ABSTRACT
ChatGPT (OpenAI) is an advanced natural language processing tool with growing applications across various disciplines in medical research. Thematic analysis, a qualitative research method to identify and interpret patterns in data, is one application that stands to benefit from this technology. This viewpoint explores the use of ChatGPT in three core phases of thematic analysis within a medical context: (1) direct coding of transcripts, (2) generating themes from a predefined list of codes, and (3) preprocessing quotes for manuscript inclusion. Additionally, we explore the potential of ChatGPT to generate interview transcripts, which may be used for training purposes. We assess the strengths and limitations of using ChatGPT in these roles, highlighting areas where human intervention remains necessary. Overall, we argue that ChatGPT can function as a valuable tool during analysis, enhancing the efficiency of the thematic analysis and offering additional insights into the qualitative data. While ChatGPT may not adequately capture the full context of each participant, it can serve as an additional member of the analysis team, contributing to researcher triangulation through knowledge building and sensemaking.
Subject(s)
Natural Language Processing , Humans , Qualitative ResearchABSTRACT
In current clinical practice, radiotherapy (RT) is prescribed as a pre-determined total dose divided over daily doses (fractions) given over several weeks. The treatment response is typically assessed months after the end of RT. However, the conventional one-dose-fits-all strategy may not achieve the desired outcome, owing to patient and tumor heterogeneity. Therefore, a treatment strategy that allows for RT dose personalization based on each individual response is preferred. Multiple strategies have been adopted to address this challenge. As an alternative to current known strategies, artificial intelligence (AI)-derived mechanism-independent small data phenotypic medicine (PM) platforms may be utilized for N-of-1 RT personalization. Unlike existing big data approaches, PM does not engage in model refining, training, and validation, and guides treatment by utilizing prospectively collected patient's own small datasets. With PM, clinicians may guide patients' RT dose recommendations using their responses in real-time and potentially avoid over-treatment in good responders and under-treatment in poor responders. In this paper, we discuss the potential of engaging PM to guide clinicians on upfront dose selections and ongoing adaptations during RT, as well as considerations and limitations for implementation. For practicing oncologists, clinical trialists, and researchers, PM can either be implemented as a standalone strategy or in complement with other existing RT personalizations. In addition, PM can either be used for monotherapeutic RT personalization, or in combination with other therapeutics (e.g. chemotherapy, targeted therapy). The potential of N-of-1 RT personalization with drugs will also be presented.
Subject(s)
Neoplasms , Precision Medicine , Humans , Precision Medicine/methods , Neoplasms/radiotherapy , Artificial Intelligence , Phenotype , Radiotherapy DosageABSTRACT
Aims: Artificial intelligence-driven small data platforms such as CURATE.AI hold potential for personalized hypertension care by assisting physicians in identifying personalized anti-hypertensive doses for titration. This trial aims to assess the feasibility of a larger randomized controlled trial (RCT), evaluating the efficacy of CURATE.AI-assisted dose titration intervention. We will also collect preliminary efficacy and safety data and explore stakeholder feedback in the early design process. Methods and results: In this open-label, randomized, pilot feasibility trial, we aim to recruit 45 participants with primary hypertension. Participants will be randomized in 1:1:1 ratio into control (no intervention), home blood pressure monitoring (active control; HBPM), or CURATE.AI arms (intervention; HBPM and CURATE.AI-assisted dose titration). The home treatments include 1 month of two-drug anti-hypertensive regimens. Primary endpoints assess the logistical (e.g. dose adherence) and scientific (e.g. percentage of participants for which CURATE.AI profiles can be generated) feasibility, and define the progression criteria for the RCT in a 'traffic light system'. Secondary endpoints assess preliminary efficacy [e.g. mean change in office blood pressures (BPs)] and safety (e.g. hospitalization events) associated with each treatment protocol. Participants with both baseline and post-treatment BP measurements will form the intent-to-treat analysis. Following their involvement with the CURATE.AI intervention, feedback from CURATE.AI participants and healthcare providers will be collected via exit survey and interviews. Conclusion: Findings from this study will inform about potential refinements of the current treatment protocols before proceeding with a larger RCT, or potential expansion to collect additional information. Positive results may suggest the potential efficacy of CURATE.AI to improve BP control. Trial registration number: NCT05376683.
ABSTRACT
Despite being a convenient clinical substrate for biomonitoring, saliva's widespread utilization has not yet been realized. The non-Newtonian, heterogenous, and highly viscous nature of saliva complicate the development of automated fluid handling processes that are vital for accurate diagnoses. Furthermore, conventional saliva processing methods are resource and/or time intensive precluding certain testing capabilities, with these challenges aggravated during a pandemic. The conventional approaches may also alter analyte structure, reducing application opportunities in point-of-care diagnostics. To overcome these challenges, we introduce the SHEAR saliva collection device that mechanically processes saliva, in a rapid and resource-efficient way. We demonstrate the device's impact on reducing saliva's viscosity, improving sample's uniformity, and increasing diagnostic performance of a COVID-19 rapid antigen test. Additionally, a formal user experience study revealed generally positive comments. SHEAR saliva collection device may support realization of the saliva's potential, particularly in large-scale and/or resource-limited settings for global and community diagnostics.
ABSTRACT
BACKGROUND: Physicians play a key role in integrating new clinical technology into care practices through user feedback and growth propositions to developers of the technology. As physicians are stakeholders involved through the technology iteration process, understanding their roles as users can provide nuanced insights into the workings of these technologies that are being explored. Therefore, understanding physicians' perceptions can be critical toward clinical validation, implementation, and downstream adoption. Given the increasing prevalence of clinical decision support systems (CDSSs), there remains a need to gain an in-depth understanding of physicians' perceptions and expectations toward their downstream implementation. This paper explores physicians' perceptions of integrating CURATE.AI, a novel artificial intelligence (AI)-based and clinical stage personalized dosing CDSSs, into clinical practice. OBJECTIVE: This study aims to understand physicians' perspectives of integrating CURATE.AI for clinical work and to gather insights on considerations of the implementation of AI-based CDSS tools. METHODS: A total of 12 participants completed semistructured interviews examining their knowledge, experience, attitudes, risks, and future course of the personalized combination therapy dosing platform, CURATE.AI. Interviews were audio recorded, transcribed verbatim, and coded manually. The data were thematically analyzed. RESULTS: Overall, 3 broad themes and 9 subthemes were identified through thematic analysis. The themes covered considerations that physicians perceived as significant across various stages of new technology development, including trial, clinical implementation, and mass adoption. CONCLUSIONS: The study laid out the various ways physicians interpreted an AI-based personalized dosing CDSS, CURATE.AI, for their clinical practice. The research pointed out that physicians' expectations during the different stages of technology exploration can be nuanced and layered with expectations of implementation that are relevant for technology developers and researchers.
Subject(s)
Decision Support Systems, Clinical , Physicians , Humans , Artificial Intelligence , Attitude of Health Personnel , Qualitative ResearchABSTRACT
Objective: Patient-reported outcome measures (PROMs) are useful standardized tools to measure current patient health status and well-being. While there are existing constipation-related PROMs, the majority of PROMs were not developed with adequate patient involvement and few examined content validity. Accordingly, the current study aimed to develop a constipation PROM with multiple phases of patient and clinician involvement. Methods: To generate PROM items, 15 patients with chronic constipation (age range =28-79 years, 10 females) underwent a qualitative interview exploring their experiences with chronic constipation. Following that, eight clinical experts completed the content validity index (CVI) ratings of all the items generated to assess content validity. Based on results of the content validity assessment, relevant items were maintained and 12 participants with chronic constipation were re-interviewed to obtain feedback about comprehensibility, comprehensiveness and relevance. Results: Six themes and 25 sub-themes emerged from the qualitative interview, and an initial list of 33 symptom items and 18 quality of life (QoL) items were generated. Based on the CVIs calculated, 11 symptom items and nine QoL items were maintained with the scale-content validity index indicating excellent content validity. Overall, participants indicated the PROM to be relevant, comprehensive and easy to understand however, minor amendments were made to improve the three qualities of interest. Conclusion: The current study developed a constipation PROM that measures both symptom severity and constipation-related QoL, with supporting evidence for relevance, comprehensiveness and comprehensibility. Further prioritization should be given to validating and exploring new digital modalities of PROM administration.
ABSTRACT
Health behaviors before, during and after pregnancy can have lasting effects on maternal and infant health outcomes. Although digital health interventions (DHIs) have potential as a pertinent avenue to deliver mechanisms for a healthy behavior change, its success is reliant on addressing the user needs. Accordingly, the current study aimed to understand DHI needs and expectations of women before, during and after pregnancy to inform and optimize future DHI developments. Forty-four women (13 pre-, 16 during and 15 postpregnancy; age range = 21-40 years) completed a 60-minute, semistructured, qualitative interview exploring participant's experience in their current phase, experience with digital health tools, and their needs and expectations of DHIs. Interviews were audio-recorded, transcribed verbatim and thematically analyzed. From the interviews, two core concepts emerged-personalization and localization of DHI. Between both concepts, five themes and nine subthemes were identified. Themes and subthemes within personalization cover ideas of two-way interactivity, journey organization based on phases and circumstances, and privacy trade-off. Themes and subthemes within localization cover ideas of access to local health-related resources and information, and connecting to local communities through anecdotal stories. Here we report, through understanding user needs and expectations, the key elements for the development and optimization of a successful DHI for women before, during and after pregnancy. To potentially empower downstream DHI implementation and adoption, these insights can serve as a foundation in the initial innovation process for DHI developers and be further built upon through a continued co-design process.
Subject(s)
Constipation , Health Knowledge, Attitudes, Practice , Humans , Singapore , Constipation/therapy , Constipation/drug therapy , Male , Female , Practice Patterns, Physicians'/statistics & numerical data , Surveys and Questionnaires , Middle Aged , Adult , Physicians/psychology , Attitude of Health PersonnelABSTRACT
Digital health interventions are being increasingly incorporated into health care workflows to improve the efficiency of patient care. In turn, sustained patient engagement with digital health interventions can maximize their benefits toward health care outcomes. In this viewpoint, we outline a dynamic patient engagement by using various communication channels and the potential use of omnichannel engagement to integrate these channels. We conceptualize a novel patient care journey where multiple web-based and offline communication channels are integrated through a "digital twin." The principles of implementing omnichannel engagement for digital health interventions and digital twins are also broadly covered. Omnichannel engagement in digital health interventions implies a flexibility for personalization, which can enhance and sustain patient engagement with digital health interventions, and ultimately, patient quality of care and outcomes. We believe that the novel concept of omnichannel engagement in health care can be greatly beneficial to patients and the system once it is successfully realized to its full potential.
Subject(s)
Patient Participation , Telemedicine , Humans , Communication , WorkflowABSTRACT
Objective: Chronic constipation is a prevalent gastrointestinal disorder that requires long-term management and treatment adherence. With increasing smartphone usage, health app adoption represents an opportunity to incorporate personalized, patient-led care into chronic constipation management. Despite the number of apps available targeting patients with constipation, studies have not yet examined user needs and barriers towards successful app adoption and sustained usage. Accordingly, the current study explored user perception, needs, and concerns of health apps in patients with chronic constipation. Methods: Fifteen participants with chronic constipation (age range = 28-79 years, 10 females) in Singapore completed a 60â min semi-structured qualitative interview exploring participant's experiences with and attitudes towards chronic constipation and health apps. Participants also completed two questionnaires regarding their constipation symptoms and general technology usage. Interviews were audio-recorded, transcribed verbatim, and coded using NVivo. Results: Four themes and 10 sub-themes were identified using inductive thematic analysis. Themes and sub-themes cover importance of patient identity, disease-based expectations of health apps, barriers towards adoption and sustained usage of health apps, necessary conditions when adopting health apps (including perception of supportive benefits, clear understanding of app intention, personalized technology, and trusted sources), and push factor expectations which includes creative engagement and incentivization embedded within the app. Conclusion: The findings captured barriers and key elements necessary for successful health app adoption and continued usage by patients with chronic constipation. Identified elements that matter to patients can provide app developers with user-focused insights and recommendations to develop effective health apps that sustain user engagement.
ABSTRACT
Background/Aims: Constipation can be a chronic condition that impacts daily functioning and quality of life (QoL). To aid healthcare providers in accurately assessing patient symptoms and treatment outcomes, patient-related outcome measures (PROMs) have been increasingly adopted in clinical settings. This review aims to (1) evaluate the methodological quality and measurement properties of constipation-related PROMs, using the COnsensus-based Standards for the selection of health Measurement INtruments (COSMIN) criteria; and (2) assess the modes of digital dissemination of constipation-related PROMs. Methods: PubMed, Embase, and PsycINFO databases were searched and 11 011 records ranging from 1989 to 2020 were screened by 2 independent reviewers. A total of 26 studies (23 PROMs; 18 measuring symptom-related items and 5 measuring constipation-related QoL items) were identified for the review and assessed. Results: There were multiple variations between PROMs, including subtypes of constipation, methods of administration, length of PROM and recall period. While no PROM met all the COSMIN quality standards for development and measurement properties, 5 constipation-related PROMs received at least 4 (out of 7) sufficient ratings. Only 2 PROMs were developed in Asia. Five PROMs were administered through digital methods during the validation process but methods of adapting the PROMs into digital formats were not reported. Conclusions: The constipation-related PROMs identified in this review present varying quality of development and validation, with an overall need for improvement. Further considerations should be given towards more consistent methodology and reporting of PROM development, increase in culturally-specific PROMs, and better reporting of protocol for the digitisation of PROMs.
ABSTRACT
Disrupted sleep through sleep deprivation or sleep fragmentation has previously been shown to impair cognitive processing. Nevertheless, limited studies have examined the impact of disrupted sleep on the processing of emotional information. The current study aimed to use an experimental approach to generate sleep disruption and examine whether SD and SF in otherwise healthy individuals would impair emotional facial processing. Thirty-five healthy individuals participated in three-day/two-night laboratory study which consisted of two consecutive overnight polysomnograms and cognitive testing during the day. The first night was an adaptation night of normal sleep while the second was an experimental night where participants underwent either a night of 1) normal sleep, 2) no sleep (SD) or 3) fragmented sleep (SF). The emotional Go/No-Go task was completed in the morning following each night. Data from 33 participants (14 females, mean age = 24.6 years) were included in the final analysis. Following a night of SD or SF, participants performed significantly poorer with emotional (fearful and happy) targets, while no significant changes occurred after a night of normal sleep. Further, sleep deprived individuals experienced additional impairments with notably poorer performance with neutral targets and slower reaction time for all targets, suggesting an overall slowing of cognitive processing speed. These findings suggest that facial recognition in socio-emotional contexts may be impaired in individuals who experience disrupted sleep.
Subject(s)
Emotions , Sleep Deprivation , Adult , Female , Humans , Male , Polysomnography , Reaction Time , Sleep , Sleep Deprivation/psychology , Young AdultABSTRACT
BACKGROUND: Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder that is associated with a range of adverse daytime sequelae, including significantly higher rates of clinical depression than is seen in the general community. Improvements in depressive symptoms occur after treatment of the primary sleep disorder, suggesting that comorbid depression might be an intrinsic feature of OSA. However, there are limited data on whether treatment for OSA in patients diagnosed with clinical depression improves mood symptoms meaningfully enough to lead to the remission of the psychiatric diagnosis. METHODS: N = 121 untreated OSA patients were randomized to either continuous positive airway pressure (CPAP) treatment or waitlist control, and depressive symptoms, sleepiness and clinical depression (using a structured clinical interview) were assessed at baseline and 4 months. Linear and logistic regression analyses were conducted, controlling for baseline scores, stratification factors and antidepressant use. RESULTS: Depressive symptoms (odds ratio [OR] = -4.19; 95% confidence interval [CI] = -7.25, -1.13; p = .008) and sleepiness (OR = -4.71; 95% CI = -6.26, -3.17; p < .001) were significantly lower at 4 months in the CPAP group compared to waitlist. At 4 months, there was a significant reduction in the proportion of participants in the CPAP group meeting criteria for clinical depression, compared to the waitlist controls (OR = 0.06, 95% CI = 0.01, 0.37; p = .002). CONCLUSION: Treatment of OSA may be a novel approach for the management and treatment of clinical depression in those with comorbid sleep disordered breathing. Larger trials of individuals with clinical depression and comorbid OSA are needed.
Subject(s)
Depressive Disorder, Major , Sleep Apnea, Obstructive , Continuous Positive Airway Pressure , Depression/epidemiology , Depression/therapy , Depressive Disorder, Major/epidemiology , Depressive Disorder, Major/therapy , Humans , Sleep , Sleep Apnea, Obstructive/epidemiology , Sleep Apnea, Obstructive/therapyABSTRACT
An intimate relationship exists between sleep and affective states. Disturbances in sleep are common across a spectrum of psychopathologies, and are recognised as precipitating or prodromal factors for mood disorders. Conversely, affective states can impact sleep quality and ability to fall asleep. However, one of the main limitations of this literature is that studies have typically assessed sleep and mood at one time point and studies are often laboratory-based, where measurement of both sleep and mood has dubious ecological validity. The aim of the current review was to systematically examine the evidence for associations between day-to-day fluctuations in sleep and mood in naturalistic studies using ambulatory diary techniques. Electronic databases (EMBASE, PsycINFO, PubMed, and SCOPUS) were searched for studies using experience sampling methodology to investigate daily associations between sleep and mood in naturalistic environments in healthy and clinical samples. Findings of the included studies supported the notion of a reciprocal relationship between subjective sleep variables (sleep quality, sleep duration and sleep latency) and daytime affective states over the short term, and highlight the potential clinical importance of daily sleep disturbance in the prediction and prevention of the development of psychopathology in the future.
Subject(s)
Emotions , Mood Disorders/physiopathology , Sleep Initiation and Maintenance Disorders/epidemiology , Humans , Mood Disorders/psychology , Sleep Initiation and Maintenance Disorders/physiopathologyABSTRACT
STUDY OBJECTIVES: Poor upper airway dilator muscle function may contribute to obstructive sleep apnea (OSA). Sleep deprivation reduces dilator muscle responsiveness, but sleep fragmentation, which is most characteristic of OSA, has not been assessed. This study compared the effects of sleep deprivation and fragmentation on dilator muscle responsiveness during wakefulness. METHODS: Twenty-four healthy individuals (10 female) participated in two consecutive overnight polysomnography (PSG) sessions. The first was an adaptation PSG of normal sleep. The second was an experimental PSG, where participants were allocated to groups of either normal sleep, no sleep, or fragmented sleep. Inspiratory resistive loading assessment occurred the morning following each PSG. Four 10 cmH2O and four 20 cmH2O loads were presented in random order for 60 seconds while participants were awake and supine. Sleep (electroencephalogram, electrooculogram, electromyogram [EMG]), intramuscular genioglossus activity (EMGGG), and ventilation were measured throughout the loading sessions. RESULTS: Five controls, seven sleep deprivation participants, and seven sleep fragmentation participants provided data. Contrary to expectations, neither EMGGG nor ventilation showed significant interaction effects (group × session × load) during resistive loading. There was a main effect of load, with peak EMGGG (mean % max ± standard error) significantly higher for the 20 cmH2O load (4.1 ± 0.6) than the 10 cmH2O load (3.3 ± 0.6) across both sessions and all groups. Similar results were observed for peak inspiratory flow, duty cycle, and mask pressure. CONCLUSIONS: Upper airway function was not affected by 1 night of no sleep or poor-quality sleep. This raises doubt as to whether fragmented sleep in OSA increases disorder severity via reduced upper airway dilator responses.
Subject(s)
Inhalation/physiology , Muscles/physiopathology , Sleep Deprivation/physiopathology , Tongue/physiopathology , Adult , Airway Resistance/physiology , Electromyography , Female , Humans , Male , Polysomnography , Young AdultABSTRACT
Obstructive sleep apnea is associated with memory impairments, and higher rates of depressive symptoms and major depressive disorder compared with community estimates. Autobiographical memory overgenerality, a behaviour characterized by difficulty recalling specific memories from one's own life, is recognized as a marker of depression. Previous studies have demonstrated the predictive quality of specific autobiographical memory recall on the course of depression in patients with obstructive sleep apnea. However, it remains unclear whether impaired autobiographical memory is simply a feature of depression, or whether it is also impaired in patients with obstructive sleep apnea without depression. This study aimed to investigate whether autobiographical memory impairments can be observed in patients with obstructive sleep apnea, independent of the severity of depressive symptoms. Twenty-one patients with obstructive sleep apnea symptomatic for depressive symptoms (mean age = 43.43 years, SD = 9.97), 17 patients with obstructive sleep apnea asymptomatic for depressive symptoms (mean age = 40.65 years, SD = 9.39), and 20 healthy controls without sleep-disordered breathing (mean age = 32.80 years, SD = 6.69) completed an Autobiographical Memory Test. Patients with obstructive sleep apnea symptomatic for depressive symptoms recalled significantly fewer specific memories when compared with healthy controls (P = 0.010). No difference in the recall of specific autobiographical memory was observed between symptomatic and asymptomatic patients with obstructive sleep apnea. With regard to valence, symptomatic patients with obstructive sleep apnea recalled significantly fewer negative specific memories when compared with controls (P = 0.010). Impairment in specific autobiographical memory recall can be observed in patients with obstructive sleep apnea, regardless of the severity of depressive symptoms; however, this effect may not be as prominent in younger patients with obstructive sleep apnea.