The oral health status and treatment needs of adults with intellectual disabilities in Auckland.

AIMS: Adults with intellectual disabilities (ID) are known to have poor oral health and complex dental needs requiring treatment under general anesthesia (GA). This retrospective chart review aimed to provide information on the oral health status and treatment needs of adults with ID in Auckland. METHODS AND RESULTS: Data on 1075 adult patients with ID seen through the Auckland public dental service during the period June 2016 to April 2020 were drawn from electronic notes. Analyses focused on age group differences and the characteristics associated with the use of GA for dental treatment. More cumulative caries experience, poorer oral hygiene, and more missing teeth were observed among those who were older. About half (50.8%) of the patients used GA for dental treatment. This proportion was higher among those who were younger, less independent, non-verbal, with poorer oral hygiene, or who had active decay. CONCLUSION: Adults with ID are a heterogeneous population with unmet dental treatment needs. Different age groups require consideration of distinct characteristics for dental care provision. It is important to be for public sector service provision to be developed to consider predictors for GA service use in patients who are younger, less independent, non-verbal, or have active decay.

Clinical Service Incorporating Mobile Technology on Weight Loss in Patients With Metabolic Dysfunction-Associated Steatotic Liver Disease: A Translation From Research Trial.

BACKGROUND: The prevalence and healthcare cost of metabolic dysfunction-associated steatotic liver disease (MASLD) has increased alongside the epidemic surge in obesity and Type 2 diabetes. Weight loss through lifestyle modification remains the primary effective therapy for MASLD. Incorporation of mobile technology in lifestyle interventions has been previously found to be efficacious and cost-effective in facilitating weight loss. However, there is a paucity of studies that have successfully translated lifestyle research into clinical service for weight loss to alleviate disease burden. Our study aimed to describe the process of translating a mobile technology-enabled trial into a tertiary hospital outpatient dietetics service for patients with MASLD. METHODS: The Iowa Model of Evidence-Based Practice to Improve Quality Care was used as a framework for this paper to guide implementation at the organizational level. RESULTS: Regular engagement of key operational staff and the hospital management team facilitated open discussions of the challenges faced and enabled rapid implementation of strategies that contributed to the smooth piloting of the service. A service adoption rate of 81% was achieved. Preliminary outcome evaluation found that the percentage of patients achieving ≥ 5% weight loss from baseline at 6 months was comparable at 54% and 52% for the service and trial groups, respectively. CONCLUSIONS: Evaluation of the implementation process found that a hybrid model of care (in-person consultation supplemented with app coaching) preserved interpersonal connections while maximizing the convenience and scalability of mobile app-enabled service. Although high digital acceptance and adoption rates propelled by COVID-19-supported telehealth, it is prudent to assess patient's access to technology and digital literacy and offer resources to help them benefit from telehealth services.

Increased Systemic Levels of Centrally Acting B-Type Natriuretic Peptide Are Associated with Chronic Itch of Different Types.

B-type natriuretic peptide (BNP) is an itch-selective neuropeptide that was shown to play a role in both histaminergic and nonhistaminergic itch in mice. It was also shown that elevated serum BNP is linked to increased pruritus in nondiabetic hemodialysis patients. This study examined plasma BNP levels of 77 patients and N-terminal pro-BNP levels of 33 patients with differing types of chronic itch to see whether BNP and N-terminal pro-BNP levels can correlate with itch severity. Plasma BNP and N-terminal pro-BNP levels of all patients with itch correlated with itch numerical rating scale and in particular for patients with chronic pruritus of unknown origin. On the basis of this clinical observation, this study further showed that increasing pathophysiological levels of BNP in mice by intravenous or osmotic pump induced significant scratching. In addition, pharmacological and ablation strategies determined that BNP acts centrally by activating the natriuretic peptide receptor A in the dorsal horn of the spinal cord. These data support that BNP and N-terminal pro-BNP levels are associated with chronic itch and may be used in clinical setting.

Smoke exposure and childhood atopic eczema and food allergy: A systematic review and meta-analysis.

BACKGROUND: There is no consensus on the effect of timing and type of smoke exposure on early allergy development. This study aimed to determine the relationship between early eczema or food allergy/hypersensitivity development in children by firstly investigating the effect of smoke exposure across critical development periods and secondly by analyzing effects of parental atcive or passive smoking. METHODS: Four databases (PubMed, Web of Science, Scopus and Embase) were searched in May 2022 and assessed by two independent reviewers. Case-control, cross-sectional or cohort studies reporting on smoke exposure from preconception to postnatal periods and atopic eczema, food allergy and/or hypersensitivity outcomes by age 3 years were included. The Newcastle-Ottawa Scale was used to assess study quality. Random effects model was used to estimate the pooled risk ratios. RESULTS: From 1689 identified records, 32 studies with nearly 190,000 subjects were included. Parental smoking during preconception, pregnancy and postnatal periods was generally not associated with the risk of eczema, food allergy and food sensitisation development by age 3 years. Maternal active smoking during pregnancy was negatively associated with self-reported doctor diagnosis of eczema (RR = 0.87, 95% CI 0.77-0.98; I2 = 50.56) and maternal passive smoking during pregnancy was positively associated with clinician assessment of eczema in one study (RR = 1.38; 95% CI 1.06-1.79). CONCLUSION: Our findings highlighted the importance of in utero programming in early-life allergy development. Despite the weak evidence, our results suggest pregnant women should minimise their contact with second-hand smoke to prevent offspring eczema development. There is a need for greater utilisation of objective allergy assessments in future studies.

Clinical predictors of wheeze trajectories and associations with allergy in Asian children.

BACKGROUND: Childhood wheezing is a highly heterogeneous condition with an incomplete understanding of the characteristics of wheeze trajectories, particularly for persistent wheeze. OBJECTIVE: To characterize predictors and allergic comorbidities of distinct wheeze trajectories in a multiethnic Asian cohort. METHODS: A total of 974 mother-child pairs from the prospective Growing Up in Singapore Towards healthy Outcomes (GUSTO) cohort were included in this study. Wheeze and allergic comorbidities in the first 8 years of life were assessed using the modified International Study of Asthma and Allergies in Childhood questionnaires and skin prick tests. Group-based trajectory modeling was used to derive wheeze trajectories and regression was used to assess associations with predictive risk factors and allergic comorbidities. RESULTS: There were 4 wheeze trajectories derived, including the following: (1) early-onset with rapid remission from age 3 years (4.5%); (2) late-onset peaking at age 3 years and rapidly remitting from 4 years (8.1%); (3) persistent with a steady increase to age 5 years and high wheeze occurrence until 8 years (4.0%); and (4) no or low wheeze (83.4%). Early-onset wheezing was associated with respiratory infections during infancy and linked to subsequent nonallergic rhinitis throughout childhood. Late-onset and persistent wheeze shared similar origins characterized by parent-reported viral infections in later childhood. However, persistent wheezing was generally more strongly associated with a family history of allergy, parent-reported viral infections in later childhood, and allergic comorbidities as compared with late-onset wheezing. CONCLUSION: The timing of viral infection occurrence may determine the type of wheeze trajectory development in children. Children with a family history of allergy and viral infections in early life may be predisposed to persistent wheeze development and the associated comorbidities of early allergic sensitization and eczema.

Deep learning assessment compared to radiologist reporting for metastatic spinal cord compression on CT.

Introduction: Metastatic spinal cord compression (MSCC) is a disastrous complication of advanced malignancy. A deep learning (DL) algorithm for MSCC classification on CT could expedite timely diagnosis. In this study, we externally test a DL algorithm for MSCC classification on CT and compare with radiologist assessment. Methods: Retrospective collection of CT and corresponding MRI from patients with suspected MSCC was conducted from September 2007 to September 2020. Exclusion criteria were scans with instrumentation, no intravenous contrast, motion artefacts and non-thoracic coverage. Internal CT dataset split was 84% for training/validation and 16% for testing. An external test set was also utilised. Internal training/validation sets were labelled by radiologists with spine imaging specialization (6 and 11-years post-board certification) and were used to further develop a DL algorithm for MSCC classification. The spine imaging specialist (11-years expertise) labelled the test sets (reference standard). For evaluation of DL algorithm performance, internal and external test data were independently reviewed by four radiologists: two spine specialists (Rad1 and Rad2, 7 and 5-years post-board certification, respectively) and two oncological imaging specialists (Rad3 and Rad4, 3 and 5-years post-board certification, respectively). DL model performance was also compared against the CT report issued by the radiologist in a real clinical setting. Inter-rater agreement (Gwet's kappa) and sensitivity/specificity/AUCs were calculated. Results: Overall, 420 CT scans were evaluated (225 patients, mean age=60 ± 11.9[SD]); 354(84%) CTs for training/validation and 66(16%) CTs for internal testing. The DL algorithm showed high inter-rater agreement for three-class MSCC grading with kappas of 0.872 (p<0.001) and 0.844 (p<0.001) on internal and external testing, respectively. On internal testing DL algorithm inter-rater agreement (κ=0.872) was superior to Rad 2 (κ=0.795) and Rad 3 (κ=0.724) (both p<0.001). DL algorithm kappa of 0.844 on external testing was superior to Rad 3 (κ=0.721) (p<0.001). CT report classification of high-grade MSCC disease was poor with only slight inter-rater agreement (κ=0.027) and low sensitivity (44.0), relative to the DL algorithm with almost-perfect inter-rater agreement (κ=0.813) and high sensitivity (94.0) (p<0.001). Conclusion: Deep learning algorithm for metastatic spinal cord compression on CT showed superior performance to the CT report issued by experienced radiologists and could aid earlier diagnosis.

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT.

PURPOSE: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians. METHODS: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC. RESULTS: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001). CONCLUSION: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Post-mRNA vaccine flares in autoimmune inflammatory rheumatic diseases: Results from the COronavirus National Vaccine registry for ImmuNe diseases SINGapore (CONVIN-SING).

BACKGROUND: Studies of flares of autoimmune inflammatory rheumatic diseases (AIIRD) after COVID-19 mRNA vaccination are limited by small sample size, short follow up or at risk of selection bias. METHODS: A national retrospective cohort study of consecutive AIIRD patients ≥12 years old, across 8 hospitals who received at least one dose of a COVID-19 mRNA vaccine. Patients were included from the date of 1st vaccine dose and censored at the time of flare or on the date of the clinic visit at least 3 months from cohort entry, whichever came first. Predictors of flare were determined by Cox proportional hazards analysis. FINDINGS: 4627 patients (73% Chinese, 71% female) of median (IQR) age 61 (48, 70) years were included; 42% Rheumatoid arthritis, 14% Systemic lupus erythematosus and 11% Psoriatic arthritis. 47% were in remission, 41% low disease activity, 10% moderate disease activity and 1% in high disease activity. 18% patients flared, of which 11.7% were within the 3-month period of interest. 11.8% patients improved. Median (IQR) time-to-flare was 60 (30, 114) days. 25% flares were self-limiting, 61% mild-moderate and 14% severe. Older patients (53-65 years and >66 years) had a lower risk of flare [HR 0.6 (95% CI 0.5-0.8) and 0.7 (0.6-0.8) respectively]. Patients with inflammatory arthritis and with active disease had a higher risk of flare [HR 1.5 (1.2-2.0) and 1.4 (1.2-1.6), respectively]. Treatment with conventional synthetic disease-modifying anti-rheumatic drugs (csDMARDs), immunosuppression and prednisolone was also associated with an increased risk of flare [HR 1.5 (1.1-2), 1.2 (1.1-1.4) and 1.5 (1.2-1.8) for prednisolone ≤7.5 mg respectively]. INTERPRETATION: There was a moderately high rate of AIIRD flares after mRNA vaccination but also improvement in several patients. Severe flares and hospitalisation were rare. Thus, vaccination remains safe and highly recommended.

Psychological Health of Surgeons in a Time of COVID-19: A Global Survey.

OBJECTIVE: To assess the degree of psychological impact among surgical providers during the COVID-19 pandemic. SUMMARY OF BACKGROUND DATA: The COVID-19 pandemic has extensively impacted global healthcare systems. We hypothesized that the degree of psychological impact would be higher for surgical providers deployed for COVID-19 work, certain surgical specialties, and for those who knew of someone diagnosed with, or who died, of COVID-19. METHODS: We conducted a global web-based survey to investigate the psychological impact of COVID-19. The primary outcomes were the depression anxiety stress scale-21 and Impact of Event Scale-Revised scores. RESULTS: A total of 4283 participants from 101 countries responded. 32.8%, 30.8%, 25.9%, and 24.0% screened positive for depression, anxiety, stress, and PTSD respectively. Respondents who knew someone who died of COVID-19 were more likely to screen positive for depression, anxiety, stress, and PTSD (OR 1.3, 1.6, 1.4, 1.7 respectively, all P < 0.05). Respondents who knew of someone diagnosed with COVID-19 were more likely to screen positive for depression, stress, and PTSD (OR 1.2, 1.2, and 1.3 respectively, all P < 0.05). Surgical specialties that operated in the head and neck region had higher psychological distress among its surgeons. Deployment for COVID- 19-related work was not associated with increased psychological distress. CONCLUSIONS: The COVID-19 pandemic may have a mental health legacy outlasting its course. The long-term impact of this ongoing traumatic event underscores the importance of longitudinal mental health care for healthcare personnel, with particular attention to those who know of someone diagnosed with, or who died of COVID-19.

Chronic pruritus in multiple sclerosis and clinical correlates.

BACKGROUND: To date, little is known about the prevalence of itch in multiple sclerosis (MS) and its characteristics. OBJECTIVES: In this cross-sectional study, we assessed the prevalence, intensity and characteristics of chronic pruritus in MS patients and its effect on quality-of-life and association with MS symptoms, clinical signs, comorbidities and MRI findings. METHODS: MS patients presenting to an outpatient neurology clinic were asked about their current symptoms. Those who experienced chronic pruritus were administered the Standardized Itch Questionnaire and Itch Quality of Life forms. All patients' medical records were reviewed. Patients with any medical conditions associated with chronic itch were excluded. RESULTS: Seventy-seven total MS patients were included, and 27 (35%) reported pruritus. The average itch NRS severity was 5.42 (range 0-10). The most affected body parts were the extremities, face or scalp, and trunk. Itch was characterized as acute (74%), paroxysmal (59%) and tingling (55%). Heat (52%) was the most common aggravating factor, while cold temperatures had no effect. Compared with MS patients without itch, itch patients reported more fatigue (77% vs 44%, p = 0.004), heat sensitivity (48% vs 20%, p = 0.0177), cognitive impairment (62% vs 26%, p = 0.0029) and depression or anxiety (48% vs 16%, p = 0.0063). Additionally, itch patients had more T2 hyperintensities in the posterior cervical cord and anterior pons/ventromedial medulla (74.1% vs 46.0%, p = 0.018 and 29.6% vs 8.0%, p = 0.020, respectively). Finally, T2 hyperintensities in the anterior pons/ventromedial medulla were strongly associated with itch localized to the face or scalp (OR 11.3, 95% CI 1.6-78.6, p = 0.025). CONCLUSION: MS patients experience paroxysmal neuropathic pruritus that is most frequently localized to the extremities, face or scalp. Patients with itch were more likely to have MS-related comorbidities and demyelinating lesions in the spinal cord or brainstem.

Latent Class Analysis Identifies Distinct Phenotypes of Systemic Lupus Erythematosus Predictive of Flares after mRNA COVID-19 Vaccination: Results from the Coronavirus National Vaccine Registry for ImmuNe Diseases SINGapore (CONVIN-SING).

We recently reported that messenger ribonucleic acid (mRNA) coronavirus disease 2019 (COVID-19) vaccination was associated with flares in 9% of patients with systemic lupus erythematosus (SLE). Herein, we focused our analysis on patients from a multi-ethnic Southeast Asian lupus cohort with the intention of identifying distinct phenotypes associated with increased flares after mRNA COVID-19 vaccination. METHODS: Six hundred and thirty-three SLE patients from eight public healthcare institutions were divided into test and validation cohorts based on healthcare clusters. Latent class analysis was performed based on age, ethnicity, gender, vaccine type, past COVID-19 infection, interruption of immunomodulatory/immunosuppressive treatment for vaccination, disease activity and background immunomodulatory/immunosuppressive treatment as input variables. Data from both cohorts were then combined for mixed effect Cox regression to determine which phenotypic cluster had a higher risk for time to first SLE flare, adjusted for the number of vaccine doses. RESULTS: Two clusters were identified in the test (C1 vs. C2), validation (C1' vs. C2') and combined (C1″ vs. C2″) cohorts, with corresponding clusters sharing similar characteristics. Of 633 SLE patients, 88.6% were female and there was multi-ethnic representation with 74.9% Chinese, 14.2% Malay and 4.6% Indian. The second cluster (C2, C2' and C2″) was smaller compared to the first. SLE patients in the second cluster (C2 and C2') were more likely to be male, non-Chinese and younger, with higher baseline disease activity. The second cluster (C2″) had more incident flares (hazard ratio = 1.4, 95% confidence interval 1.1-1.9, p = 0.014) after vaccination. A higher proportion of patients in C2″ had immunomodulatory/immunosuppressive treatment interruption for vaccination as compared to patients in C1″ (6.6% vs. 0.2%) (p < 0.001). CONCLUSION: We identified two distinct phenotypic clusters of SLE with different patterns of flares following mRNA COVID-19 vaccination. Caution has to be exercised in monitoring for post-vaccination flares in patients with risk factors for flares such as non-Chinese ethnicity, young age, male gender and suboptimal disease control at the time of vaccination.

Impact of Traditional and Non-Traditional Lipid Parameters on Outcomes after Intravenous Thrombolysis in Acute Ischemic Stroke.

Contradicting evidence exists regarding the role of lipids in outcomes following intravenous (IV) thrombolysis with tissue plasminogen activator (tPA). Restricted cubic spline curves and adjusted logistic regression were used to evaluate associations of low-density lipoprotein cholesterol (LDL-C), non-high-density lipoprotein cholesterol (non-HDL-C), total cholesterol (TC), high-density lipoprotein cholesterol (HDL-C) and LDL-C/HDL-C ratio with poor functional outcome, symptomatic intracranial hemorrhage (SICH) and 90-day mortality, among 1004 acute ischemic stroke (AIS) patients who received IV tPA in a comprehensive stroke center. Quartile (Q) 1, Q2 and Q3 of HDL-C were associated with increased odds of poor functional outcome (adjusted odds ratio (adjOR) 1.66, 95% CI 1.06-2.60, p = 0.028, adjOR 1.63, 95% CI 1.05-2.53, p = 0.027, adjOR 1.56, 95% CI 1.01-2.44, p = 0.048) compared to Q4. Q2 and Q4 of non-HDL-C were associated with increased odds of SICH (adjOR 4.28, 95% CI 1.36-18.90, p = 0.025, adjOR 5.17, 95% CI 1.64-22.81, p = 0.011) compared to Q3. Q1 and Q2 of LDL-C was associated with increased odds of mortality (adjOR 2.57, 95% CI 1.27-5.57, p = 0.011 and adjOR 2.28, 95% CI 1.10-5.02, p = 0.032) compared to Q3. In AIS patients who received IV tPA, low LDL-C was associated with increased odds of mortality while HDL-C may be protective against poor functional outcome.

Cholecystectomy for asymptomatic gallstones: Markov decision tree analysis.

Gallstones are a common public health problem, especially in developed countries. There are an increasing number of patients who are diagnosed with gallstones due to increasing awareness and liberal use of imaging, with 22.6%-80% of gallstone patients being asymptomatic at the time of diagnosis. Despite being asymptomatic, this group of patients are still at life-long risk of developing symptoms and complications such as acute cholangitis and acute biliary pancreatitis. Hence, while early prophylactic cholecystectomy may have some benefits in selected groups of patients, the current standard practice is to recommend cholecystectomy only after symptoms or complications occur. After reviewing the current evidence about the natural course of asymptomatic gallstones, complications of cholecystectomy, quality of life outcomes, and economic outcomes, we recommend that the option of cholecystectomy should be discussed with all asymptomatic gallstone patients. Disclosure of material information is essential for patients to make an informed choice for prophylactic cholecystectomy. It is for the patient to decide on watchful waiting or prophylactic cholecystectomy, and not for the medical community to make a blanket policy of watchful waiting for asymptomatic gallstone patients. For patients with high-risk profiles, it is clinically justifiable to advocate cholecystectomy to minimize the likelihood of morbidity due to complications.

Diagnostic Accuracy of CT for Metastatic Epidural Spinal Cord Compression.

BACKGROUND: Early diagnosis of metastatic epidural spinal cord compression (MESCC) is vital to expedite therapy and prevent paralysis. Staging CT is performed routinely in cancer patients and presents an opportunity for earlier diagnosis. METHODS: This retrospective study included 123 CT scans from 101 patients who underwent spine MRI within 30 days, excluding 549 CT scans from 216 patients due to CT performed post-MRI, non-contrast CT, or a gap greater than 30 days between modalities. Reference standard MESCC gradings on CT were provided in consensus via two spine radiologists (11 and 7 years of experience) analyzing the MRI scans. CT scans were labeled using the original reports and by three radiologists (3, 13, and 14 years of experience) using dedicated CT windowing. RESULTS: For normal/none versus low/high-grade MESCC per CT scan, all radiologists demonstrated almost perfect agreement with kappa values ranging from 0.866 (95% CI 0.787-0.945) to 0.947 (95% CI 0.899-0.995), compared to slight agreement for the reports (kappa = 0.095, 95%CI -0.098-0.287). Radiologists also showed high sensitivities ranging from 91.51 (95% CI 84.49-96.04) to 98.11 (95% CI 93.35-99.77), compared to 44.34 (95% CI 34.69-54.31) for the reports. CONCLUSION: Dedicated radiologist review for MESCC on CT showed high interobserver agreement and sensitivity compared to the current standard of care.

Association Between Mobile Health App Engagement and Weight Loss and Glycemic Control in Adults With Type 2 Diabetes and Prediabetes (D'LITE Study): Prospective Cohort Study.

BACKGROUND: Mobile health apps are increasingly used as early intervention to support behavior change for diabetes prevention and control, with the overarching goal of lowering the overall disease burden. OBJECTIVE: This prospective cohort study conducted in Singapore aimed to investigate app engagement features and their association with weight loss and improved glycemic control among adults with diabetes and prediabetes from the intervention arm of the Diabetes Lifestyle Intervention using Technology Empowerment randomized controlled trial. METHODS: Diabetes and prediabetes participants (N=171) with a median age of 52 years, BMI of 29.3 kg/m2, and glycated hemoglobin (HbA1c) level of 6.5% and who were being assigned the Nutritionist Buddy Diabetes app were included. Body weight and HbA1c were measured at baseline, 3 months, and 6 months. A total of 476,300 data points on daily app engagement were tracked via the backend dashboard and developer's report. The app engagement data were analyzed by quartiles and weekly means expressed in days per week. Linear mixed model analysis was used to determine the associations between the app engagements with percentage weight and HbA1c change. RESULTS: The median overall app engagement rate was maintained above 90% at 6 months. Participants who were actively engaged in ≥5 app features were associated with the greatest overall weight reduction of 10.6% from baseline (mean difference -6, 95% CI -8.9 to -3.2; P<.001) at 6 months. Adhering to the carbohydrate limit of >5.9 days per week and choosing healthier food options for >4.3 days per week had the most impact, eliciting weight loss of 9.1% (mean difference -5.2, 95% CI -8.2 to -2.2; P=.001) and 8.8% (mean difference -4.2, 95% CI -7.1 to -1.3; P=.005), respectively. Among the participants with diabetes, those who had a complete meal log for >5.1 days per week or kept within their carbohydrate limit for >5.9 days per week each achieved greater HbA1c reductions of 1.2% (SD 1.3%; SD 1.5%), as compared with 0.2% (SD 1%; SD 0.6%). in the reference groups who used the features <1.1 or ≤2.5 days per week, respectively. CONCLUSIONS: Higher app engagement led to greater weight loss and HbA1c reduction among adults with overweight or obesity with type 2 diabetes or prediabetes. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR) ACTRN12617001112358; https://anzctr.org.au/Trial/Registration/TrialReview.aspx?ACTRN=12617001112358.

Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT.

Background: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2−7 years of experience) for comparison. Results: DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873−0.911 (p < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858−0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803−0.837) and general radiologist (κ = 0.726, 95% CI 0.706−0.747), both p < 0.001. Conclusion: DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.

Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI.

Background Lumbar spine MRI studies are widely used for back pain assessment. Interpretation involves grading lumbar spinal stenosis, which is repetitive and time consuming. Deep learning (DL) could provide faster and more consistent interpretation. Purpose To assess the speed and interobserver agreement of radiologists for reporting lumbar spinal stenosis with and without DL assistance. Materials and Methods In this retrospective study, a DL model designed to assist radiologists in the interpretation of spinal canal, lateral recess, and neural foraminal stenoses on lumbar spine MRI scans was used. Randomly selected lumbar spine MRI studies obtained in patients with back pain who were 18 years and older over a 3-year period, from September 2015 to September 2018, were included in an internal test data set. Studies with instrumentation and scoliosis were excluded. Eight radiologists, each with 2-13 years of experience in spine MRI interpretation, reviewed studies with and without DL model assistance with a 1-month washout period. Time to diagnosis (in seconds) and interobserver agreement (using Gwet κ) were assessed for stenosis grading for each radiologist with and without the DL model and compared with test data set labels provided by an external musculoskeletal radiologist (with 32 years of experience) as the reference standard. Results Overall, 444 images in 25 patients (mean age, 51 years ± 20 [SD]; 14 women) were evaluated in a test data set. DL-assisted radiologists had a reduced interpretation time per spine MRI study, from a mean of 124-274 seconds (SD, 25-88 seconds) to 47-71 seconds (SD, 24-29 seconds) (P < .001). DL-assisted radiologists had either superior or equivalent interobserver agreement for all stenosis gradings compared with unassisted radiologists. DL-assisted general and in-training radiologists improved their interobserver agreement for four-class neural foraminal stenosis, with κ values of 0.71 and 0.70 (with DL) versus 0.39 and 0.39 (without DL), respectively (both P < .001). Conclusion Radiologists who were assisted by deep learning for interpretation of lumbar spinal stenosis on MRI scans showed a marked reduction in reporting time and superior or equivalent interobserver agreement for all stenosis gradings compared with radiologists who were unassisted by deep learning. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Deep Learning Model for Classifying Metastatic Epidural Spinal Cord Compression on MRI.

Background: Metastatic epidural spinal cord compression (MESCC) is a devastating complication of advanced cancer. A deep learning (DL) model for automated MESCC classification on MRI could aid earlier diagnosis and referral. Purpose: To develop a DL model for automated classification of MESCC on MRI. Materials and Methods: Patients with known MESCC diagnosed on MRI between September 2007 and September 2017 were eligible. MRI studies with instrumentation, suboptimal image quality, and non-thoracic regions were excluded. Axial T2-weighted images were utilized. The internal dataset split was 82% and 18% for training/validation and test sets, respectively. External testing was also performed. Internal training/validation data were labeled using the Bilsky MESCC classification by a musculoskeletal radiologist (10-year experience) and a neuroradiologist (5-year experience). These labels were used to train a DL model utilizing a prototypical convolutional neural network. Internal and external test sets were labeled by the musculoskeletal radiologist as the reference standard. For assessment of DL model performance and interobserver variability, test sets were labeled independently by the neuroradiologist (5-year experience), a spine surgeon (5-year experience), and a radiation oncologist (11-year experience). Inter-rater agreement (Gwet's kappa) and sensitivity/specificity were calculated. Results: Overall, 215 MRI spine studies were analyzed [164 patients, mean age = 62 ± 12(SD)] with 177 (82%) for training/validation and 38 (18%) for internal testing. For internal testing, the DL model and specialists all showed almost perfect agreement (kappas = 0.92-0.98, p < 0.001) for dichotomous Bilsky classification (low versus high grade) compared to the reference standard. Similar performance was seen for external testing on a set of 32 MRI spines with the DL model and specialists all showing almost perfect agreement (kappas = 0.94-0.95, p < 0.001) compared to the reference standard. Conclusion: A DL model showed comparable agreement to a subspecialist radiologist and clinical specialists for the classification of malignant epidural spinal cord compression and could optimize earlier diagnosis and surgical referral.