional can see that the knee is not the problem. The problem is the weak hip that causes the pain to the knee.
If the problem of the health care user is not clear [for example difficulty with getting out of the chair], it can be a trigger to do the Posture Scan because that can yield results sometimes. If it is a medical thing you need a physiotherapist, but with vague complaints the Posture Scan can give some useful information.
The posture scanning data is processed through machine learning algorithms (Screen C) that quantify movement and enable monitoring of progress and potentially identify the cause of pain. The quantification of movement levels supports the health care professional in defining the baseline for care (ie, the care starting point for the individual health care user) (Screen D).
The second type of support concerns the use of posture scanning data in reaching a shared understanding on the care options. Posture scanning can be used to visualize the health care user’s movement levels through data displays, which can then be used to guide the discussion between the health care professional and the health care user. The health care users were expecting the health care professional to be active in explaining the care options and leading the decision-making regarding the care options; however, the visualization through data displays also provided a means for the health care user to be more informed and involved in the discussions:
We call this like a communication tool between health care professional and health care user. With this system, the health care professional can say to a health care user that you still have pain, but your movement is much better so keep going with [the rehabilitation].
The communication with the health care user now goes via WhatsApp and that is just easily accessible and quick. Via PC it is a step back. I would use the scan to show progress. Then I can numerically show people that they are doing better.
The importance of reaching common ground and keeping the health care user informed was also prevalent in the case of motivation. The level of motivation to commit to the exercises was discussed by the health care professionals, as they reported using different motivational techniques and pep talks to address the importance of the exercises. The need for these techniques was apparent, as the health care users were not always motivated to commit to and follow the care options that were verbally discussed and agreed upon at the appointment:
Most people just do not want to do exercises. Of course, these exercises are somewhat boring, but that is why you have to try and find a way and think with your health care user. What they have to do and when.
Visualization through data displays can be an informative and illustrative way to represent the movement levels to the health care user (Screen E). Visualizing the potentially decreased movement levels can be a more concrete way to illustrate the connection between the potential problem or pain and the care options and prescribed exercises.
The third type of support concerns the impact evaluation of the intervention. As the health care user conducts the prescribed exercises using the Movement Lab (Screen F), the aggregated data help the health care professional monitor the care process. The data also provide evidence that the prescribed exercises have been effective (Screen G) and that the movement has potentially improved. In some cases, the health care user’s pain level may not yet have changed, even though their movement levels may have already improved:
If, for example, my back pain has not improved, I expect some personalized help from the health care professional. Maybe exercises need to be changed or the time plan.
In such cases, the aggregated data were seen to be especially useful:
I would use the scan to show progress. Then I can numerically show people that they are doing better.
The evaluation of the impact of the intervention also included a comparison of the aggregated data sets. Comparison of data can show whether the health care user’s movement levels have improved (Screen H). In addition, the data aggregated by Posture Scan and the data that health care users report using Movement Lab can be used as a basis to collaboratively evaluate why the movement levels and pain levels have not (yet) improved:
You can compare scan 1 and 2. The health care user can say that s/he has done the exercises but has not improved. The exercise may be wrong, or the health care user has done the exercise wrongly or has not done the exercises at all.
In the case that their condition did not improve, the health care users expected personalization of care in a way that considered the aggregated data:
If I get exercises to do every day, I will do it, but I also want to do another scan to see the progress. If there has been progress, fine, but if not then I want to contact the health care professional and get an appointment.
The aggregated data provide a means for the health care professional and the health care user to consider and evaluate the potentially changed movement levels and pain levels of the health care user. The aggregated data also provide evidence for the health care professional to evaluate the impact of the intervention and to consider with the health care user what to change and do differently; this can result in a more personalized care process.
This study investigated how the availability of a new set of digital data, namely posture scanning data, can support and enable more personalized delivery of physiotherapy. We propose that posture scanning data can provide three different types of support to enhance traditional expert-driven physiotherapy and to help personalize the delivery of physiotherapy. The three types of support that we identified and described are 1) modeling the condition, 2) visualization for shared understanding, and 3) evaluating the impact of the intervention. Through our case study, we also described the potential to create value from the data. This knowledge can help to ease the adoption of information systems in physiotherapy, which still remains low in practice [
The findings of this study show that posture scanning data can provide new means to deliver and co-create a care service. The aggregated posture scanning data can be used to quantify the health care user’s movement levels, which provides new means for the health care professional to evaluate the health care user’s movement condition. The visualization of data can also be illustrative for the health care user to be more involved and informed regarding their movement and physical therapy. This provides new possibilities to increase the agency of the health care user, which can improve their quality of health (eg, through better adherence) [
Our findings show how the posture scanning data can be blended into the traditional physiotherapy service encounter and how they can be seamlessly integrated into the care practice. Increasing amounts of data about the individual health care user can be aggregated through different devices and sensors. The findings of this study increase our understanding of the value of these data for the core stakeholders in the context of physiotherapy.
As people collect more personal data about themselves and organizations store information on their interactions with people [
Lee [
Service design is not often used in health care [
Like most research, this study has limitations. First, the reported case study was conducted in Northern European countries, and all the study participants were working in these countries. Therefore, this study does not account for cultural differences worldwide, which can be considered as a limitation to the generalizability of the results. Second, we collected data from different stakeholder viewpoints; however, for ethical reasons, the health care users were healthy individuals who were recruited through purposeful sampling. However, as the PSRS can also be used to provide data for healthy individuals who are interested in their movement levels, we believe that even though the users were not currently in need of physiotherapy, they were capable of reliably expressing a user’s viewpoint, opportunities, and expectations regarding personalization.
Health care is becoming increasingly data-driven. The availability of digital data can be used for data-driven personalization, providing opportunities to align the care process more closely with the needs of an individual health care user in a person-centered manner. In physiotherapy, the adoption of digital tools that can support rehabilitation practice has remained low; however, personalization is considered to be the key factor in the adoption of digital technologies. This study contributes to this area of research by proposing three different types of support that digital data acquired from posture scanning can provide to enhance and enable more personalized delivery of physiotherapy. The results of this work provide insights for the design of personalized health care services that consider the viewpoints of different stakeholders in the future of personalization. Future research could also investigate and measure the effects of using a posture scan system and its data on the outcome of the physiotherapy service—for example, does the use of the system shorten the time required for health care users to recover from a certain type of health problem or overcome pain in a specific body part? Future research could also investigate in more detail how the viewpoints of the three different stakeholder groups—health care professionals, health care users, and information system providers—should be integrated when designing personalized health care services.
artificial intelligence
electronic health record
International Classification of Disease, Tenth Revision
posture scan recording system
Author GB is the founder of Qinematic, and author TK is an employee of Qinematic.