Machine Learning Supports Automated Digital Image Scoring of Stool Consistency in Diapers.

BACKGROUND/AIMS: Accurate stool consistency classification of non-toilet-trained children remains challenging. This study evaluated the feasibility of automated classification of stool consistencies from diaper photos using machine learning (ML). METHODS: In total, 2687 usable smartphone photos of diapers with stool from 96 children younger than 24 months were obtained after independent ethical study approval. Stool consistency was assessed from each photo according to the original 7 types of the Brussels Infant and Toddler Stool Scale independently by study participants and 2 researchers. A health care professional assigned a final score in case of scoring disagreement between the researchers. A proof-of-concept ML model was built upon this collected photo database, using transfer learning to re-train the classification layer of a pretrained deep convolutional neural network model. The model was built on random training (n = 2478) and test (n = 209) subsets. RESULTS: Agreements between study participants and both researchers were 58.0% and 48.5%, respectively, and between researchers 77.5% (assessable n = 2366). The model classified 60.3% of the test photos in exact agreement with the final score. With respect to the 4-class grouping of the 7 Brussels Infant and Toddler Stool Scale types, the agreement between model-based and researcher classification was 77.0%. CONCLUSION: The automated and objective scoring of stool consistency from diaper photos by the ML model shows robust agreement with human raters and overcomes limitations of other methods relying on caregiver reporting. Integrated with a smartphone application, this new framework for photo database construction and ML classification has numerous potential applications in clinical studies and home assessment.

Effectiveness of a peer-led self-management programme for people with schizophrenia: protocol for a randomized controlled trial.

AIM: To determine the effectiveness of a peer-led self-management programme for people with schizophrenia in reducing psychotic symptom severity, hospital readmission and psychiatric consultation and in enhancing cognition, empowerment, functioning level, medication adherence, perceived recovery, quality of life and social support. BACKGROUND: Several self-management programmes have been developed to empower patients with severe mental illness in achieving recovery. Research suggests that peer-led self-management programmes have positive effects on patient recovery. However, the existing evidence is inconclusive, due to a lack of credible evidence and long-term follow-up evaluations. DESIGN: A stratified randomized controlled trial will be conducted at six community mental health rehabilitation centres METHODS: A sample of 242 adults with schizophrenia will be recruited. A peer-led self-management programme, comprising six 2-hour sessions, will be implemented in the intervention group and a standard rehabilitation programme in the control group. Outcomes will be measured at baseline, postintervention and at the 6- and 12-month follow-ups. The measures will include cognition, empowerment, functioning level, medication adherence, perceived recovery, quality of life, social support, symptom severity, hospital readmission and psychiatric consultation. A mixed effects model will be used to analyse the results. Semi-structured interviews will be conducted to explore the peer-trainers' and participants' perspectives on the programme. Research Ethics Committee approval was obtained in December 2011 and funding was obtained in January 2012. CONCLUSION: This study will provide evidence on the effectiveness of a peer-led self-management programme for patient recovery. It will identify a clinically useful and potentially effective intervention that incorporates empowerment concept.

A Chatbot to Engage Parents of Preterm and Term Infants on Parental Stress, Parental Sleep, and Infant Feeding: Usability and Feasibility Study.

BACKGROUND: Parents commonly experience anxiety, worry, and psychological distress in caring for newborn infants, particularly those born preterm. Web-based therapist services may offer greater accessibility and timely psychological support for parents but are nevertheless labor intensive due to their interactive nature. Chatbots that simulate humanlike conversations show promise for such interactive applications. OBJECTIVE: The aim of this study is to explore the usability and feasibility of chatbot technology for gathering real-life conversation data on stress, sleep, and infant feeding from parents with newborn infants and to investigate differences between the experiences of parents with preterm and term infants. METHODS: Parents aged ≥21 years with infants aged ≤6 months were enrolled from November 2018 to March 2019. Three chatbot scripts (stress, sleep, feeding) were developed to capture conversations with parents via their mobile devices. Parents completed a chatbot usability questionnaire upon study completion. Responses to closed-ended questions and manually coded open-ended responses were summarized descriptively. Open-ended responses were analyzed using the latent Dirichlet allocation method to uncover semantic topics. RESULTS: Of 45 enrolled participants (20 preterm, 25 term), 26 completed the study. Parents rated the chatbot as "easy" to use (mean 4.08, SD 0.74; 1=very difficult, 5=very easy) and were "satisfied" (mean 3.81, SD 0.90; 1=very dissatisfied, 5 very satisfied). Of 45 enrolled parents, those with preterm infants reported emotional stress more frequently than did parents of term infants (33 vs 24 occasions). Parents generally reported satisfactory sleep quality. The preterm group reported feeding problems more frequently than did the term group (8 vs 2 occasions). In stress domain conversations, topics linked to "discomfort" and "tiredness" were more prevalent in preterm group conversations, whereas the topic of "positive feelings" occurred more frequently in the term group conversations. Interestingly, feeding-related topics dominated the content of sleep domain conversations, suggesting that frequent or irregular feeding may affect parents' ability to get adequate sleep or rest. CONCLUSIONS: The chatbot was successfully used to collect real-time conversation data on stress, sleep, and infant feeding from a group of 45 parents. In their chatbot conversations, term group parents frequently expressed positive emotions, whereas preterm group parents frequently expressed physical discomfort and tiredness, as well as emotional stress. Overall, parents who completed the study gave positive feedback on their user experience with the chatbot as a tool to express their thoughts and concerns. TRIAL REGISTRATION: ClinicalTrials.gov NCT03630679; https://clinicaltrials.gov/ct2/show/NCT03630679.

Serial monitoring of nutritional status in Chinese peritoneal dialysis patients by Subjective Global Assessment and comprehensive Malnutrition Inflammation Score.

AIM: The Malnutrition Inflammation Score (MIS) has been proposed for the assessment of nutritional status in peritoneal dialysis (PD) patients. The MIS and the Subjective Global Assessment (SGA) for serial monitoring of nutritional status in PD patients were compared. METHODS: The change in the MIS and SGA overall score of 59 PD patients (28 male) over 12 months was studied. Clinical factors relating to the discrepancy between the two instruments were explored. RESULTS: The average patient age was 55.8+/-9.7 years. Thirty of the 59 patients (50.8%) had exact agreement in the changed MIS and SGA scores. Cohen's kappa score was 0.274, indicating a modest degree of agreement. For the detection of deterioration in nutritional status and using the MIS as the reference measure, the SGA had a sensitivity of 61.9% and specificity of 86.8%; serum ferritin level was substantially higher in the ones whose SGA did not detect a deterioration in nutrition (1464.1+/-873.3 vs 800.5+/-561.6 pmol/L, P=0.046). For the detection of improvement in nutritional status, the SGA had a sensitivity of 45.8% and specificity of 82.9%; patients whose SGA did not detect an improvement in nutrition were dialyzed longer (53.8+/-35.3 vs 27.6+/-18.9 months, P=0.038), had higher total iron binding capacity (TIBC) (45.6+/-5.5 vs 38.2+/-8.1 micromol/L, P=0.015), had higher total Kt/V (2.02+/-0.36 vs 1.75+/-0.23, P=0.048) and higher normalized protein nitrogen appearance (1.16+/-0.25 vs 0.95+/-0.23 g/kg per day, P=0.048). CONCLUSION: The longitudinal changes in the MIS and SGA score have modest agreement with each other. However, PD patients with a longer duration of dialysis, higher serum ferritin, TIBC, total Kt/V or normalized protein nitrogen appearance tend to have discrepancies between the longitudinal changes in the MIS and SGA overall score.

Risk factors for contact lens-related fusarium keratitis: a case-control study in Singapore.

OBJECTIVE: To evaluate the specific contact lens-related or other factors that may contribute to the outbreak of Fusarium keratitis. METHODS: A case-control study was conducted of Fusarium keratitis in contact lens users in Singapore from March 1, 2005, to May 31, 2006, and included 61 patients with Fusarium keratitis and 188 population-based and 179 hospital-based control subjects. Interviewers asked about contact lens solution use and other risk factors. RESULTS: Patients with Fusarium keratitis were more likely to use ReNu contact lens solutions (Bausch & Lomb, Rochester, NY) 58 [95.1%] of 61 cases) than were either population-based (62 [34.3%] of 181) or hospital-based (50 [30.1%] of 166) control subjects. After controlling for age, sex, contact lens hygiene, and other factors, the use of ReNu with MoistureLoc significantly increased the risk of Fusarium keratitis (odds ratio, 99.3; 95% confidence interval, 18.4-535.4; P<.001), and the risk was 5 times higher compared with the risk with use of ReNu MultiPlus, a multipurpose solution (odds ratio, 21.5; 95% confidence interval, 4.0-115.5; P<.001). CONCLUSIONS: The use of ReNu contact lens solutions significantly increased the risk of contact lens-related Fusarium keratitis in Singapore. Our data support the recall of ReNu MultiPlus from the Singapore market and the need for further investigations into the role of ReNu MultiPlus in the development of Fusarium keratitis in other populations.

The relationship between anterior chamber depth and the presence of diabetes in the Tanjong Pagar Survey.

PURPOSE: To examine the relationships of diabetes with anterior chamber depth, axial length, and refraction. DESIGN: Population-based cross-sectional study. METHODS: This analysis included 943 Singapore Chinese subjects ages 40 to 81 years from the Tanjong Pagar Survey. Diabetes was determined by self-report. A-mode ultrasound was used to measure axial dimensions. Refraction was performed with an autorefractor and refined subjectively. RESULTS: There were 140 (11.4%) participants with diabetes. After controlling for age and gender, participants with diabetes had shallower anterior chambers (2.78 vs 2.91 mm, P = .004) and thicker lenses (4.88 vs 4.75 mm, P = .003), but similar spherical equivalent refraction (-0.38 vs -0.47 diopters [D], P = .73), axial length (23.09 vs 23.19 mm, P = .40), and vitreous chamber depth (15.52 vs 15.59 mm, P = .53). CONCLUSIONS: In the Singapore Chinese population, persons with diabetes have shallower anterior chambers and thicker lenses than those without diabetes. Diabetes may be a risk factor for angle closure glaucoma (ACG).