Characterising user engagement with mHealth for chronic disease self-management and impact on machine learning performance

Mobile Health (mHealth) has the potential to be transformative in the management of chronic conditions. Machine learning can leverage self-reported data collected with apps to predict periods of increased health risk, alert users, and signpost interventions. Despite this, mHealth must balance the treatment burden of frequent self-reporting and predictive performance and safety. Here we report how user engagement with a widely used and clinically validated mHealth app, myCOPD (designed for the self-management of Chronic Obstructive Pulmonary Disease), directly impacts the performance of a machine learning model predicting an acute worsening of condition (i.e., exacerbations). We classify how users typically engage with myCOPD, finding that 60.3% of users engage frequently, however, less frequent users can show transitional engagement (18.4%), becoming more engaged immediately ( < 21 days) before exacerbating. Machine learning performed better for users who engaged the most, however, this performance decrease can be mostly offset for less frequent users who engage more near exacerbation. We conduct interviews and focus groups with myCOPD users, highlighting digital diaries and disease acuity as key factors for engagement. Users of mHealth can feel overburdened when self-reporting data necessary for predictive modelling and confidence of recognising exacerbations is a significant barrier to accurate self-reported data. We demonstrate that users of mHealth should be encouraged to engage when they notice changes to their condition (rather than clinically defined symptoms) to achieve data that is still predictive for machine learning, while reducing the likelihood of disengagement through desensitisation.

Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations

BACKGROUND

The occurrences of acute complications arising from hypoglycemia and hyperglycemia peak as young adults with type 1 diabetes (T1D) take control of their own care. Continuous glucose monitoring (CGM) devices provide real-time glucose readings enabling users to manage their control proactively. Machine learning algorithms can use CGM data to make ahead-of-time risk predictions and provide insight into an individual's longer term control.

METHODS

We introduce explainable machine learning to make predictions of hypoglycemia (<70 mg/dL) and hyperglycemia (>270 mg/dL) up to 60 minutes ahead of time. We train our models using CGM data from 153 people living with T1D in the CITY (CGM Intervention in Teens and Young Adults With Type 1 Diabetes)survey totaling more than 28 000 days of usage, which we summarize into (short-term, medium-term, and long-term) glucose control features along with demographic information. We use machine learning explanations (SHAP [SHapley Additive exPlanations]) to identify which features have been most important in predicting risk per user.

RESULTS

Machine learning models (XGBoost) show excellent performance at predicting hypoglycemia (area under the receiver operating curve [AUROC]: 0.998, average precision: 0.953) and hyperglycemia (AUROC: 0.989, average precision: 0.931) in comparison with a baseline heuristic and logistic regression model.

CONCLUSIONS

Maximizing model performance for glucose risk prediction and management is crucial to reduce the burden of alarm fatigue on CGM users. Machine learning enables more precise and timely predictions in comparison with baseline models. SHAP helps identify what about a CGM user's glucose control has led to predictions of risk which can be used to reduce their long-term risk of complications.

Exploring the Validity of GOLD 2023 Guidelines: Should GOLD C and D Be Combined?

Introduction

The GOLD (Global Initiative for Chronic Obstructive Lung Disease) 2023 guidelines proposed important changes to the stratification of disease severity using the "ABCD" assessment tool. The highest risk groups "C" and "D" were combined into a single category "E" based on exacerbation history, no longer considering symptomology.

Purpose

We quantify the differential disease progression of individuals initially stratified by the GOLD 2022 "ABCD" scheme to evaluate these proposed changes.

Patients and Methods

We utilise data collected from 1529 users of the myCOPD mobile app, a widely used and clinically validated app supporting people living with COPD in the UK. For patients in each GOLD group, we quantify symptoms using COPD Assessment Tests (CAT) and rate of exacerbation over a 12-month period post classification.

Results

CAT scores for users initially classified into GOLD C and GOLD D remain significantly different after 12 months (Kolmogorov-Smirnov statistic = 0.59, P = 8.2 × 10-23). Users initially classified into GOLD C demonstrate a significantly lower exacerbation rate over the 12 months post classification than those initially in GOLD D (Kolmogorov-Smirnov statistic = 0.26; P = 3.1 × 10-2; all exacerbations). Further, those initially classified as GOLD B have higher CAT scores and exacerbation rates than GOLD C in the following 12 months.

Conclusion

CAT scores remain important for stratifying disease progression both in-terms of symptomology and future exacerbation risk. Based on this evidence, the merger of GOLD C and GOLD D should be reconsidered.

COVID-19 Oximetry @home: evaluation of patient outcomes

BACKGROUND

COVID-19 has placed unprecedented demands on hospitals. A clinical service, COVID-19 Oximetry @home (CO@h) was launched in November 2020 to support remote monitoring of COVID-19 patients in the community. Remote monitoring through CO@h aims to identify early patient deterioration and provide timely escalation for cases of silent hypoxia, while reducing the burden on secondary care.

METHODS

We conducted a retrospective service evaluation of COVID-19 patients onboarded to CO@h from November 2020 to March 2021 in the North Hampshire (UK) community led service (a collaboration of 15 General Practitioner (GP) practices covering 230 000 people). We have compared outcomes for patients admitted to Basingstoke and North Hampshire Hospital who were CO@h patients (COVID-19 patients with home monitoring of oxygen saturation (SpO₂; n=115), with non-CO@h patients (those directly admitted without being monitored by CO@h (n=633)). Crude and adjusted OR analysis was performed to evaluate the effects of CO@h on patient outcomes of 30-day mortality, Intensive care unit (ICU) admission and hospital length of stay greater than 3, 7, 14 and 28 days.

RESULTS

Adjusted ORs for CO@h show an association with a reduction for several adverse patient outcome: 30-day hospital mortality (p<0.001, OR 0.21, 95% CI 0.08 to 0.47), hospital length of stay larger than 3 days (p<0.05, OR 0.62, 95% CI 0.39 to 1.00), 7 days (p<0.001, OR 0.35, 95% CI 0.22 to 0.54), 14 days (p<0.001, OR 0.22 95% CI, 0.11 to 0.41), and 28 days (p<0.05, OR 0.21, 95% CI 0.05 to 0.59). No significant reduction ICU admission was observed (p>0.05, OR 0.43, 95% CI 0.15 to 1.04). Within 30 days of hospital admission, there were no hospital readmissions for those on the CO@h service as opposed to 8.7% readmissions for those not on the service.

CONCLUSIONS

We have demonstrated a significant association between CO@h and better patient outcomes; most notably a reduction in the odds of hospital lengths of stays longer than 7, 14 and 28 days and 30-day hospital mortality.

Use of image cytometry to classify biliary and ampullary adenocarcinomas

OBJECTIVE

To create an objective classification system to perform TNM classification of ampullary adenocarcinoma and cholangiocarcinoma using image cytometric data derived from Feulgen-stained tumor nuclei.

STUDY DESIGN

Surgically resected cases of ampullary adenocarcinoma and cholangiocarcinoma with established TNM classifications were selected on the basis of available formalin-fixed, paraffin-embedded tissue. Fifteen numerical variables related to morphometric, densitometric and textural features of each tumor nucleus were recorded. We employed a methodology based on multivariate statistical tools to characterize the association of morphonuclear variables with TNM classification. The first step consisted of identifying and selecting representative nuclei of each T class. From this "purified" data set an objective classification system was created. The classification system was assessed using internal and external validation.

RESULTS

Employing ANOVA, all 15 variables were significantly associated with T classification, 11 of 15 with N and 4 with M. Multivariate analysis was employed to distinguish between T1, T2 and T3 lesions. Our methodology correctly classified 76% of T1 nuclei, 47% of T2 nuclei and 84% of T3 nuclei. Heterogeneity within an individual tumor was defined in 61% of cases included in the training set. Complete concordance between pathologic classification and the classification system was observed in 71% of an independent validation.

Mesenteric tumor emboli manifested as recurrent abdominal pain

Mesenteric tumor emboli have been rarely reported in the literature. Tumors associated with this phenomenon include aortic angiosarcomas, pulmonary neoplasms, Hodgkin's lymphoma, and renal cell carcinoma. In most cases, presentation is dramatic and death is rapid. We present a case of mesenteric tumor emboli from an aortic source that had a more subtle presentation with recurrent abdominal pain and leukocytosis.

In vitro influence of Phaseolus vulgaris, Griffonia simplicifolia, concanavalin A, wheat germ, and peanut agglutinins on HCT-15, LoVo, and SW837 human colorectal cancer cell growth

BACKGROUND/AIMS

Compared with normal colonic mucosa, lectin receptor expression is increased in hyperplastic and neoplastic tissues; some lectins have been shown to influence human colonic epithelial cell proliferation. The aim was to assess further the influence of five lectins (Phaseolus vulgaris (PNA), Griffonia simplicifolia (GSA), concanavalin A (Con A), wheat germ (WGA), and peanut (PHA-L) agglutinins) on cellular growth in three human colorectal cancer cell lines (LoVo, HCT-15 and SW837).

METHODS

Cells were cultured in four lectin concentrations (0.1, 1.0, 10, and 100 micrograms/ml) and growth assessed at days 2, 3, 5, and 7. The experiments were performed in media supplemented with either 1% or 10% fetal calf serum (FCS). Growth was assessed using the MTT (3-(4,5)-dimethylthiazol-2-yl)-2,5-diphenyl tetrazolium bromide) colorimetric assay.

RESULTS

Growth in each cell line was greatly affected by at least two of the lectins tested. There was some variation in the effect of a given lectin on different cell lines. Lectin effects showed a dose-response and the greatest effects generally resulted from the highest concentrations at the longest culture time. WGA and Con A induced large effects in all cell lines; the effects of Con A were partly blocked by the higher concentration of FCS. PNA had modest and uniform stimulatory effects overall. The effects of GSA and PHA-L varied between cell lines.

CONCLUSIONS

The lectins studied all have the potential to affect colonic cancer growth in vitro. Many dietary lectins are resistant to digestion and may have important effects in vitro but the definition of their role in human colonic cancer biology must take into account the variability in lectin response.

H. pylori infection and GI disease: what critical care physicians need to know. Who should be tested for H. pylori? When is treatment needed?

Helicobacter (Campylobacter) pylori infection has emerged as a major cause of gastritis, peptic ulcers, and gastric malignancies. Not all patients with H. pylori infection require treatment; however, for those with ulcer disease (particularly those with bleeding), antibiotic therapy can be curative. To confirm infection (or its eradication), use the rapid urease assay, serologic examination or, when available, the urea breath test. Treatment options include triple therapy (with bismuth subsalicylate, metronidazole, and either tetracycline or amoxicillin) and dual therapy (with omeprazole and either amoxicillin or clarithromycin). For patients with an active ulcer, follow antibiotic therapy with ranitidine or omeprazole.

Tissue penetration of clindamycin in diabetic foot infections

Serum and tissue samples were obtained during surgery from four diabetics with neuropathy who underwent debridement or amputation for foot infections while receiving clindamycin 600 or 900 mg iv. Clindamycin concentrations were assayed by radioimmunoassay. Clindamycin was detected in all serum and tissue samples (range: 0.04-2.8 mg/kg in tissues and 1.1-11.1 mg/L in serum). In nine of the eleven tissue samples the clindamycin concentration exceeded the MICs reported for many pathogens commonly involved in such infections. In only a single instance was the ratio of tissue to serum concentration < 0.13.