I denna studie undersöks individers generella attityder till vårdapplikationer som använder maskininlärning. Datainsamlingen har skett genom både kvalitativa och kvantitativa metoder som kompletterar varandra. Metoderna innefattar en enkätundersökning och två fokusgrupper baserade på scenario-based design. Teorin är baserad på forskning inom digitaliseringen av vården, bland annat maskininlärning och mHealth, som ligger till grund och stödjer undersökningen. Även teori om attityder och förtroende till digitaliseringen av vården har underbyggt undersökningen.I slutsatsen framkommer det att det finns en korrelation mellan hög medvetenhet och positiv inställning när det kommer det användandet av vårdapplikationer med maskininlärning. Den generella attityden till att få en diagnos av maskininlärning är negativ då de flesta föredrar att få en diagnos förmedlad av en läkare. Studien indikerar på att detta kan bero på att patienterna söker empati från vården, vilket artificiell intelligens saknar. Förtroendet för en vårdapplikation grundar sig främst i ryktet om den men även i vilket företag eller organisation som ligger bakom. Studien indikerar på att individer är positivt inställda till att bidra med privat hälsodata till en vårdapplikation om det leder till förebyggande av sjukdom. Studien ger även en antydan på att det finns en rädsla kring var privata hälsodata hamnar när den har lämnats ut. / This study aims to research on individuals’ general attitudes towards healthcare applications that use machine learning. The data collection has taken place through both qualitative and quantitative methods as a complement to each other. The methods include a questionnaire survey, two focus groups based on scenario-based design. The theory is based on research in the digitalisation of healthcare, including machine learning and mHealth, which is based and supports the investigation. The theory of attitudes and confidence in the digitalisation of care also forms the basis for the study.The conclusion shows that there is a correlation between high awareness and positive attitude when it comes to the use of healthcare applications with machine learning. The general attitude towards a diagnosis from machine learning is negative since most people prefer to get a diagnosis mediated by a doctor. The study indicates that this may be because the patients seek empathy from the healthcare system, which artificial intelligence lacks of. Trust towards a healthcare application is based primarily on the reputation of it, but also in which company or organization that is behind it. The respondents in the survey are positive about contributing with their personal data to a healthcare application if it leads to a prevention of a disease. The study also gives an indication that there is a fear of what happens with private health data.

Mobile phones can be used to assess patients health by collecting valuable informationthrough the sensors, GPS and accelerometers and then uploading them to a centraldatabase to allow for clinicians to remotely monitor the decline, improvement or over-all health status of a patient [1] [2].Many mHealth applications use mobile phones built-in GPS, accelerometer and othersensors which allows for a large selection of work to compare the implemented exercisecapacity test to [1].The exercise capacity tests developed for this thesis is to be used in Mobistudy. Mobis-tudy is an open mobile-health platform for clinical research. The platform has an emphasison regulatory compliance, patient consent and transparency [3].The thesis resulted in the creation of two artifacts which were able to successfullycollect data from the user to transfer to the clinicians using the application. During theanalysis it was found that the SMWT algorithm developed by Salvi et al [4] worked wellunder non optimal conditions. The Queens College Step Tests result were in general poor,however more testing with more different phones is required to provide a clear answer.

I denna studie undersöks individers generella attityder till vårdapplikationer som användermaskininlärning. Datainsamlingen har skett genom både kvalitativa och kvantitativa metodersom kompletterar varandra. Metoderna innefattar en enkätundersökning och två fokusgrupperbaserade på scenario-based design. Teorin är baserad på forskning inom digitaliseringen avvården, bland annat maskininlärning och mHealth, som ligger till grund och stödjerundersökningen. Även teori om attityder och förtroende till digitaliseringen av vården harunderbyggt undersökningen.I slutsatsen framkommer det att det finns en korrelation mellan hög medvetenhet och positivinställning när det kommer det användandet av vårdapplikationer med maskininlärning. Dengenerella attityden till att få en diagnos av maskininlärning är negativ då de flesta föredrar att fåen diagnos förmedlad av en läkare. Studien indikerar på att detta kan bero på att patienternasöker empati från vården, vilket artificiell intelligens saknar. Förtroendet för en vårdapplikationgrundar sig främst i ryktet om den men även i vilket företag eller organisation som liggerbakom. Studien indikerar på att individer är positivt inställda till att bidra med privat hälsodatatill en vårdapplikation om det leder till förebyggande av sjukdom. Studien ger även en antydanpå att det finns en rädsla kring var privata hälsodata hamnar när den har lämnats ut. / This study aims to research on individuals’ general attitudes towards healthcare applicationsthat use machine learning. The data collection has taken place through both qualitative andquantitative methods as a complement to each other. The methods include a questionnairesurvey, two focus groups based on scenario-based design. The theory is based on research in thedigitalisation of healthcare, including machine learning and mHealth, which is based andsupports the investigation. The theory of attitudes and confidence in the digitalisation of carealso forms the basis for the study.The conclusion shows that there is a correlation between high awareness and positive attitudewhen it comes to the use of healthcare applications with machine learning. The general attitudetowards a diagnosis from machine learning is negative since most people prefer to get adiagnosis mediated by a doctor. The study indicates that this may be because the patients seekempathy from the healthcare system, which artificial intelligence lacks of. Trust towards ahealthcare application is based primarily on the reputation of it, but also in which company ororganization that is behind it. The respondents in the survey are positive about contributing withtheir personal data to a healthcare application if it leads to a prevention of a disease. The studyalso gives an indication that there is a fear of what happens with private health data.

The World Health Organization (WHO) has forecast a global shortage of health workers by 2030, predominantly affecting low- and middle-income countries (LMICs). This sits in tension with the United Nations’ (UN) Sustainable Development Goal 3 (healthy lives and well-being) through universal health coverage (UHC). To address this problem, the WHO encourages task shifting, recruitment, training, and deployment of health workers. In lowand middle-income countries (LMICs), frontline health workers (FLHWs) are responsible for expanding the reach of the health system and providing crucial reproductive, maternal, newborn and child health (RMNCH) services. Adequate and appropriate training is fundamental to the success of FLHWs, particularly in contexts where their scope of work may evolve or expand over time. Digital health solutions (defined as the use of digital, mobile and wireless technologies to support the achievement of health objectives) are increasingly being used to support the training of FLHWs. Strategies may rely on use of digital tools, including mobile phones, as the primary modality for training or as tools which augment traditional face-to-face instruction. Digital health has potential for FLHW training as it allows for listening, learning and teaching through interactive health content accessible even on basic mobile phones. This dissertation explored the literature on FLHWs in LMICs, digital health in LMICs, digital health used by FLHWs, and digital health used for training of FLHWs in LMICs. The journal “ready” component is a systematic review which discusses the various aspects of digital training for FLHWs in LMICs. For the purposes of the systematic review, seven electronic databases were searched for articles published in English from 2008-2018. Combinations of medical subheadings (MeSH) that were used were: “mHealth”, “health worker”, “community health worker” and “low- and middle-income country”. From a total of 2628 identified studies, abstracts were screened with four filters to identify studies about “training”, and eventually a total of 16 studies were included. The included studies were critically appraised and coded descriptively to enable a narrative synthesis of findings. Of the sixteen studies, twelve used mobile and/or smartphones for FLHW training. A wide range of digital platforms were used to provide information (and where relevant enable interaction). Duration of training programs varied from five days to six months. Training content was relevant to the various health services and practice areas the FLHWs worked in. Training focused on continuing education through in-service training of new content or in-service refresher courses. Three training pedagogies were used: 1) didactic training techniques – in four studies information was provided passively without an interactive component; 2) interactive training techniques – six studies used platforms to provide information along with an interactive component via multi-media; and, 3) blended-learning approach – six studies delivered training via didactic and interactive approaches by combining live and distance training. Consistent with the literature review, all studies reported increased knowledge and positive perceptions of digital health for FLHW training. Interactive and blended learning approaches, especially when accessed through mHealth technologies, are feasible, effective, appropriate, cost effective and scalable in LMICs. The conclusion from the literature and systematic reviews were that long-term effects (e.g. change in behaviour, improved service provision) need to be researched further.

Indiana University-Purdue University Indianapolis (IUPUI) / Introduction Mobile health (mHealth) applications (apps) are increasingly accessible and popular. In 2015, over 60% of smartphone users used their phones to look up health related information. mHealth apps related to maternal and child health (MCH) are particularly prevalent and frequently used. As high as 73% pregnant women and new mothers reported the use of MCH apps, with 27% using them daily. Methods A cross-sectional sample of MCH apps was extracted from the Apple App and Google Play stores using a JavaScript Scraper program. A multivariable linear regression, and series of ordinal logistic regression assessed the relationship between MCH app characteristics and two outcomes, end users’ perceived satisfaction (star ratings), and intent to use (downloads). Next, theory-based content analysis reviewed the presence and use of behavior change techniques (BCTs) in popular MCH apps using the mHealth app taxonomy framework. Finally, a qualitative inductive analysis assessed user self-reported experiences, perceived benefits, and general feedback for MCH apps. Results Seven hundred and forty-two apps met the inclusion criteria. A large majority of MCH apps were developed by non-healthcare developers. Google Play store apps had higher user ratings; while, apps within health & fitness genre, with older updates, and no agerestrictions had fewer user ratings. Furthermore, lower priced apps, with high star ratings, in-app purchase options, and in-app advertisement presence had high downloads. And, apps belonging to medical and health & fitness genre had fewer user downloads. Content analysis revealed that popular MCH apps on an average include 7.4 behavior change techniques (BCTs) with a median of 6 BCTs. Apps developed by healthcare developers had higher BCTs present within app content. Qualitative analysis shows that consumers value apps that are low cost, with superior features, smooth technical aspects, high quality content, and easy to use. Conclusions Healthcare providers, app developers, and policymakers may benefit from a better understanding of MCH apps available in two popular app stores and may consider strategies to review and promote apps to consumers based on information accuracy and trustworthiness. / 2020-11-06

Indiana University-Purdue University Indianapolis (IUPUI) / Medication nonadherence among middle-aged to older adults with chronic conditions often stems from forgetting to take or fill medications as prescribed. A pilot study indicated the feasibility of technology acceptance model (TAM)-based smartphone medication reminder app (SMRA) training as a way to promote their app use and medication adherence. This dissertation assesses the viability and effect size of the modified TAM-based SMRA training in promoting app use and medication adherence, as well as its delivery design in preparation for a larger efficacy study. A two-group pretest-posttest design was employed. Twenty-nine adults aged over 40 years and taking medications for chronic condition management were recruited from Midwestern university and community sites. The training group (n = 15) received the modified TAM-based SMRA training; whereas the non-training group (n = 14) self-navigated app features. The training group reported significantly higher levels of perceived usefulness, perceived ease of use, positive subjective norm, and intention to use the app. In addition, the training group reported a higher proportion of active app use than the non-training group. Modified TAM-based SMRA training was not viable in increasing the levels of medication adherence variables. Effect sizes suggested at least 52 participants as a sample size for a larger efficacy study. Participants suggested that training could be improved by scheduling separate group training for iPhone and Android phone users, providing a live online training option, providing small group training with peer helper, tailoring training length to participant preference, and working with family members and healthcare providers as co-trainees and co-trainers.

An early detection of heart disease can save lives, caution individuals and also help to determine the type of treatment to be given to the patients. The first test of diagnosing a heart disease is through auscultation - listening to the heart sounds. The interpretation of heart sounds is subjective and requires a professional skill to identify the abnormalities in these sounds. A medical practitioner uses a stethoscope to perform an initial screening by listening for irregular sounds from the patient's chest. Later, echocardiography and electrocardiography tests are taken for further diagnosis. However, these tests are expensive and require specialized technicians to operate. A simple and economical way is vital for monitoring in homecare or rural hospitals and urban clinics. This dissertation is focused on developing a patient-centered device for initial screening of the heart sounds that is both low cost and can be used by the users on themselves, and later share the readings with the healthcare providers. An innovative mobile health service platform is created for analyzing and classifying heart sounds. Certain properties of heart sounds have to be evaluated to identify the irregularities such as the number of heart beats and gallops, intensity, frequency, and duration. Since heart sounds are generated in low frequencies, human ears tend to miss certain sounds as the high frequency sounds mask the lower ones. Therefore, this dissertation provides a solution to process the heart sounds using several signal processing techniques, identifies the features in the heart sounds and finally classifies them. This dissertation enables remote patient monitoring through the integration of advanced wireless communications and a customized low-cost stethoscope. It also permits remote management of patients' cardiac status while maximizing patient mobility. The smartphone application facilities recording, processing, visualizing, listening, and classifying heart sounds. The application also generates an electronic medical record, which is encrypted using the efficient elliptic curve cryptography and sent to the cloud, facilitating access to physicians for further analysis. Thus, this dissertation results in a patient-centered device that is essential for initial screening of the heart sounds, and could be shared for further diagnosis with the medical care practitioners.

No description available.

No description available.

Det här arbetet handlar om hur man kan utveckla ett digitalt gränssnitt i en vårdapplikation till Region Sörmland, med utgångspunkt från en befintlig vårdapplikation som används av Region Örebro län. Meningen är att designa om gränssnittet så att det är anpassat efter en äldre målgrupp mellan 65–75 år. Designen ska vara användarvänlig, och se till att navigation och information presenteras på ett sådant vis att det sker med en låg kognitiv belastning, och att man ska kunna vara en ny användare med lägre digital förmåga, och ändå kunna förstå hur man enkelt kan nå fram till sitt mål. I den här rapporten testat det hur man kan boka ett vårdbesök digitalt, och hur man kan följa upp vad man har för recept sedan tidigare, och se vad man har för bokade vårdbesök. För att undersöka detta så har olika metoder använts, såsom: litteraturstudie, marknadsanalys, heuristisk analys, behovsanalys, användbarhetstester, SUS-enkät, skisser, wireframe och prototypande. Meningen med att använda dessa olika metoder var att kunna få fram en stadig grund att stå på, genom de olika analyserna och efterforskningen i början av projektet. För att sedan kunna testa prototypen mot användarna, och utvärdera detta med hjälp av affinitetsdiagram och SUS-enkät. Meningen var att kunna se om de förändringar i Region Örebro läns gränssnitt kunde leda till en förbättrad användbarhet för användarna. Med resultatet från användbarhetstesterna, och SUS-enkäten framkommer det att de förändringar som har skett i gränssnittet från Region Örebro läns vårdapplikation, till mid-fi prototypen, och slutligen hi-fi prototypen så kan man se att den upplevda användbarheten har ökat, och att användarna både förstår gränssnittet bättre och att de uppfattar informationen bättre, än vad de gjorde från början. Genom att designa ett gränssnitt med hjälp av olika teorier om kognition, semiotik och affordans så bevisas det att man kan se till att utveckla ett gränssnitt så att det blir lätt att använda för äldre användare, och andra med liknande behov som dem. Detta gör att det förslag på vårdapplikation som föreslås i rapporten till Region Sörmland skulle kunna implementeras av dem.