Dataset Information

Labtracker+, a medical smartphone app for the interpretation of consecutive laboratory results: an external validation study.

ABSTRACT:

Objectives

When monitoring patients over time, clinicians may struggle to distinguish 'real changes' in consecutive blood parameters from so-called natural fluctuations. In practice, they have to do so by relying on their clinical experience and intuition. We developed Labtracker+, a medical app that calculates the probability that an increase or decrease over time in a specific blood parameter is real, given the time between measurements.

Design

We presented patient cases to 135 participants to examine whether there is a difference between medical students, residents and experienced clinicians when it comes to interpreting changes between consecutive laboratory results. Participants were asked to interpret if changes in consecutive laboratory values were likely to be 'real' or rather due to natural fluctuations. The answers of the study participants were compared with the calculated probabilities by the app Labtracker+ and the concordance rates were assessed.

Setting and participants

Medical students (n=92), medical residents from the department of internal medicine (n=19) and internists (n=24) at a Dutch University Medical Centre.

Primary and secondary outcome measures

Concordance rates between the study participants and the calculated probabilities by the app Labtracker+ were compared. Besides, we tested whether physicians with clinical experience scored better concordance rates with the app Labtracker+ than inexperienced clinicians.

Results

Medical residents and internists showed significantly better concordance rates with the calculated probabilities by the app Labtracker+ than medical students, regarding their interpretation of differences between consecutive laboratory results (p=0.009?and p<0.001, respectively).

Conclusion

The app Labtracker+ could serve as a clinical decision tool in the interpretation of consecutive laboratory test results and could contribute to rapid recognition of parameter changes by physicians.

SUBMITTER: Hilderink JM

PROVIDER: S-EPMC5589013 | biostudies-literature | 2017 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

<i>Labtracker+</i>, a medical smartphone app for the interpretation of consecutive laboratory results: an external validation study.

Hilderink Judith M JM Rennenberg Roger J M W RJMW Vanmolkot Floris H M FHM Bekers Otto O Koopmans Richard P RP Meex Steven J R SJR

BMJ open 20170901 9

<h4>Objectives</h4>When monitoring patients over time, clinicians may struggle to distinguish 'real changes' in consecutive blood parameters from so-called natural fluctuations. In practice, they have to do so by relying on their clinical experience and intuition. We developed <i>Labtracker+</i>, a medical app that calculates the probability that an increase or decrease over time in a specific blood parameter is real, given the time between measurements.<h4>Design</h4>We presented patient cases ...[more]

PMID: 28864694

Similar Datasets

Project description:BackgroundAlthough alcohol breath testing devices that pair with smartphones are promoted for the prevention of alcohol-impaired driving, their accuracy has not been established.MethodsIn a within-subjects laboratory study, we administered weight-based doses of ethanol to two groups of 10 healthy, moderate drinkers aiming to achieve a target peak blood alcohol concentration (BAC) of 0.10%. We obtained a peak phlebotomy BAC and measured breath alcohol concentration (BrAC) with a police-grade device (Intoxilyzer 240) and two randomly ordered series of 3 consumer smartphone-paired devices (6 total devices) with measurements every 20 min until the BrAC reached <0.02% on the police device. Ten participants tested the first 3 devices, and the other 10 participants tested the other 3 devices. We measured mean paired differences in BrAC with 95% confidence intervals between the police-grade device and consumer devices.ResultsThe enrolled sample (N = 20) included 11 females; 15 white, 3 Asian, and 2 Black participants; with a mean age of 27 and mean BMI of 24.6. Peak BACs ranged from 0.06-0.14%. All 7 devices underestimated BAC by >0.01%, though the BACtrack Mobile Pro and police-grade device were consistently more accurate than the Drinkmate and Evoc. Compared with the police-grade device measurements, the BACtrack Mobile Pro readings were consistently higher, the BACtrack Vio and Alcohoot measurements similar, and the Floome, Drinkmake, and Evoc consistently lower. The BACtrack Mobile Pro and Alcohoot were most sensitive in detecting BAC driving limit thresholds, while the Drinkmate and Evoc devices failed to detect BAC limit thresholds more than 50% of the time relative to the police-grade device.ConclusionsThe accuracy of smartphone-paired devices varied widely in this laboratory study of healthy participants. Although some devices are suitable for clinical and research purposes, others underestimated BAC, creating the potential to mislead intoxicated users into thinking that they are fit to drive.

Project description:BackgroundNovel wearable biosensors, ubiquitous smartphone ownership, and telemedicine are converging to enable new paradigms of clinical research. A new generation of continuous glucose monitoring (CGM) devices provides access to clinical-grade measurement of interstitial glucose levels. Adoption of these sensors has become widespread for the management of type 1 diabetes and is accelerating in type 2 diabetes. In parallel, individuals are adopting health-related smartphone-based apps to monitor and manage care.ObjectiveWe conducted a proof-of-concept study to investigate the potential of collecting robust, annotated, real-time clinical study measures of glucose levels without clinic visits.MethodsSelf-administered meal-tolerance tests were conducted to assess the impact of a proprietary synbiotic medical food on glucose control in a 6-week, double-blind, placebo-controlled, 2×2 cross-over pilot study (n=6). The primary endpoint was incremental glucose measured using Abbott Freestyle Libre CGM devices associated with a smartphone app that provided a visual diet log.ResultsAll subjects completed the study and mastered CGM device usage. Over 40 days, 3000 data points on average per subject were collected across three sensors. No adverse events were recorded, and subjects reported general satisfaction with sensor management, the study product, and the smartphone app, with an average self-reported satisfaction score of 8.25/10. Despite a lack of sufficient power to achieve statistical significance, we demonstrated that we can detect meaningful changes in the postprandial glucose response in real-world settings, pointing to the merits of larger studies in the future.ConclusionsWe have shown that CGM devices can provide a comprehensive picture of glucose control without clinic visits. CGM device usage in conjunction with our custom smartphone app can lower the participation burden for subjects while reducing study costs, and allows for robust integration of multiple valuable data types with glucose levels remotely.Trial registrationClinicalTrials.gov NCT04424888; http://clinicaltrials.gov/ct2/show/NCT04424888.

Project description:BackgroundThe decline of cognitive processing speed (CPS) is a common dysfunction in persons with multiple sclerosis (MS). The Symbol Digit Modalities Test (SDMT) is widely used to formally quantify CPS. We implemented a variant of the SDMT in MS sherpa, a smartphone app for persons with MS.ObjectiveThe aim of this study was to investigate the construct validity and test-retest reliability of the MS sherpa smartphone variant of the SDMT (sSDMT).MethodsWe performed a validation study with 25 persons with relapsing-remitting MS and 79 healthy control (HC) subjects. In the HC group, 21 subjects were matched to the persons with MS with regard to age, gender, and education and they followed the same assessment schedule as the persons with MS (the "HC matched" group) and 58 subjects had a less intense assessment schedule to determine reference values (the "HC normative" group). Intraclass correlation coefficients (ICCs) were determined between the paper-and-pencil SDMT and its smartphone variant (sSDMT) on 2 occasions, 4 weeks apart. Other ICCs were determined for test-retest reliability, which were derived from 10 smartphone tests per study participant, with 3 days in between each test. Seven study participants with MS were interviewed regarding their experiences with the sSDMT.ResultsThe SDMT scores were on average 12.06% higher than the sSDMT scores, with a standard deviation of 10.68%. An ICC of 0.838 was found for the construct validity of the sSDMT in the combined analysis of persons with MS and HC subjects. Average ICCs for test-retest reliability of the sSDMT for persons with MS, the HC matched group, and the HC normative group were 0.874, 0.857, and 0.867, respectively. The practice effect was significant between the first and the second test of the persons with MS and the HC matched group and trivial for all other test-retests. The interviewed study participants expressed a positive attitude toward the sSDMT, but they also discussed the importance of adapting a smartphone cognition test in accordance with the needs of the individual persons with MS.ConclusionsThe high correlation between sSDMT and the conventional SDMT scores indicates a very good construct validity. Similarly, high correlations underpin a very good test-retest reliability of the sSDMT. We conclude that the sSDMT has the potential to be used as a tool to monitor CPS in persons with MS, both in clinical studies and in clinical practice.

Project description:BackgroundPrevious studies have suggested that resident physicians are the most meaningful teachers during the clinical clerkships of third-year medical students (MS3s). Unfortunately, residents often feel unprepared for this crucial role. The pediatrics clerkship at our institution identified a paucity in the frequency of resident-led teaching with MS3s. Lack of confidence, suboptimal teaching space, and insufficient time were cited as the most significant barriers. To enhance resident-led teaching of MS3s, we created teaching scripts of general pediatrics topics accessible via a smartphone application (app).MethodsPrior to the implementation of the app, MS3s and pediatric residents were surveyed on clerkship teaching practices. From May 2017 through July 2018, pediatric residents working with MS3s were introduced to the app, with both groups queried on resident teaching habits afterward. We compared pre-intervention and post-intervention data of time spent teaching, teaching frequency, and a ranking of pediatric resident teaching performance compared to residents of other MS3 core clerkships.Results44 out of 90 residents (49%) responded to a pre-intervention survey on baseline teaching habits. 49 out of 61 residents (80%) completed our post-intervention survey. Pre-intervention, 75% (33/44) of residents reported spending less than 5 min per teaching session on average. Post-intervention, 67% (33/49) reported spending more than 5 min (p < 0.01). 25% (11/44) of residents reported teaching at least once per day pre-intervention, versus 55% (27/49, p = 0.12) post-intervention. Post-intervention data demonstrated a statistically significant correlation between app use and increased frequency of teaching (p < 0.01). The MS3 average ranking of pediatric resident teaching increased from 2.4 to 3.4 out of 6 (p < 0.05) after this intervention.ConclusionsResidency programs looking to reform resident-led teaching, particularly of residents early in their training, should consider our novel approach. In addition to addressing barriers to teaching and creating a platform for near-peer teaching, it is adaptable to any specialty or learner level. Future direction includes developing objective measures for teaching performance and content proficiency to better assess our intervention as an educational curriculum, as well as further investigation of the intervention as a controlled trial.

Project description:BackgroundGenetic testing allows patients and clinicians to understand the risk of hereditary diseases. By testing early, individuals can make informed medical decisions about management which may minimize the risk of developing certain diseases. Importantly, genetic test results may also be applicable to patients' biological relatives; thus, these results could also lead to minimizing their risk of disease. However, sharing genetic test results between patients and their relatives is scarce. The most frequently reported problems are that patients cannot clearly explain this information and relatives misinterpret the results. Smartphone apps in the healthcare field are a possible solution as they allow patients to accurately share sensitive information to others, while providing educational material to support understanding the information. However, these apps may not provide security to protect patients' identifiable information. We developed ShareDNA, a smartphone app that (1) allows patients to securely share their genetic test results with others, (2) provides information on how to interpret these results, and (3) minimizes the amount of patient information needed to use the service.ResultsWe recruited thirteen participants to test the usability of our app and provide feedback. We found overall that participants were comfortable with using this app and could easily learn each app function when filling out our questionnaire. Additionally, based on vocalized impressions of the usefulness of the app, participants indicated that the user-interface could be more intuitive and that we needed to add more text within the app to explain why ShareDNA is a secure service.ConclusionsShareDNA is a free smartphone app that allows patients to share their genetic test results with others, including their biological relatives. Sharing these results along with educational material will enable relatives to share accurate information and discuss their possible risk for disease with their clinical providers. As a result, appropriate testing in relatives could be improved.

Project description:BackgroundRapid digitalization in health care has led to the adoption of digital technologies; however, limited trust in internet-based health decisions and the need for technical personnel hinder the use of smartphones and machine learning applications. To address this, automated machine learning (AutoML) is a promising tool that can empower health care professionals to enhance the effectiveness of mobile health apps.ObjectiveWe used AutoML to analyze data from clinical studies involving patients with chronic hand and/or foot eczema or psoriasis vulgaris who used a smartphone monitoring app. The analysis focused on itching, pain, Dermatology Life Quality Index (DLQI) development, and app use.MethodsAfter extensive data set preparation, which consisted of combining 3 primary data sets by extracting common features and by computing new features, a new pseudonymized secondary data set with a total of 368 patients was created. Next, multiple machine learning classification models were built during AutoML processing, with the most accurate models ultimately selected for further data set analysis.ResultsItching development for 6 months was accurately modeled using the light gradient boosted trees classifier model (log loss: 0.9302 for validation, 1.0193 for cross-validation, and 0.9167 for holdout). Pain development for 6 months was assessed using the random forest classifier model (log loss: 1.1799 for validation, 1.1561 for cross-validation, and 1.0976 for holdout). Then, the random forest classifier model (log loss: 1.3670 for validation, 1.4354 for cross-validation, and 1.3974 for holdout) was used again to estimate the DLQI development for 6 months. Finally, app use was analyzed using an elastic net blender model (area under the curve: 0.6567 for validation, 0.6207 for cross-validation, and 0.7232 for holdout). Influential feature correlations were identified, including BMI, age, disease activity, DLQI, and Hospital Anxiety and Depression Scale-Anxiety scores at follow-up. App use increased with BMI >35, was less common in patients aged >47 years and those aged 23 to 31 years, and was more common in those with higher disease activity. A Hospital Anxiety and Depression Scale-Anxiety score >8 had a slightly positive effect on app use.ConclusionsThis study provides valuable insights into the relationship between data characteristics and targeted outcomes in patients with chronic eczema or psoriasis, highlighting the potential of smartphone and AutoML techniques in improving chronic disease management and patient care.