Health economic benefits through the use of diagnostic support systems and expert knowledge

Real-world experience of diagnosis, disability, and daily management in parents of children with different genetic developmental and epileptic encephalopathies: a qualitative study

PURPOSE

This study describes the experience of parents of children with developmental and epileptic encephalopathies (DEE) and how the disease impacts their daily lives.

MATERIALS AND METHODS

A descriptive qualitative study was conducted using purposeful sampling. Twenty-one parents of children with DEEs caused by SCN1A, KCNQ2, CDKL5, PCDH19, and GNAO1 variants were included. Data collection was based on in-depth interviews and researchers' field notes. An inductive thematic analysis was performed.

RESULTS

Five themes emerged: (a) the diagnostic process, which describes the path from the time parents recognize the first symptoms until diagnostic confirmation is obtained; (b) the relationship with health professionals during the search for a diagnosis, which describes how the entire process is conditioned by the relationships established; (c) the world of disability, revealing how the disease and disability impact the life of the parents; (d) living day to day, the parents continuously change their plans in anticipation of the onset of a seizure; (e) the disease progression, a cause of great concern in the parents.

CONCLUSIONS

Our results show the need to develop recovery programs that integrate health and social interventions to support parents of children with DEE in the process of diagnosis and disease management.

The cost of the diagnostic odyssey of patients with suspected rare diseases

PURPOSE

Patients with rare diseases often undergo a long diagnostic odyssey. However, there is little empirical evidence on the cost incurred during the diagnostic pathway for patients with suspected rare diseases. This study provides a comprehensive analysis of healthcare costs and utilization during the diagnostic pathway for a heterogeneous sample of patients with suspected rare diseases but unclear diagnosis.

METHODS

Using claims data from five German statutory health insurance organizations for the years 2014-2019, we analyzed costs and healthcare utilization of 1,243 patients (aged 0 to 82 years) with suspected rare diseases referred to a rare disease center. A control cohort was assigned using 1:75 exact matching on age, sex and place of residence.

RESULTS

In the years prior to referral to an expert center, healthcare utilization of patients with suspected rare diseases was, on average, substantially and significantly higher compared to a matched control cohort during the same observation period - e.g. in terms of the number of hospitalizations (3.1 (95%CI: 2.9-3.4) vs. 0.5 (95%CI: 0.5-0.5)), different diagnoses (50.0 (95%CI: 48.1-51.9) vs. 26.4 (95%CI: 26.2-26.5)), different active substances prescribed (12.7 (95%CI: 12.2-13.3) vs. 8.2 (95%CI: 8.2-8.3)) and the number of genetic tests (14.7 (95%CI: 12.6-16.7) vs. 0.3 (95%CI: 0.3-0.3)). We found evidence of heterogeneity in utilization by age and sex. On average, direct costs (inpatient, outpatient and prescription drug costs) of patients with suspected rare diseases during the diagnostic pathway were 7.6-fold higher than the costs of matched controls (€26,999 (95%CI: €23,751 - 30,247) vs. €3,561 (95% CI: € 3,455-3,667)). Inpatient costs were the main cost component, accounting for 62.5% of total costs.

CONCLUSIONS

The diagnostic odyssey of patients with suspected rare diseases is associated with extensive healthcare utilization and high cost. Against this background, new ways to shorten the diagnostic journey have a high potential to decrease the financial burden related to rare diseases.

Multidisciplinary consensus on the diagnosis and management of patients with atypical Hemolytic Uremic Syndrome (complement-mediated TMA): Recommendations from Italian scientific societies, patient associations and regulators

Atypical Hemolytic Uremic Syndrome (aHUS) is a severe, systemic, rare disease (RD) that can occur in people of all ages, and is associated with high rates of morbidity and mortality. Because the management of patients with aHUS can be difficult, more effective strategies should be implemented. Faculty members from several Italian Scientific Societies, Patient Associations and Regional Institutional Experts on RDs met to discuss aHUS management within a multidisciplinary team (MDT), using a Delphi process to develop consensus recommendations. Consensus (≥70 % agreement by faculty members) was reached on 51 statements with the aim of improving patient management and outcomes. These statements provide a unified framework for the differential diagnosis of aHUS, prompt recognition of the pathology, referral to RD reference centers, selecting between treatment relapse prevention measures options, patient management by a MDT and improving the overall awareness of aHUS. Despite the broad scope of the consensus statements, several unmet needs in the management of patients with aHUS were identified, including diagnostic suspicion, rapid genetic investigations, regular review of the centers of expertise (considering the number of treated patients), permanent clinical referral in treatment centers and widespread expertise among adult and pediatric specialists. We hope that this standardized framework will form the basis of the "digital ecosystem" concept and development of possible information technology solutions to assist the MDT involved in the management of patients with aHUS.

AI in medical diagnosis: A contextualised study of patient motivations and concerns

Patients' reactions to the implementation of Artificial Intelligence (AI) in healthcare range from adverse to favourable. While AI holds the promise of revolutionising healthcare by enhancing, accelerating, and improving the precision of care services, our understanding of patients' reactions to these paradigm shifts remains limited. In particular, little is known about the extent to which patients are receptive to independently use AI-enabled applications for diagnosis. This research seeks to develop a holistic, context-specific model capturing both the negative and positive cognitive responses of patients utilising AI-powered diagnostic services. Employing a sequential mixed-methods approach, the study draws on Behavioural Reasoning Theory to decode patients' cognitive reactions, including their reasons for and reasons giants using such applications. The research begins with a qualitative exploration, analysing user reviews to identify context-specific barriers and motivators. Building on these qualitative insights, the model's empirical validity is tested through a quantitative phase involving survey data analysis. Our findings provide a nuanced understanding of the context-dependent factors shaping patients' cognitive responses to AI-enabled diagnostic services, offering valuable insights for the design and implementation of patient-centred AI solutions in healthcare.

Development and expert inspections of the user interface for a primary care decision support system

BACKGROUND

General practitioners play a unique key role in diagnosing patients with unclear diseases. Decision support systems in primary care can assist with diagnosis provided that they are efficient and user-friendly.

OBJECTIVES

The objective of this study is to develop a high-fidelity prototype of the user interface of a clinical decision support system for primary care, particularly for diagnosis support in unclear diseases, using expert inspections at an early stage of development to ensure a high level of usability.

METHODS

The user interface prototype was iteratively developed based on previous research, design principles, and usability guidelines. During the development phase, three usability inspections were carried out by all experts at four-week intervals as heuristic walkthrough. Each inspection consisted of two parts: 1) Task-based inspection 2) Free exploration and evaluation based on usability heuristics. Five domain experts assessed the current status of development. The tasks in the inspections were based on the task model derived in the requirements analysis: perform data entry, review and discuss results, schedule further diagnostics, refer to specialists and close case.

RESULTS

As a result of this iterative development, a high-fidelity, clickable user interface prototype was created that is able to fulfil all six tasks of our task model. The usability inspections identified a total of 196 usability issues (for all 3 inspections; Part 1: 90 issues, Part 2: 106 issues), ranging in severity from minor to severe. These served the continuous adjustment and improvement of the prototype. All main tasks were completed successfully despite these problems.

CONCLUSION

Usability inspections through heuristic walkthroughs can support and optimise the development of a user-centred decision support system in order to ensure its suitability for performing relevant tasks.

The economic burden of diagnostic uncertainty on rare disease patients

BACKGROUND

It often takes a long time before a rare disease is diagnosed. Without a diagnosis, the right therapy often cannot be carried out and without the right therapy, the patients are denied the opportunity for a cure or relief from their symptoms. In addition, rare diseases can also have economic consequences for those affected. This study aimed to investigate the extent to which a rare disease affects the income and work performance of the patients concerned and whether the use of AI in diagnostics would have the potential to reduce economic losses.

METHODS

The work performance and income of 71 patients of the outpatient clinic for rare inflammatory systemic diseases with renal involvement at Hannover Medical School were analyzed during the course of the disease. The WHO Health and Work Performance Questionnaire (HPQ) was used to collect data. During the patient interviews, the questionnaire was completed four times: at the onset of the first symptoms, when a diagnostic decision support system (DDSS) would have suggested the correct diagnosis, at the time of diagnosis and at the current status.

RESULTS

With the onset of the diagnostic odyssey, the monthly net income of the patients under study dropped by an average of 5.32% due to lower work performance or work absenteeism. With the correct diagnosis, the original or even a better income of 11.92% could be achieved. Loss of income due to illness was more massive in patients with a rare disease with joint, muscle and connective tissue involvement than in patients with rare vasculitides. If a DDSS had been used, the loss of income would have been 2.66% instead of the actual 5.32%.

CONCLUSION

Rare diseases resulted in temporary or existing income losses in 28.17% of the patients. Losses in work performance and income were related to the type of disease and were more pronounced in patients with joint, muscle or connective tissue disease than in patients with rare vasculitides. The use of a DDSS may have the potential to reduce the negative income effects of patients through earlier correct diagnosis.

TRIAL REGISTRATION

Retrospectively registered.

The transition from genomics to phenomics in personalized population health

Modern health care faces several serious challenges, including an ageing population and its inherent burden of chronic diseases, rising costs and marginal quality metrics. By assessing and optimizing the health trajectory of each individual using a data-driven personalized approach that reflects their genetics, behaviour and environment, we can start to address these challenges. This assessment includes longitudinal phenome measures, such as the blood proteome and metabolome, gut microbiome composition and function, and lifestyle and behaviour through wearables and questionnaires. Here, we review ongoing large-scale genomics and longitudinal phenomics efforts and the powerful insights they provide into wellness. We describe our vision for the transformation of the current health care from disease-oriented to data-driven, wellness-oriented and personalized population health.

[Faster diagnosis of rare diseases with artificial intelligence-A precept of ethics, economy and quality of life]

BACKGROUND

Approximately 300 million people worldwide suffer from a rare disease. An optimal treatment requires a successful diagnosis. This takes a particularly long time, especially for rare diseases. Digital diagnosis support systems could be important aids in accelerating a successful diagnosis in the future.

OBJECTIVE

The current possibilities of digital diagnostic support systems in the diagnosis of rare diseases and questions that still need to be clarified are presented in relation to the parameters of ethics, economy and quality of life.

MATERIAL AND METHODS

Current research results of the authors were compiled and discussed in the context of the current literature. A case study is used to illustrate the potential of digital diagnostic support systems.

RESULTS

Digital diagnostic support systems and experts together can accelerate the successful diagnosis in patients with rare diseases. This could have a positive impact on patients' quality of life and lead to potential savings in direct and indirect costs in the healthcare system.

CONCLUSION

Ensuring data security, legal certainty and functionality in the use of digital diagnostic support systems is of great importance in order to create trust among experts and patients. Continuous further development of the systems by means of artificial intelligence (AI) could also enable patients to accelerate diagnosis in the future.

Surfacing undiagnosed disease: consideration, counting and coding

The diagnostic odyssey for people living with rare diseases (PLWRD) is often prolonged for myriad reasons including an initial failure to consider rare disease and challenges to systemically and systematically identifying and tracking undiagnosed diseases across the diagnostic journey. This often results in isolation, uncertainty, a delay to targeted treatments and increase in risk of complications with significant consequences for patient and family wellbeing. This article aims to highlight key time points to consider a rare disease diagnosis along with elements to consider in the potential operational classification for undiagnosed rare diseases during the diagnostic odyssey. We discuss the need to create a coding framework that traverses all stages of the diagnostic odyssey for PLWRD along with the potential benefits this will have to PLWRD and the wider community.

The Impact of Artificial Intelligence on Optimizing Diagnosis and Treatment Plans for Rare Genetic Disorders

Rare genetic disorders (RDs), characterized by their low prevalence and diagnostic complexities, present significant challenges to healthcare systems. This article explores the transformative impact of artificial intelligence (AI) and machine learning (ML) in addressing these challenges. It emphasizes the need for accurate and early diagnosis of RDs, often hindered by genetic and clinical heterogeneity. This article discusses how AI and ML are reshaping healthcare, providing examples of their effectiveness in disease diagnosis, prognosis, image analysis, and drug repurposing. It highlights AI's ability to efficiently analyze extensive datasets and expedite diagnosis, showcasing case studies like Face2Gene. Furthermore, the article explores how AI tailors treatment plans for RDs, leveraging ML and deep learning (DL) to create personalized therapeutic regimens. It emphasizes AI's role in drug discovery, including the identification of potential candidates for rare disease treatments. Challenges and limitations related to AI in healthcare, including ethical, legal, technical, and human aspects, are addressed. This article underscores the importance of data ethics, privacy, and algorithmic fairness, as well as the need for standardized evaluation techniques and transparency in AI research. It highlights second-generation AI systems that prioritize patient-centric care, efficient patient recruitment for clinical trials, and the significance of high-quality data. The integration of AI with telemedicine, the growth of health databases, and the potential for personalized therapeutic recommendations are identified as promising directions for the field. In summary, this article provides a comprehensive exploration of how AI and ML are revolutionizing the diagnosis and treatment of RDs, addressing challenges while considering ethical implications in this rapidly evolving healthcare landscape.

Neuroimaging based biotypes for precision diagnosis and prognosis in cancer-related cognitive impairment

Cancer related cognitive impairment (CRCI) is commonly associated with cancer and its treatments, yet the present binary diagnostic approach fails to capture the full spectrum of this syndrome. Cognitive function is highly complex and exists on a continuum that is poorly characterized by dichotomous categories. Advanced statistical methodologies applied to symptom assessments have demonstrated that there are multiple subclasses of CRCI. However, studies suggest that relying on symptom assessments alone may fail to account for significant differences in the neural mechanisms that underlie a specific cognitive phenotype. Treatment plans that address the specific physiologic mechanisms involved in an individual patient's condition is the heart of precision medicine. In this narrative review, we discuss how biotyping, a precision medicine framework being utilized in other mental disorders, could be applied to CRCI. Specifically, we discuss how neuroimaging can be used to determine biotypes of CRCI, which allow for increased precision in prediction and diagnosis of CRCI via biologic mechanistic data. Biotypes may also provide more precise clinical endpoints for intervention trials. Biotyping could be made more feasible with proxy imaging technologies or liquid biomarkers. Large cross-sectional phenotyping studies are needed in addition to evaluation of longitudinal trajectories, and data sharing/pooling is highly feasible with currently available digital infrastructures.

Rare diseases: why is a rapid referral to an expert center so important?

BACKGROUND

Patients with rare diseases usually go through years of diagnostic odysseys. The large number of rare diseases and the associated lack of expertise pose a major challenge to physicians. There are few physicians dealing with patients with rare diseases and they usually work in a limited number of specialized centers. The aim of this study was to evaluate the diagnostic efficiency of an expert center.

METHODS

The diagnostic pathway of 78 patients of the outpatient clinic for rare inflammatory systemic diseases with renal involvement was analyzed retrospectively. For this purpose, each examination day was documented with the corresponding examinations performed from the onset of initial symptoms. Three time points were considered: The time when patients first visited a physician with symptoms, the time when patients consulted an expert, and the time when they received the correct diagnosis. In addition, it was documented whether the diagnosis could be made without the expert, or only with the help of the expert. The examinations that confirmed the diagnosis were also documented for each patient.

RESULTS

A correct diagnosis was made without the help of the expert in only 21% of cases. Each patient visited an average of 6 physicians before consulting the expert. Targeted diagnostics enabled the expert to make the correct diagnosis with an average of seven visits, or one inpatient stay. However, referral to the expert took an average of 4 years.

CONCLUSION

The data show that rapid and targeted diagnostics were possible in the expert center due to the available expertise and the interdisciplinary exchange. Early diagnosis is of great importance for many patients, as an early and correct therapy can be decisive for the course of the disease.

The Impact of Artificial Intelligence in the Odyssey of Rare Diseases

Emerging machine learning (ML) technologies have the potential to significantly improve the research and treatment of rare diseases, which constitute a vast set of diseases that affect a small proportion of the total population. Artificial Intelligence (AI) algorithms can help to quickly identify patterns and associations that would be difficult or impossible for human analysts to detect. Predictive modeling techniques, such as deep learning, have been used to forecast the progression of rare diseases, enabling the development of more targeted treatments. Moreover, AI has also shown promise in the field of drug development for rare diseases with the identification of subpopulations of patients who may be most likely to respond to a particular drug. This review aims to highlight the achievements of AI algorithms in the study of rare diseases in the past decade and advise researchers on which methods have proven to be most effective. The review will focus on specific rare diseases, as defined by a prevalence rate that does not exceed 1-9/100,000 on Orphanet, and will examine which AI methods have been most successful in their study. We believe this review can guide clinicians and researchers in the successful application of ML in rare diseases.

Mobile Apps for People With Rare Diseases: Review and Quality Assessment Using Mobile App Rating Scale

BACKGROUND

Mobile apps are becoming increasingly popular, with 5.70 million apps available in early 2021. Smartphones can provide portable and convenient access to health apps. Here, we consider apps for people with one of the estimated 7000 rare conditions, which are defined as having an incidence of <1 in 2000. The needs of people with rare conditions are known to be different from those of people with more common conditions. The former may be socially isolated (not knowing anyone else who has the condition) and may not be able to find reliable information about the disorder.

OBJECTIVE

The aim of this review is to search for apps developed specifically for people diagnosed with a rare disease and to assess them for quality using the Mobile App Rating Scale (MARS). We examine features that address 6 identified needs of people with a rare disorder and make recommendations for future developers.

METHODS

Google Play Store (Android) and Apple App Store (iOS) were searched for relevant health-related apps specifically for rare diseases. The search included the names of 10 rare disease groups. App quality was determined using MARS, assessing app engagement, functionality, aesthetics, and information.

RESULTS

We found 29 relevant apps (from a total of 2272) addressing 14 rare diseases or disease groups. The most common rare conditions addressed were cystic fibrosis (n=6), hemophilia (n=5), and thalassemia (n=5). The most common app features were web-based information and symptom trackers. The mean MARS score was 3.44 (SD 0.84). Lowest scores were for engagement.

CONCLUSIONS

Most apps provided factual and visual information, providing tools for self-monitoring and resources to help improve interactions during health consultations. App origin and quality varied greatly. Developers are recommended to consider ways to make appropriate apps more easily identifiable to consumers, to always include high-quality information, improve engagement, provide qualitative evaluations of the app, and include consumers and clinicians in the design.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson's Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson's disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

Investigating the Potential for Clinical Decision Support in Sub-Saharan Africa With AFYA (Artificial Intelligence-Based Assessment of Health Symptoms in Tanzania): Protocol for a Prospective, Observational Pilot Study

BACKGROUND

Low- and middle-income countries face difficulties in providing adequate health care. One of the reasons is a shortage of qualified health workers. Diagnostic decision support systems are designed to aid clinicians in their work and have the potential to mitigate pressure on health care systems.

OBJECTIVE

The Artificial Intelligence-Based Assessment of Health Symptoms in Tanzania (AFYA) study will evaluate the potential of an English-language artificial intelligence-based prototype diagnostic decision support system for mid-level health care practitioners in a low- or middle-income setting.

METHODS

This is an observational, prospective clinical study conducted in a busy Tanzanian district hospital. In addition to usual care visits, study participants will consult a mid-level health care practitioner, who will use a prototype diagnostic decision support system, and a study physician. The accuracy and comprehensiveness of the differential diagnosis provided by the diagnostic decision support system will be evaluated against a gold-standard differential diagnosis provided by an expert panel.

RESULTS

Patient recruitment started in October 2021. Participants were recruited directly in the waiting room of the outpatient clinic at the hospital. Data collection will conclude in May 2022. Data analysis is planned to be finished by the end of June 2022. The results will be published in a peer-reviewed journal.

CONCLUSIONS

Most diagnostic decision support systems have been developed and evaluated in high-income countries, but there is great potential for these systems to improve the delivery of health care in low- and middle-income countries. The findings of this real-patient study will provide insights based on the performance and usability of a prototype diagnostic decision support system in low- or middle-income countries.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04958577; http://clinicaltrials.gov/ct2/show/NCT04958577.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/34298.

[What is confirmed in the diagnostics of autoinflammatory fever diseases?]

Periodic fever syndromes (PFS) are a group of rare autoinflammatory diseases, which are characterized by disorders of the innate immune reaction and life-long recurrent episodes of inflammatory symptoms. This article describes the diagnostic approach. In addition to the patient medical history, physical examination and laboratory determinations, gene tests are becoming increasingly more important. The panel diagnostics using high throughput sequencing or next generation sequencing (NGS) is the method of choice for the detection of a genetic cause of PFS. This article discusses the diagnostic decision support systems (DDSS) that can play a future role in the diagnosis of rare diseases, especially those with complex patterns of symptoms.