Kerstin Denecke

• Dr.
• Professor at Bern University of Applied Sciences

Safety planning is an intervention that demonstrated to be successful in help individuals self-manage suicidal crises. The SERO suicide prevention app supports this safety planning in a digital manner. The objective of this paper is to identify the specific components of safety plans and thereby guiding the design of digital solutions in a way that...

Objective: To study which behavioral components are implemented within participatory health interventions for precision prevention, specifically how they are realized as part of the interventions and how the tailoring of the interventions is implemented. Methods: We selected three case studies of participatory health interventions for precision pre...

Background Hospital at home (HaH) care models have gained significant attention due to their potential to reduce healthcare costs, improve patient satisfaction, and lower readmission rates. However, the lack of a standardized classification system has hindered systematic evaluation and comparison of these models. Taxonomies serve as classification...

BACKGROUND The diagnosis of sleep disorders presents a challenging landscape, characterized by the complex nature of their assessment and the often divergent views between objective clinical assessment and subjective patient experience. This study explores the interplay between these perspectives, focusing on the variability of individual perceptio...

Hospital at Home (HaH) is a model of care that provides hospital-level care in the patient’s home, requiring a unique set of competencies and skills from both multidisciplinary care teams and informal caregivers. These skills are often different from those required in traditional hospital settings. The aim of this paper is to consolidate the inform...

Introduction Digital health interventions specifically those realized as chatbots are increasingly available for mental health. They include technologies based on artificial intelligence that assess user’s sentiment and emotions for the purpose of responding in an empathetic way, or for treatment purposes, e.g. for analyzing the expressed emotions...

BACKGROUND Structured reporting is essential for improving the clarity and accuracy of radiological information. Despite its benefits, the European Society of Radiology (ESR) notes that it is not widely adopted. This raises the need for automatic methods to extract relevant information from unstructured radiology reports and thereby create structur...

Background: Hospital at home (HaH) care models have gained significant attention due to their potential to reduce healthcare costs, improve patient satisfaction, and lower readmission rates. However, the lack of a standardized classification system has hindered systematic evaluation and comparison of these models. Taxonomies serve as classification...

Background: The design and development of patient-centered digital health solutions requires user involvement, for example through usability testing. Although there are guidelines for conducting usability tests, there is a lack of knowledge about the technical, human, and organizational factors that influence the success of the tests. Objective:...

Background: The rapid technical progress in the domain of clinical Natural Language Processing and information extraction (IE) has resulted in challenges concerning the comparability and replicability of studies. Aim: This paper proposes a reporting guideline to standardize the description of methodologies and outcomes for studies involving IE f...

Background and objective: Social media physical activity chatbots use both chatbots and social media platforms for physical activity promotion and, thus, could face privacy and security challenges inherent in both technologies. This study aims to provide an overview of physical activity chatbot interventions delivered via social media platforms, s...

Despite their variability, Digital Health Apps (DHAs) typically share functionalities (i.e. core assets) and can thus be considered as a family of similar products with unique features adapted to specific use cases. Objective: We aim to identify and model reusable core assets to facilitate the development of a number of similar, but adapted DHAs in...

Searches for autism on social media have soared, making it a top topic. Social media posts convey not only plain text, but also sentiments and emotions that provide insight into the experiences of the autism community. While sentiment analysis categorizes overall sentiment, emotion analysis provides nuanced insights into specific emotional states....

Introduction Radiologists frequently lack direct patient contact due to time constraints. Digital medical interview assistants aim to facilitate the collection of health information. In this paper, we propose leveraging conversational agents to realize a medical interview assistant to facilitate medical history taking, while at the same time offeri...

Background The integration of smart technologies, including wearables and voice-activated devices, is increasingly recognized for enhancing the independence and well-being of older adults. However, the long-term dynamics of their use and the coadaptation process with older adults remain poorly understood. This scoping review explores how interactio...

Background Artificial intelligence (AI) has the potential to enhance physical activity (PA) interventions. However, human factors (HFs) play a pivotal role in the successful integration of AI into mobile health (mHealth) solutions for promoting PA. Understanding and optimizing the interaction between individuals and AI-driven mHealth apps is essent...

Annually and globally, over three billion radiography examinations and computer tomography scans result in mostly unstructured radiology reports containing free text. Despite the potential benefits of structured reporting, its adoption is limited by factors such as established processes, resource constraints and potential loss of information. Howev...

Unlabelled: The care model Hospital@Home offers hospital-level treatment at home, aiming to alleviate hospital strain and enhance patient comfort. Despite its potential, integrating digital health solutions into this care model still remains limited. This paper proposes a concept for integrating laboratory testing at the Point of Care (POC) into H...

Unlabelled: Hospital@home is a healthcare approach, where patients receive active treatment from health professionals in their own home for conditions that would normally necessitate a hospital stay. Objective: To develop a framework of relevant features for describing hospital@home care models. Methods: The framework was developed based on a...

A Critical Incident Reporting System (CIRS) collects anecdotal reports from employees, which serve as a vital source of information about incidents that could potentially harm patients. Objectives: To demonstrate how natural language processing (NLP) methods can help in retrieving valuable information from such incident data. Methods: We analyzed f...

Background: Healthcare systems are increasingly resource constrained, leaving less time for important patient-provider interactions. Conversational agents (CAs) could be used to support the provision of information and to answer patients’ questions. However, information must be accessible to a variety of patient populations, which requires understa...

Background Regular physical activity helps to reduce weight and improve the general well-being of individuals living with obesity. Chatbots have shown the potential to increase physical activity among their users. We aimed to explore the preferences of individuals living with obesity for the features and functionalities of a modern chatbot based on...

Large Language Models (LLMs) such as General Pretrained Transformer (GPT) and Bidirectional Encoder Representations from Transformers (BERT), which use transformer model architectures, have significantly advanced artificial intelligence and natural language processing. Recognized for their ability to capture associative relationships between words...

BACKGROUND The integration of smart technologies, including wearables and voice-activated devices, is increasingly recognized for enhancing the independence and well-being of older adults. However, the long-term dynamics of their use and the coadaptation process with older adults remain poorly understood. This scoping review explores how interactio...

Conversational agents in healthcare are gaining popularity, for example, in the context of eliciting medical histories. Furthermore, due to the growing diversity of use cases and stakeholders, they are becoming increasingly configurable and are often based on variability mechanisms. In this paper, we present a high-level perspective on typical vari...

The application of digital interventions in healthcare beyond research has been translated in the development of software as a medical device. Along with corresponding regulations for medical devices, there is a need for assessing adverse events to conduct post-market surveillance and to appropriately label digital health interventions to ensure pr...

BACKGROUND Artificial intelligence (AI) has the potential to enhance physical activity (PA) interventions. However, human factors (HFs) play a pivotal role in the successful integration of AI into mobile health (mHealth) solutions for promoting PA. Understanding and optimizing the interaction between individuals and AI-driven mHealth apps is essent...

Objective: To identify links between Participatory Health Informatics (PHI) and the One Digital Health framework (ODH) and to show how PHI could be used as a catalyst or contributor to ODH. Methods: We have analyzed the addressed topics within the ODH framework in previous IMIA Yearbook contributions from our working group during the last 10 years....

Background: With the rise of social media, social media use for delivering mental health interventions has become increasingly popular. However, there is no comprehensive overview available on how this field developed over time. Objectives: The objective of this paper is to provide an overview over time of the use of social media for delivering me...

Introduction Radiological imaging is one of the most frequently performed diagnostic tests worldwide. The free-text contained in radiology reports is currently only rarely used for secondary use purposes, including research and predictive analysis. However, this data might be made available by means of information extraction (IE), based on natural...

Recent developments related to tools based on artificial intelligence (AI) have raised interests in many areas, including higher education. While machine translation tools have been available and in use for many years in teaching and learning, generative AI models have sparked concerns within the academic community. The objective of this paper is t...

Transformer models have been successfully applied to various natural language processing and machine translation tasks in recent years, e.g. automatic language understanding. With the advent of more efficient and reliable models (e.g. GPT-3), there is a growing potential for automating time-consuming tasks that could be of particular benefit in hea...

Motivation: Digital therapeutics (DTX), i.e., health interventions that are provided through digital means, are increasingly available for use; in some countries, physicians can even prescribe selected DTX following a reimbursement by health insurances. This results in an increasing need for methodologies to consider and monitor DTX's negative con...

Introduction: Mental health is one of the major global concerns in the field of healthcare. The emergence of digital solutions is proving to be a great aid for individuals suffering from mental health disorders. These solutions are particularly useful and effective when they are personalized. The objective of this paper is to understand the person...

Background The Internet of Things (IoT) has gained significant attention due to advancements in technology and has potential applications in meeting the needs of an aging population. Smart technologies, a subset of IoT, can support older adults in aging in place, promoting independent living and improving their quality of life. However, there is a...

Introduction Mobile health, or mHealth, is based on mobile information and communication technologies and provides solutions for empowering individuals to participate in healthcare. Personalisation techniques have been used to increase user engagement and adherence to interventions delivered as mHealth solutions. This study aims to explore the curr...

BACKGROUND A large language model (LLM) is a type of artificial intelligence (AI) algorithm that uses deep learning techniques and massively large data sets to understand, summarize, generate and predict new content. Modern LLMs use transformer-based models or short "transformers", which are neural networks and have been tested for various tasks in...

Background A large language model (LLM) is a machine learning model inferred from text data that captures subtle patterns of language use in context. Modern LLMs are based on neural network architectures that incorporate transformer methods. They allow the model to relate words together through attention to multiple words in a text sequence. LLMs h...

Introduction Radiological imaging is one of the most frequently performed diagnostic tests worldwide. The free text contained in radiology reports is currently only rarely utilized for secondary use, including research and predictive analysis. However, this data might be made available by means of information extraction (IE), based on natural langu...

BACKGROUND The Internet of Things (IoT) has gained significant attention due to advancements in technology and has potential applications in meeting the needs of an aging population. Smart technologies, a subset of IoT, can support older adults in aging in place, promoting independent living and improving their quality of life. However, there is a...

Conversational agents (CA) applied in a healthcare setting are often designed to mimic healthcare professionals. Inappropriate design of their implemented conversation flow might impact on the achieved outcome, patient adherence and experience, and might even become a risk for patient safety. Objective of this paper is to identify factors to be con...

Attention, which is the process of noticing the surrounding environment and processing information, is one of the cognitive functions that deteriorate gradually as people grow older. Games that are used for other than entertainment, such as improving attention, are often referred to as serious games. This study examined the effectiveness of serious...

Social media provide easy ways to autistic individuals to communicate and to make their voices heard. The objective of this paper is to identify the main themes that are being discussed by autistic people on Twitter. We collected a sample of tweets containing the hashtag #ActuallyAutistic during the period 10/02/2022 and 14/09/2022. To identify the...

Social media chatbots could help increase obese adults' physical activity behaviour. The study aims to explore obese adults' preferences for a physical activity chatbot. Individual- and focus group interviews will be conducted in 2023. Identified preferences will inform the development of a chatbot that motivates obese adults to increase their phys...

Participatory design (PD) is increasingly used to support design and development of digital health solutions. The involves representatives of future user groups and experts to collect their needs and preferences and ensure easy to use and useful solutions. However, reflections and experiences with PD in designing digital health solutions are rarely...

Conversational agents (CA) are becoming very popular to deliver digital health interventions. These dialog-based systems are interacting with patients using natural language which might lead to misunderstandings and misinterpretations. To avoid patient harm, safety of health CA has to be ensured. This paper raises awareness on safety when developin...

Background: The need for software suppliers to react swiftly to the plethora of application requests and constantly shifting market requirements is one of the major problems facing the health IT business in the context of digital health transformation. This can only be achieved when the necessary staff and resources are available. Objectives: Th...

Fatigue is the most prevalent Long-COVID symptom. Individuals who are affected have to learn to organize and manage daily activities according to the subjectively perceived energy reserves. Our objective was to develop an application, Fading Fatigue, that supports patients in their energy management, in particular after an initial therapy guided by...

Radiologists rarely interact with the patients whose radiological images they are reviewing due to time and resource constraints. However, relevant information about the patient’s medical history could improve reporting performance and quality. In this work, our objective was to collect requirements for a digital medical interview assistant (DMIA)...

Evaluating conversational agents (CAs) that are supposed to be applied in healthcare settings and ensuring their quality is essential to avoid patient harm and ensure efficacy of the CA-delivered intervention. However, a guideline for a standardized quality assessment of health CAs is still missing. The objective of this work is to describe a frame...

Understanding the underlying mechanisms of a medical sentiment analysis algorithm is essential when its results are used within clinical decision making. Rule-based methods to medical sentiment analysis are explainable by nature: there are underlying rules that help understanding how the system came to its decision. For machine learning based metho...

In this chapter, I will outline open challenges of medical sentiment analysis, basically from a linguistic point of view. There are several challenges related to the analysis of freetextual language that complicate medical sentiment analysis and impact the quality of results. Typical phenomena in particular in clinical narratives are paraphrases an...

Research in the domain of medical sentiment analysis is very active. For this reason, researchers propose, evaluate and compare different approaches, feature sets and tools, consider different levels of analysis and address a multitude of related tasks. The overarching aim of these efforts is to increase performance of sentiment analysis results an...

After analysing strengths, weaknesses, opportunities and threats of medical sentiment analysis, this chapter outlines a potentials for future research in this field. The use cases described in this book demonstrated the potentials medical sentiment analysis could have. The question arises which next steps have to be taken to bring the research to a...

Sentiment analysis studies opinions, sentiments, evaluations, attitudes and emotions as expressed in natural language text. In recent years, sentiment analysis research and applications in the health domain gained in interest. This chapter defines the sentiment analysis problem in the context of healthcare and medicine. It gives an overview on the...

With the raise of intelligent agents in healthcare with conversational user interface, medical sentiment analysis becomes integrated in these agents to analyse user statements regarding opinions and emotions. In contrast to the previously described text types, the texts of interest are user statements resulting from interaction with an intelligent...

Lexicon-based (or knowledge-based) approaches to sentiment analysis require a lexical resource referred to as sentiment or opinion lexicon for analysing the sentiment. The single words or phrases of a text can then be matched to the lexicon entries and the polarity can be assigned. The biggest challenge is to generate the lexicon. In this chapter,...

Medical sentiment analysis can be considered as a two-step process comprising topic detection or health mention classification and the actual sentiment analysis. Health mention classification can be realised using topic detection methods such as topic modelling or named entity extraction. To be able to analyse expressed sentiments and their polarit...

Medical sentiment analysis considers traditional medical documents, such as nursing notes, radiology reports, or prescriptions. These clinical narratives document the clinical treatment process and are written by healthcare professionals. This chapter describes the types of clinical narratives and their linguistic and semantic peculiarities. Since...

Medical sentiment analysis aims to understand and analyse the emotions and sentiments expressed by individuals for various purposes in healthcare. This can raise ethical concerns related to the text analysis process itself and the potential consequences of this analysis and the use of its results in healthcare contexts. For this reason, it is essen...

In the previous chapters of this book, an overview was given on use cases that have been considered, on available resources to conduct or develop solutions to analyse medical sentiment. Methods applied to realise medical sentiment analysis were introduced. Sentiment analysis of social media data has become a popular research method to study charact...

In order to determine the polarity of sentences, phrases, or documents, machine learning can be used to train classifiers using domain-specific data sets. Supervised approaches, unsupervised approaches and hybrid methods for medical sentiment analysis can be distinguished. While supervised methods require labelled examples, unsupervised methods are...

Sentiment lexicons contain sentiment-bearing terms with polarities, scorings or other categorical information. The single terms or phrases are associated with their polarity score or category label. They form the foundation of many sentiment analysis applications. We can distinguish general domain lexicons from lexicons that have been specifically...

In this chapter, several case studies applying medical sentiment analysis techniques to real world problems are presented. In each study, I begin with a statement of the problem addressed and then show how it was solved. The studies may provide ideas of how medical sentiment analysis methods can be used to solve real-world problems or how challenge...

Medical social media derivatives such as tweets, online forums or drug reviews, can be subject of interest for medical sentiment analysis. Such data is data published by individuals (not necessarily patients, but their relatives, friends and healthcare professionals). While tweets are restricted in their length and are therefore characterised by a...

When we want to study sentiment distributions or opinions in medical texts or require sentiment scores for risk prediction, the simplest way is to use out-of-the box tools. Some of them are described in this chapter. We are focusing on tools that have been used and tested for medical sentiment analysis. There are clearly more tools available. Howev...

Both patients and healthcare providers may benefit from systems performing medical sentiment analysis. Extracted sentiment has been used to realise a variety of use cases in healthcare, including quality assessment, pharmacovigilance, risk prediction for various diseases, and public health. Through monitoring and analysing sentiment expressed on so...

Data is necessary for training sentiment classifiers as well as for testing and comparing sentiment algorithms. The datasets that have been used for medical sentiment analysis are described in this chapter. We separate datasets made up of clinical records from those made up of information from social media. Most of the currently accessible corpora...

A clinical sentiment is a judgment, thought or attitude promoted by an observation with respect to the health of an individual. Sentiment analysis has drawn attention in the healthcare domain for secondary use of data from clinical narratives, with a variety of applications including predicting the likelihood of emerging mental illnesses or clinica...

Background Hospital@home is a model of healthcare, where healthcare professionals actively treat patients in their homes for conditions that may otherwise require hospitalization. Similar models of care have been implemented in jurisdictions around the world over the past few years. However, there are new developments in health informatics includin...

Background: Health care has evolved to support the involvement of individuals in decision making by, for example, using mobile apps and wearables that may help empower people to actively participate in their treatment and health monitoring. While the term "participatory health informatics" (PHI) has emerged in literature to describe these activiti...

[This corrects the article DOI: 10.2196/42672.].

Evaluating conversational agents (CA) that are supposed to be applied in healthcare and ensuring their quality is essential to avoid patient harm. However, most researchers only study usability and use the CA in clinical trials before conducting such careful evaluation. In previous work, consensus on metrics for evaluating healthcare CA have been f...

The Swiss classification of surgical interventions (CHOP) has to be used in daily practice by physicians to classify clinical procedures. Its purpose is to encode the delivered healthcare services for the sake of quality assurance and billing. For encoding a procedure, a code of a maximal of 6-digits has to be selected from the classification syste...

Background Anxiety and depression are the most common mental disorders worldwide. Owing to the lack of psychiatrists around the world, the incorporation of artificial intelligence (AI) into wearable devices (wearable AI) has been exploited to provide mental health services. Objective This review aimed to explore the features of wearable AI used fo...

Background The evolution of artificial intelligence and natural language processing generates new opportunities for conversational agents (CAs) that communicate and interact with individuals. In the health domain, CAs became popular as they allow for simulating the real-life experience in a health care setting, which is the conversation with a phys...

Health care is shifting toward become proactive according to the concept of P5 medicine–a predictive, personalized, preventive, participatory and precision discipline. This patient-centered care heavily leverages the latest technologies of artificial intelligence (AI) and robotics that support diagnosis, decision making and treatment. In this paper...

Providing urgent and emergency care to migrant children is often hampered or delayed. Reasons for this are language barriers when children, and their care givers, don’t speak any of the languages commonly spoken in Switzerland, which include German, French, Italian, and English. By a participatory design process, we want to develop a novel image-ba...

In the medical domain, multiple ontologies and terminology systems are available. However, existing classification and prediction algorithms in the clinical domain often ignore or insufficiently utilize semantic information as it is provided in those ontologies. To address this issue, we introduce a concept for augmenting embeddings, the input to d...

Objective: Social media is used in the context of healthcare, for example in interventions for promoting health. Since social media are easily accessible they have potential to promote health equity. This paper studies relevant factors impacting on health equity considered in social media interventions. Methods: We searched for literature to identi...

Objective: Social media is used in the context of healthcare, for example in interventions for promoting health. Since social media are easily accessible they have potential to promote health equity. This paper studies relevant factors impacting on health equity considered in social media interventions. Methods: We searched for literature to identi...

Conversational agents (CA) are chatbot-based systems supporting the interaction with users through text, speech, or other modalities. They are used in an increasing number of medical use cases. Even though usability is considered a prerequisite for the success of mHealth apps using CA, there is still no standard procedure to study usability of heal...

Digital interventions for increasing physical activity behavior have shown great potential, especially those with social media. Chatbots, also known as conversational agents, have emerged in healthcare in relation to digital interventions and have proven effective in promoting physical activity among adults. The study’s objective is to explore user...

Action observation (AO) and motor imagery (MI) are considered as promising therapeutic approaches in the rehabilitation of patients after a stroke (PaS). Observing and mentally rehearsing motor movements stimulate the motor system in the brain and result in a positive effect on movement execution. To support patients in the early rehabilitation pha...

This paper presents a comparison of deep learning models for classifying P300 events, i.e., event-related potentials of the brain triggered during the human decision-making process. The evaluated models include CNN, (Bi | Deep | CNN-) LSTM, ConvLSTM, LSTM + Attention. The experiments were based on a large publicly available EEG dataset of school-ag...

Language barriers hamper or delay delivery of urgent and emergency care to migrant children when they or their parents don’t speak any of the languages commonly spoken in Switzerland. In such situations, nurses often fall back to use ad hoc communication aids, including translation apps and visual dictionaries, to collect information about a patien...

Background: Personal contact between radiologists and their patients is scarce due to time constraints and logistical reasons which impacts on patient knowledgeability and satisfaction, but also on examination and diagnostic quality. Objective: We illuminate medical history interviews from a radiologist's perspective and discuss its impact on th...

Background In recent years, an increasing number of health chatbots has been published in app stores and described in research literature. Given the sensitive data they are processing and the care settings for which they are developed, evaluation is essential to avoid harm to users. However, evaluations of those systems are reported inconsistently...