DataPDF Available
§SMS costs for both health providers and patients can be saved
§Patients’ interactions are way more efficient with pre-defined
answer options such as Likert-scales, pictorial scales, image
upload, or video clips among many more
§Integration of sensor data from the smartphone and external
devices for micro-interventions and digital biomarkers
§Delivery of just-in-time adaptive interventions by sensing the
state of receptivity, opportunity and vulnerability of patients
§Full control of the data in contrast to other messaging platforms
like WhatsApp, iMessage or Facebook Messenger.
§Non communicable diseases (NCDs) such as cardiovascular
diseases, asthma, obesity or diabetes impose the greatest
burden on global health.
§However, health personnel is strongly limited to address NCDs
satisfactory and thus, scalable, cost-efficient and evidence-
based digital health interventions (DHIs) are required to
complement existing health services.
§MobileCoach is a validated open source platform for the design
and delivery of DHIs with a healthcare chatbot but currently
supports a digital coaching that is limited to text-based SMS.
Design and Evaluation of a Mobile Chat App for the Open
Source Behavioral Health Intervention Platform MobileCoach
Tobias Kowatsch*, Dirk Volland, Iris Shih, Dominik Rüegger, Florian Künzler, Filipe
Barata, Andreas Filler, Dirk Büchter, Björn Brogle, Katrin Heldt, Pauline Gindrat,
Nathalie Farpour-Lambert & Dagmar l’Allemand
*Corresponding author: tobias.kowatsch@unisg.ch
Motivation
Screenshots and First Evaluation Results in the Domain of Childhood Obesity
www.c4dhi.org
www.mobile-coach.eu | www.c4dhi.org
We would like to thank the CSS Insurance and the Swiss National Science Foundation for their support through grants 159289 and 162724.
Physician
Quick
Dashboard
View
Micro Interventions
with Sensor Integration
Dashboard
Media Elements:
Photos, Video, etc.
Digital Coach
Answer Options
and Text Input
Mobile Chat App for the Open Source Platform MobileCoach 4
4 Evaluation of the Artifact
Based on prior work demonstrating the acceptance of chat apps by adolescents [11],"
the first test of the novel chat app was conducted in a children’s hospital in December
2016 with 11 patients (ageMean=12.6 years, SD = 2.4; 8 girls), who participated in an
intervention for the treatment of obesity. The goal of this test was (1) to assess en-
joyment, ease of use, usefulness and the intention to use the app [10], and (2) to iden-
tify and address major usability problems with the app [12] prior to a randomized
controlled trial (RCT), in which the efficacy of a chat-based six-month DHI for the
treatment of childhood obesity will be compared to a control group.
First, a chat-based DHI was collaboratively designed by computer scientists, phy-
sicians, a psychotherapist, diet and sport experts. The patients were then asked to
select a chatbot of their liking, i.e. they could choose between a female and male
chatbot (Anna or Lukas). Then, they interacted with the bot for 10 minutes including
various chat-based photo, physical activity and quiz interactions. The patients were
observed during these interactions by a computer scientist and physician. Afterwards,
patients were asked to fill out a questionnaire to assess the app and to provide qualita-
tive feedback on their experience with the app. Similar to prior work [10], we as-
sessed technology perceptions and behavioral intentions with seven-point Likert
scales anchored from strongly disagree (1) to strongly agree (7). As young patients
deserve special consideration, we used single-item measures to reduce the burden of
evaluation [3].
The descriptive statistics of the evaluation are shown in Table 1. Results indicate
that the chat app was perceived positive regarding all four constructs. A sign test
against the neutral Likert-scale median of 4 supports this observation. Finally, we
found no major usability problems based on the observations and the qualitative feed-
back.
Table 1. Descriptive statistics and results of a sign test against the neutral value 4 on a 7-point
Likert-scale (N=11). Note: Perceived ease of use (PEU), Perceived enjoyment (PEN), Per-
ceived usefulness (PU) and Intention to use (IU); Significance * / ** / *** p < .05 / .01 / .001
#
Item
Mean
Median
SD
p-value
PEU
I found the chat easy to use.
6.7
7.0
0.7
PEN
I enjoyed chatting.
6.2
7.0
1.5
PU
Chatting with Lukas/Anna could motivate me to
accomplish my intervention tasks.
5.9
6.0
1.1
IU
I could imagine chatting daily that way.
5.6
6.0
1.4
First findings of the aforementioned RCT show that new young patients assigned to
the chat-based DHI (N=14) completed successfully more than 60% of the daily inter-
vention tasks over the first two months. The efficacy of this DHI will be finally meas-
ured by the Body Mass Index after the six-month RCT. We hypothesize that the chat-
based DHI is more effective as the chatbot can provide everyday support on therapy
goals and tasks, thus increasing therapy adherence compared to patients of the treat-
ment-as-usual control group without everyday support.
Pretest with 11 obese patients
Descriptive statistics and results of a sign test against the neutral value 4 on a 7-point Likert-scale. Note: Perceived ease of use (PEU),
Perceived enjoyment (PEN), Perceived usefulness (PU) and Intention to use (IU); Significance * / ** / *** p < .05 / .01 / .001
We thus
built a
native
chat
app.
© University of St. Gallen & ETH Zurich & CSS
Slide 1| Iris Shih | May 16th, 2017
80%
74%
54%
62%
53%
58% 57%
51%
48%
42%
56%
42% 44% 44%
37% 37%
WEEK$
1
WEEK$
2
WEEK$
3
WEEK$
4
WEEK$
5
WEEK$
6
WEEK$
7
WEEK$
8
WEEK$
9
WEEK$
10
WEEK$
11
WEEK$
12
WEEK$
13
WEEK$
14
WEEK$
15
WEEK$
16
Key$Achievement$
93% 89%
71%
89%
68%
77%
81%
71%
68% 70%
74%
59%
69% 67%
63%
67%
Active$Patients
% out of 15 patients using the app
% of daily goal achievements
Design Rationale
Apache 2
licensed

File (1)

ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.