ABSTRACT
Background: Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)-based time series data are rare. Objective: In this study, we aimed to detect the early occurrence of AKI by applying an interpretable long short-term memory (LSTM)-based model to hospital electronic health record (EHR)-based time series data in patients who took nephrotoxic drugs using a DRN. Methods: We conducted a multi-institutional retrospective cohort study of data from 6 hospitals using a DRN. For each institution, a patient-based data set was constructed using 5 drugs for AKI, and an interpretable multivariable LSTM (IMV-LSTM) model was used for training. This study used propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model's contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using 1-way ANOVA. Results: This study analyzed 8643 and 31,012 patients with and without AKI, respectively, across 6 hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median 12, IQR 5-25 days), and acyclovir was the slowest compared to the other drugs (median 23, IQR 10-41 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcvancomycin ium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase. Conclusions: Early surveillance of AKI outbreaks can be achieved by applying an IMV-LSTM based on time series data through an EHR-based DRN. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.
ABSTRACT
Background: Not all non-small cell lung cancer (NSCLC) patients will benefit from immune checkpoint therapy and use of these medications carry serious autoimmune adverse effects. Therefore, biomarkers are needed to better identify patients who will benefit from its use. Here, the correlation of overall survival (OS) with baseline and early treatment period serum biomarker responses was evaluated in patients with NSCLC undergoing immunotherapy. Methods: Patients diagnosed with NSCLC undergoing immunotherapy (n=597) at a tertiary academic medical center in South Korea were identified between January 2010 and November 2021. The neutrophil-lymphocyte ratio (NLR), C-reactive protein (CRP), and lactate dehydrogenase (LDH) levels in the survival and non-survival groups were examined at baseline and early treatment periods. Additionally, aberrant laboratory parameters at each period were used to stratify survival curves and examine their correlation with one-year OS. Results: In the non-survival group, the NLR, CRP, and LDH levels at the early treatment period were higher than those at the baseline (P<0.001). The survival curves stratified based on aberrant laboratory findings in each period varied (log-rank test P<0.001). Multivariate Cox regression analysis revealed that having prescribed more than 3rd line of chemotherapy [hazard ratio (HR) =3.19, 95% confidence interval (CI): 1.04-9.82; P=0.043] and early treatment period CRP (HR =3.88; 95% CI: 1.55-9.72; P=0.004) and LDH (HR =4.04; 95% CI: 2.01-8.12; P<0.001) levels were significant predictors of one-year OS. Conclusions: Early treatment period CRP and LDH levels were significant predictors of OS in patients with NSCLC undergoing immunotherapy.
ABSTRACT
BACKGROUND: Ischemic stroke with active cancer is thought to have a unique mechanism compared to conventional stroke etiologies. There is no gold standard guideline for secondary prevention in patients with cancer-related stroke, hence, adequate type of antithrombotic agent for treatment is controversial. METHODS: Subjects who were enrolled in National Health Insurance System Customized Research data during the period between 2010 and 2015 were observed until 2019. Subject diagnosed with ischemic stroke within six months before and 12 months after a cancer diagnosis was defined as cancer-related stroke patient. To solve immeasurable time bias, the drug exposure evaluation was divided into daily units, and each person-day was classified as four groups: antiplatelet, anticoagulant, both types, and unexposed to antithrombotic drugs. To investigate bleeding risk and mortality, Cox proportional hazards regression model with time-dependent covariates were used. RESULTS: Two thousand two hundred eighty-five subjects with cancer-related stroke were followed and analyzed. A group with anticoagulation showed high estimated hazard ratios (HRs) of all bleeding events compared to a group with antiplatelet (major bleeding HR, 1.35; 95% confidence interval [CI], 1.20-1.52; p < 0.001). And the result was also similar in the combination group (major bleeding HR, 1.54; 95% CI, 1.13-2.09; p = 0.006). The combination group also showed increased mortality HR compared to antiplatelet group (HR, 1.72; 95% CI, 1.47-2.00; p < 0.001). CONCLUSIONS: Bleeding risk increased in the anticoagulant-exposed group compared to antiplatelet-exposed group in cancer-related stroke patients. Thus, this result should be considered when selecting a secondary prevention drug.
Subject(s)
Ischemic Stroke , Neoplasms , Stroke , Humans , Fibrinolytic Agents/adverse effects , Cohort Studies , Stroke/drug therapy , Stroke/epidemiology , Republic of Korea/epidemiology , Anticoagulants/adverse effects , Neoplasms/complications , Neoplasms/epidemiologyABSTRACT
BACKGROUND: Childhood cancer has a high long-term morbidity and mortality rate. Five years after the initial cancer diagnosis, approximately two-thirds of childhood cancer survivors experience at least one late complication, with one-quarter experiencing severe, life-threatening complications. Chronic health conditions can impact survivors' life planning and daily activities, reducing their health-related quality of life. Comprehensive and longitudinal data are required for investigations of national claims data. OBJECTIVE: This study aimed to address clinical and health policy interventions and improved survival rates. A comprehensive categorization of the long-term morbidities associated with childhood cancer survivorship is required. We analyzed the trajectory groups associated with long-term mortality among childhood cancer survivors. METHODS: We collected data from a nationwide claims database of the entire Korean population. Between 2003 and 2007, patients diagnosed with and treated for cancer before the age of 20 years were included. With 8119 patients who survived >10 years, 3 trajectory groups were classified according to yearly changes in the number of diagnoses (the lowest in group 1 and the highest in group 3). RESULTS: The patterns of most comorbidities and survival rates differed significantly between the trajectory groups. Group 3 had a higher rate of mental and behavioral disorders, neoplasms, and blood organ diseases than the other two groups. Furthermore, there was a difference in the number of diagnoses by trajectory groups over the entire decade, and the disparity increased as the survival period increased. If a patient received more than four diagnoses, especially after the fourth year, the patient was likely to be assigned to group 3, which had the worst prognosis. Group 1 had the highest overall survival rate, and group 3 had the lowest (P<.001). Group 3 had the highest hazard ratio of 4.37 (95% CI 2.57-7.42; P<.001) in a multivariate analysis of late mortality. CONCLUSIONS: Our findings show that the pattern of comorbidities differed significantly among trajectory groups for late death, which could help physicians identify childhood cancer survivors at risk for late mortality. Patients with neoplasms, blood organ diseases, or mental and behavioral disorders should be identified as having an increased risk of late mortality. Furthermore, vigilance and prompt action are essential to mitigate the potential consequences of a child cancer survivor receiving four or more diagnoses within a year.
Subject(s)
Cancer Survivors , Neoplasms , Humans , Child , Young Adult , Adult , Cohort Studies , Neoplasms/epidemiology , Quality of Life , Retrospective Studies , ComorbidityABSTRACT
BACKGROUND: Adverse drug reactions (ADRs) are unintended negative drug-induced responses. Determining the association between drugs and ADRs is crucial, and several methods have been proposed to demonstrate this association. This systematic review aimed to examine the analytical tools by considering original articles that utilized statistical and machine learning methods for detecting ADRs. METHODS: A systematic literature review was conducted based on articles published between 2015 and 2020. The keywords used were statistical, machine learning, and deep learning methods for detecting ADR signals. The study was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement (PRISMA) guidelines. RESULTS: We reviewed 72 articles, of which 51 and 21 addressed statistical and machine learning methods, respectively. Electronic medical record (EMR) data were exclusively analyzed using the regression method. For FDA Adverse Event Reporting System (FAERS) data, components of the disproportionality method were preferable. DrugBank was the most used database for machine learning. Other methods accounted for the highest and supervised methods accounted for the second highest. CONCLUSIONS: Using the 72 main articles, this review provides guidelines on which databases are frequently utilized and which analysis methods can be connected. For statistical analysis, >90% of the cases were analyzed by disproportionate or regression analysis with each spontaneous reporting system (SRS) data or electronic medical record (EMR) data; for machine learning research, however, there was a strong tendency to analyze various data combinations. Only half of the DrugBank database was occupied, and the k-nearest neighbor method accounted for the greatest proportion.
Subject(s)
Adverse Drug Reaction Reporting Systems , Drug-Related Side Effects and Adverse Reactions , Databases, Factual , Drug-Related Side Effects and Adverse Reactions/epidemiology , Electronic Health Records , Humans , Machine LearningABSTRACT
BACKGROUND: Disability, which is considered a health-related condition, increases care demands and socioeconomic burdens for both families and communities. To confirm the trend of dynamic longitudinal changes in disability, this study aims to explore how disability is divided by the trajectory method, which deals with time-sequenced data. Additionally, this study examines the differences in demographics, geriatric conditions, and time spent at home among the trajectory groups in community-dwelling older adults. Home time is defined as the period during which the patient was not in a hospital or health care facility during their lifetime. METHODS: Records of 786 community-dwelling older participants were analyzed from the Aging Study of PyeongChang Rural Area, a population-based cohort study that took place over three years. Using 7 domains of activities of daily living and 10 domains of instrumental activities of daily living, participants were grouped into no dependency (0 disabled domain), mild (1 disabled domain), and severe (2 or more disabled domains) disability groups. The longitudinal trajectory group of disability was calculated as a trajectory method. Three distinct trajectory groups were calculated over time: a relatively-stable group (78.5%; n = 617), a gradually-aggravated group (16.0%; n = 126), and a rapidly-deteriorated group (5.5%; n = 43). RESULTS: The average age of 786 participants was 73.3 years (SD: 5.8), and the percentage of female was 52.7%. It was found that 78.5% of patients showed relatively no dependence and 5.5% of older adults in a rural area showed severe dependence. Through applying the trajectory method, it was shown that the Short Physical Performance Battery (SPPB) score was 10.2 points in the relatively-stable group and 3.1 points in the rapidly-deteriorating group by the 3rd year. Additionally, by the trajectory method, the rate of decrease in home time was 3.33% in the rapidly-deteriorated group compared to the relatively-stable group. CONCLUSIONS: This study shows the difference in demographics and geriatric conditions (such as SPPB) through the examination of longitudinal trajectory groups of disability in community-dwelling older adults. Significant differences were also found in the amount of home time among the trajectory groups.
Subject(s)
Disabled Persons , Independent Living , Activities of Daily Living , Aged , Cohort Studies , Disability Evaluation , Female , Geriatric Assessment , Humans , Republic of Korea/epidemiologyABSTRACT
Wait time and scheduling for outpatient chemotherapy administration depends on various factors including infusion room hours of operation, availability of oncologists, nursing and pharmacy staffing, and physical space limitations. The aim of this study was to use the electronic event log of patients on health information system (HIS) to map and analyze patient flow in advanced metastatic colorectal patients at an academic cancer center. From January 2009 to December 2014, patients who were diagnosed with metastatic colorectal cancer and received outpatient chemotherapy confined to FOLFIRI (fluorouracil, leucovorin, and irinotecan) or FOLFOX (folinic acid, fluorouracil, and oxaliplatin) were identified. From the HIS, patient flow was mapped by collection of event records including blood collection and pretreatment laboratory test, arrival to outpatient clinics, outpatient session (interview, drug accountability and appointment scheduling), and initiation of chemotherapy. A total of 10,638 patients were analyzed for 136,281 outpatient visits. The total office stay time from outpatient registration to initiation of chemotherapy was 92.58â±â87.96 (meanâ±âstandard deviation) minutes. Each outpatient session lasted 23.75â±â51.55 minutes. After completing the outpatient session, patients waited 1,657.23â±â3,027.65 minutes before chemotherapy and 46.66â±â75.94 minutes within infusion room. Compared to the prior first come first serve rule, the new reservation system showed an improvement in overall waiting time from 2,432.3â±â4,822.9 to 2,386.7â±â143.4 minutes; however, waiting time within infusion room slightly increased from 36.68â±â49.33 to 48.13â±â46.32 minutes. Our findings indicate that transaction data analytics from HIS can be used to evaluate patient flow within oncology outpatient practice based on real-world hospital data.
Subject(s)
Appointments and Schedules , Cancer Care Facilities/statistics & numerical data , Colorectal Neoplasms/therapy , Aged , Female , Humans , Male , Medical Oncology/methods , Middle Aged , Time FactorsABSTRACT
BACKGROUND: Home Internet of Things (IoT) services and devices have the potential to aid older adults and people with disabilities in their living environments. IoT services and devices can also aid caregivers and health care providers in conveniently providing care to those in need. However, real-world data on the IoT needs of vulnerable people are lacking. OBJECTIVE: The objective of this study is to conduct a face-to-face survey on the demand for IoT services among older people and people with disabilities, their caregivers, and health care providers in a real-world setting and to see if there are any differences in the aspects of need. METHODS: We conducted a face-to-face survey with 500 participants between January 2019 and March 2019. A total of 300 vulnerable people (200 older adults aged ≥65 years and 100 physically disabled people aged 30-64 years) were randomly sampled from either a population-based, prospective cohort study of aging-the Aging Study of Pyeongchang Rural Area (ASPRA)-or from the outpatient clinics at the Asan Medical Center, Seoul, South Korea. Simultaneously, their caregivers (n=150) and health care providers (n=50) participated in the survey. Detailed socioeconomic status, digital literacy, health and physical function, and home IoT service needs were determined. Among all commercially available IoT services, 27 services were classified into five categories: emergency and security, safety, health care, convenience (information), and convenience (operation). The weighted-ranking method was used to rank the IoT needs in different groups. RESULTS: There were discrepancies in the demand of IoT services among the vulnerable groups, their caregivers, and health care providers. The home IoT service category that was required the most by the vulnerable groups and their caregivers was emergency and security. However, health care providers indicated that the safety category was most needed by the older adults and disabled people. Home IoT service requirements differed according to the different types of disabilities among the vulnerable groups. Participants with fewer disabilities were more willing to use IoT services than those with more disabilities. CONCLUSIONS: Our survey study shows that there were discrepancies in the demand of IoT services among the vulnerable groups, their caregivers, and health care providers. IoT service requirements differed according to the various types of disabilities. Home IoT technology should be established by combining patients' priorities and individualized functional assessments among vulnerable people. TRIAL REGISTRATION: Clinical Research Information Service (CRIS; KCT0004157); https://tinyurl.com/r83eyva.
Subject(s)
Caregivers/standards , Disabled Persons/statistics & numerical data , Health Personnel/standards , Internet of Things/standards , Adult , Aged , Female , Humans , Male , Middle Aged , Prospective Studies , Surveys and QuestionnairesABSTRACT
BACKGROUND: Early detection or notification of adverse event (AE) occurrences during clinical trials is essential to ensure patient safety. Clinical trials take advantage of innovative strategies, clinical designs, and state-of-the-art technologies to evaluate efficacy and safety, however, early awareness of AE occurrences by investigators still needs to be systematically improved. OBJECTIVE: This study aimed to build a system to promptly inform investigators when clinical trial participants make unscheduled visits to the emergency room or other departments within the hospital. METHODS: We developed the Adverse Event Awareness System (AEAS), which promptly informs investigators and study coordinators of AE occurrences by automatically sending text messages when study participants make unscheduled visits to the emergency department or other clinics at our center. We established the AEAS in July 2015 in the clinical trial management system. We compared the AE reporting timeline data of 305 AE occurrences from 74 clinical trials between the preinitiative period (December 2014-June 2015) and the postinitiative period (July 2015-June 2016) in terms of three AE awareness performance indicators: onset to awareness, awareness to reporting, and onset to reporting. RESULTS: A total of 305 initial AE reports from 74 clinical trials were included. All three AE awareness performance indicators were significantly lower in the postinitiative period. Specifically, the onset-to-reporting times were significantly shorter in the postinitiative period (median 1 day [IQR 0-1], mean rank 140.04 [SD 75.35]) than in the preinitiative period (median 1 day [IQR 0-4], mean rank 173.82 [SD 91.07], P≤.001). In the phase subgroup analysis, the awareness-to-reporting and onset-to-reporting indicators of phase 1 studies were significantly lower in the postinitiative than in the preinitiative period (preinitiative: median 1 day, mean rank of awareness to reporting 47.94, vs postinitiative: median 0 days, mean rank of awareness to reporting 35.75, P=.01; and preinitiative: median 1 day, mean rank of onset to reporting 47.4, vs postinitiative: median 1 day, mean rank of onset to reporting 35.99, P=.03). The risk-level subgroup analysis found that the onset-to-reporting time for low- and high-risk studies significantly decreased postinitiative (preinitiative: median 4 days, mean rank of low-risk studies 18.73, vs postinitiative: median 1 day, mean rank of low-risk studies 11.76, P=.02; and preinitiative: median 1 day, mean rank of high-risk studies 117.36, vs postinitiative: median 1 day, mean rank of high-risk studies 97.27, P=.01). In particular, onset to reporting was reduced more in the low-risk trial than in the high-risk trial (low-risk: median 4-0 days, vs high-risk: median 1-1 day). CONCLUSIONS: We demonstrated that a real-time automatic alert system can effectively improve safety reporting timelines. The improvements were prominent in phase 1 and in low- and high-risk clinical trials. These findings suggest that an information technology-driven automatic alert system effectively improves safety reporting timelines, which may enhance patient safety.
ABSTRACT
Tamoxifen, an anti-estrogen agent that can suppress breast cancer, has been reported to increase endometrium-related adverse events. There are no guidelines for screening tamoxifen-treated patients for endometrial disease. We analyzed nationwide claims data related to endometrial diseases to investigate patterns of endometrial disease in breast cancer patients who underwent hormonal treatment.We sourced claims data from the Health Insurance Review and Assessment Service in South Korea. Patients who made their first claim for an anti-hormonal agent between January 1, 2010 and December 31, 2012 were enrolled retrospectively. We analyzed patient characteristics and all claims related to endometrial disease, stratified by prescribed hormonal agents.Among a total of 32,496 enrolled patients, 19,603 used tamoxifen only and 10,101 were treated with an aromatase inhibitor (AI) alone. Endometrial events occurred in 15.4% (3028/19603) of the tamoxifen-only patients and 2.0% (201/10101) of the AI-only group. In patients diagnosed with breast cancer at the age of 50 or older, the hazard ratio (HR) of endometrial malignancy in the tamoxifen-only group compared to the AI-only group was 4.13 (95% CI 1.404-12.159, P = .010). The HR of curettage in the tamoxifen-only group was 31.0 (95% CI 19.668-48.831, Pâ<.001).The occurrence of endometrial events among tamoxifen-treated breast cancer patients was higher than in patients treated with only AI, similar to previous studies. However, the HR of curettage was uniquely high, despite its invasiveness. Guidelines for screening endometrial disease and improvements of healthcare policy are required to appropriately manage high-risk patients.
Subject(s)
Antineoplastic Agents, Hormonal/therapeutic use , Aromatase Inhibitors/therapeutic use , Endometrium/pathology , Progression-Free Survival , Tamoxifen/therapeutic use , Adolescent , Adult , Age Factors , Aged , Aged, 80 and over , Antineoplastic Agents, Hormonal/administration & dosage , Antineoplastic Agents, Hormonal/adverse effects , Aromatase Inhibitors/administration & dosage , Aromatase Inhibitors/adverse effects , Drug Therapy, Combination , Female , Humans , Insurance Claim Review/statistics & numerical data , Middle Aged , Postmenopause , Proportional Hazards Models , Republic of Korea/epidemiology , Retrospective Studies , Tamoxifen/administration & dosage , Tamoxifen/adverse effects , Young AdultABSTRACT
BACKGROUND: Community-dwelling older adults living in rural areas are in a less favorable environment for health care compared with urban older adults. We believe that intermittent coaching through wearable devices can help optimize health care for older adults in medically limited environments. OBJECTIVE: We aimed to evaluate whether a wearable device and mobile-based intermittent coaching or self-management could increase physical activity and health outcomes of small groups of older adults in rural areas. METHODS: To address the above evaluation goal, we carried out the "Smart Walk" program, a health care model wherein a wearable device is used to promote self-exercise particularly among community-dwelling older adults managed by a community health center. We randomly selected older adults who had enrolled in a population-based, prospective cohort study of aging, the Aging Study of Pyeongchang Rural Area. The "Smart Walk" program was a 13-month program conducted from March 2017 to March 2018 and included 6 months of coaching, 1 month of rest, and 6 months of self-management. We evaluated differences in physical activity and health outcomes according to frailty status and conducted pre- and postanalyses of the Smart Walk program. We also performed intergroup analysis according to adherence of wearable devices. RESULTS: We recruited 22 participants (11 robust and 11 prefrail older adults). The two groups were similar in most of the variables, except for age, frailty index, and Short Physical Performance Battery score associated with frailty criteria. After a 6-month coaching program, the prefrail group showed significant improvement in usual gait speed (mean 0.73 [SD 0.11] vs mean 0.96 [SD 0.27], P=.02), International Physical Activity Questionnaire scores in kcal (mean 2790.36 [SD 2224.62] vs mean 7589.72 [SD 4452.52], P=.01), and European Quality of Life-5 Dimensions score (mean 0.84 [SD 0.07] vs mean 0.90 [SD 0.07], P=.02), although no significant improvement was found in the robust group. The average total step count was significantly different and was approximately four times higher in the coaching period than in the self-management period (5,584,295.83 vs 1,289,084.66, P<.001). We found that participants in the "long-self" group who used the wearable device for the longest time showed increased body weight and body mass index by mean 0.65 (SD 1.317) and mean 0.097 (SD 0.513), respectively, compared with the other groups. CONCLUSIONS: Our "Smart Walk" program improved physical fitness, anthropometric measurements, and geriatric assessment categories in a small group of older adults in rural areas with limited resources for monitoring. Further validation through various rural public health centers and in a large number of rural older adults is required.
ABSTRACT
BACKGROUND: Personal health records (PHRs) and mHealth apps are considered essential tools for patient engagement. Mobile PHRs (mPHRs) can be a platform to integrate patient-generated health data (PGHD) and patients' medical information. However, in previous studies, actual usage data and PGHD from mPHRs have not been able to adequately represent patient engagement. OBJECTIVE: By analyzing 5 years' PGHD from an mPHR system developed by a tertiary hospital in South Korea, we aimed to evaluate how PGHD were managed and identify issues in PGHD management based on actual usage data. Additionally, we analyzed how to improve patient engagement with mPHRs by analyzing the actively used services and long-term usage patterns. METHODS: We gathered 5 years (December 2010 to December 2015) of log data from both hospital patients and general users of the app. We gathered data from users who entered PGHD on body weight, blood pressure (BP), blood glucose levels, 10-year cardiovascular disease (CVD) risk, metabolic syndrome risk, medication schedule, insulin, and allergy. We classified users according to whether they were patients or general users based on factors related to continuous use (≥28 days for weight, BP, and blood glucose, and ≥180 days for CVD and metabolic syndrome), and analyzed the patients' characteristics. We compared PGHD entry counts and the proportion of continuous users for each PGHD by user type. RESULTS: The total number of mPHR users was 18,265 (patients: n=16,729, 91.59%) with 3620 users having entered weight, followed by BP (n=1625), blood glucose (n=1374), CVD (n=764), metabolic syndrome (n=685), medication (n=252), insulin (n=72), and allergy (n=61). Of those 18,256 users, 3812 users had at least one PGHD measurement, of whom 175 used the PGHD functions continuously (patients: n=142, 81.14%); less than 1% of the users had used it for more than 4 years. Except for weight, BP, blood glucose, CVD, and metabolic syndrome, the number of PGHD records declined. General users' continuous use of PGHD was significantly higher than that of patients in the blood glucose (P<.001) and BP (P=.03) functions. Continuous use of PGHD in health management (BP, blood glucose, and weight) was significantly greater among older users (P<.001) and men (P<.001). In health management (BP, weight, and blood glucose), overall chronic disease and continuous use of PGHD were not statistically related (P=.08), but diabetes (P<.001) and cerebrovascular diseases (P=.03) were significant. CONCLUSIONS: Although a small portion of users managed PGHD continuously, PGHD has the potential to be useful in monitoring patient health. To realize the potential, specific groups of continuous users must be identified, and the PGHD service must target them. Further evaluations for the clinical application of PGHD, feedback regarding user interfaces, and connections with wearable devices are needed.