-
1.
Medios- An offline, smartphone-based artificial intelligence algorithm for the diagnosis of diabetic retinopathy.
Sosale, B, Sosale, AR, Murthy, H, Sengupta, S, Naveenam, M
Indian journal of ophthalmology. 2020;(2):391-395
-
-
Free full text
-
Abstract
PURPOSE An observational study to assess the sensitivity and specificity of the Medios smartphone-based offline deep learning artificial intelligence (AI) software to detect diabetic retinopathy (DR) compared with the image diagnosis of ophthalmologists. METHODS Patients attending the outpatient services of a tertiary center for diabetes care underwent 3-field dilated retinal imaging using the Remidio NM FOP 10. Two fellowship-trained vitreoretinal specialists separately graded anonymized images and a patient-level diagnosis was reached based on grading of the worse eye. The images were subjected to offline grading using the Medios integrated AI-based software on the same smartphone used to acquire images. The sensitivity and specificity of the AI in detecting referable DR (moderate non-proliferative DR (NPDR) or worse disease) was compared to the gold standard diagnosis of the retina specialists. RESULTS Results include analysis of images from 297 patients of which 176 (59.2%) had no DR, 35 (11.7%) had mild NPDR, 41 (13.8%) had moderate NPDR, and 33 (11.1%) had severe NPDR. In addition, 12 (4%) patients had PDR and 36 (20.4%) had macular edema. Sensitivity and specificity of the AI in detecting referable DR was 98.84% (95% confidence interval [CI], 97.62-100%) and 86.73% (95% CI, 82.87-90.59%), respectively. The area under the curve was 0.92. The sensitivity for vision-threatening DR (VTDR) was 100%. CONCLUSION The AI-based software had high sensitivity and specificity in detecting referable DR. Integration with the smartphone-based fundus camera with offline image grading has the potential for widespread applications in resource-poor settings.
-
2.
Diagnosis of Diabetes Mellitus in Older Adults.
Reddy, SSK
Clinics in geriatric medicine. 2020;(3):379-384
Abstract
In the United States, 4 out of 10 adults with diabetes are ≥65 years of age. The older adult with diabetes is very likely to be asymptomatic and also at higher risk of vascular disease. New concerns include new diagnosis of diabetes for older adults admitted to hospital and older adults in long-term care facilities. The pathophysiology for increased incidence of diabetes in older adults is multifactorial, but dominant features are increased likelihood of metabolic syndrome, dysfunctional insulin secretion, and peripheral insulin resistance. Society in general benefits from more cost-effective care of older adults with diabetes.
-
3.
Early Detection of Mild Cognitive Impairment (MCI) in an At-Home Setting.
Sabbagh, MN, Boada, M, Borson, S, Doraiswamy, PM, Dubois, B, Ingram, J, Iwata, A, Porsteinsson, AP, Possin, KL, Rabinovici, GD, et al
The journal of prevention of Alzheimer's disease. 2020;(3):171-178
Abstract
Emerging digital tools have the potential to enable a new generation of qualitative and quantitative assessment of cognitive performance. Moreover, the ubiquity of consumer electronics, such as smartphones and tablets, can be harnessed to support large-scale self-assessed cognitive screening with benefit to healthcare systems and consumers. A wide variety of apps, wearables, and new digital technologies are either available or in development for the detection of mild cognitive impairment (MCI), a risk factor for dementia. Two categories of novel methodologies may be considered: passive technologies (which monitor a user's behavior without active user input) and interactive assessments (which require active user input). Such examinations can be self-administered, supervised by a caregiver, or conducted by an informant at home or outside of a clinical setting. These direct-to-consumer tools have the potential to sidestep barriers associated with cognitive evaluation in primary care, thus improving access to cognitive assessments. Although direct-to-consumer cognitive assessment is associated with its own barriers, including test validation, user experience, and technological concerns, it is conceivable that these issues can be addressed so that a large-scale, self-assessed cognitive evaluation that would represent an initial cognitive screen may be feasible in the future.
-
4.
Risk-based breast cancer screening strategies in women.
Harkness, EF, Astley, SM, Evans, DG
Best practice & research. Clinical obstetrics & gynaecology. 2020;:3-17
Abstract
The incidence of breast cancer continues to increase worldwide. Population-based screening is available in many countries but may not be the most efficient use of resources, thus interest in risk-based/stratified screening has grown significantly in recent years. An important part of risk-based screening is the incorporation of mammographic density (MD) and single nucleotide polymorphisms (SNPs) into risk prediction models to be combined with classical risk factors. In this article, we discuss different measures of MD and risk prediction models that are available. Risk-stratified screening options including supplemental or alternative screening modalities including digital breast tomosynthesis (DBT), automated ultrasound (ABUS) and magnetic resonance imaging (MRI) are discussed, as well as potential risk-based interventions (diet and lifestyle, chemoprevention and risk-reducing surgery). Furthermore, we look at risk feedback in practice and the cost-effectiveness and acceptability of risk-based screening, highlighting some of the current challenges.
-
5.
Nonmydriatic widefield retinal imaging with an automatic white LED confocal imaging system compared with dilated ophthalmoscopy in screening for diabetic retinopathy.
Borrelli, E, Querques, L, Lattanzio, R, Cavalleri, M, Grazioli Moretti, A, Di Biase, C, Signorino, A, Gelormini, F, Sacconi, R, Bandello, F, et al
Acta diabetologica. 2020;(9):1043-1047
Abstract
PURPOSE To compare nonmydriatic montage widefield images with dilated fundus ophthalmoscopy for determining diabetic retinopathy (DR) severity. MATERIALS AND METHODS In this prospective, observational, cross-sectional study, patients with a previous diagnosis of diabetes and without history of diabetes-associated ocular disease were screened for DR. Montage widefield imaging was obtained with a system that combines confocal technology with white-light emitting diode (LED) illumination (DRSplus, Centervue, Padua, Italy). Dilated fundus examination was performed by a retina specialist. RESULTS Thirty-seven eyes (20 patients, 8 females) were finally included in the analysis. Mean age of the patients enrolled was 58.0 ± 11.6 years [range 31-80 years]. The level of DR identified on montage widefield images agreed exactly with indirect ophthalmoscopy in 97.3% (36) of eyes and was within 1 step in 100% (37) of eyes. Cohen's kappa coefficient (κ) was 0.96, this suggesting an almost perfect agreement between the two modalities in DR screening. Nonmydriatic montage widefield imaging acquisition time was significantly shorter than that of dilated clinical examination (p = 0.010). CONCLUSION Nonmydriatic montage widefield images were compared favorably with dilated fundus examination in defining DR severity; however, they are acquired more rapidly.
-
6.
Artificial Intelligence in the assessment of diabetic retinopathy from fundus photographs.
Gilbert, MJ, Sun, JK
Seminars in ophthalmology. 2020;(7-8):325-332
Abstract
Background: Over the next 25 years, the global prevalence of diabetes is expected to grow to affect 700 million individuals. Consequently, an unprecedented number of patients will be at risk for vision loss from diabetic eye disease. This demand will almost certainly exceed the supply of eye care professionals to individually evaluate each patient on an annual basis, signaling the need for 21st century tools to assist our profession in meeting this challenge. Methods: Review of available literature on artificial intelligence (AI) as applied to diabetic retinopathy (DR) detection and predictionResults: The field of AI has seen exponential growth in evaluating fundus photographs for DR. AI systems employ machine learning and artificial neural networks to teach themselves how to grade DR from libraries of tens of thousands of images and may be able to predict future DR progression based on baseline fundus photographs. Conclusions: AI algorithms are highly promising for the purposes of DR detection and will likely be able to reliably predict DR worsening in the future. A deeper understanding of these systems and how they interpret images is critical as they transition from the bench into the clinic.
-
7.
Cascade screening and genetic diagnosis of familial hypercholesterolemia in clusters of the Southeastern region from Brazil.
de Paiva Silvino, JP, Jannes, CE, Tada, MT, Lima, IR, Silva, IFO, Pereira, AC, Gomes, KB
Molecular biology reports. 2020;(12):9279-9288
Abstract
Familial hypercholesterolemia (FH) is an autosomal dominant genetic disease characterized by high levels of low-density lipoprotein-cholesterol (LDLc), associated to premature cardiovascular disease. The detection of the variants related to FH is important to improve the early diagnosis in probands / index-cases (ICs) and their relatives. We included ICs with FH and their relatives, living in a small region of Minas Gerais state-Brazil, which were classified according to Dutch Lipid Clinic Network Criteria (DLCNC) and submitted to sequencing of genes related to FH (LDLR, APOB, PCSK9, LDLRAP1, LIPA, STAP1, APOE, ABCG5 e ABCG8). In a total of 143 subjects (32 ICs and 111 relatives), eight variants were identified in 91 individuals. From these variants, five were in LDLR [p.(Asp224Asn), p.(Ser854Gly), p.(Cys34Arg), p.(Asp601His), deletion of exon15 in LDLR)], one in APOB [p.(Met499Val)], one in PCSK9 [p.(Arg237Trp)] and one in APOE [p.(Pro28Leu)] genes. The variants were detected in 100% of those subjects classified as definitive, 87% as probable and 69% as possible FH cases based on DLCNC. The LDLc level was higher in individuals with corneal arch and xanthomas or xanthelasmas, as well as in pathogenic or probably pathogenic variants carriers. This study showed higher frequency of LDLR gene variants compared to other genes related to LDL metabolism in individuals with FH in Minas Gerais - Brazil and the presence of FH in relatives without previous diagnosis. Our data reinforce the importance of molecular and clinical evaluation of FH relatives in order to early diagnosis the FH, as well as cardiovascular diseases prevention.
-
8.
A position statement on screening and management of prediabetes in adults in primary care in Australia.
Bell, K, Shaw, JE, Maple-Brown, L, Ferris, W, Gray, S, Murfet, G, Flavel, R, Maynard, B, Ryrie, H, Pritchard, B, et al
Diabetes research and clinical practice. 2020;:108188
Abstract
Prediabetes has a high prevalence, with early detection essential to facilitate optimal management to prevent the development of conditions such as type 2 diabetes and cardiovascular disease. Prediabetes can include impaired fasting glucose, impaired glucose tolerance and elevated HbA1c. This position statement outlines the approaches to screening and management of prediabetes in primary care. There is good evidence to implement intensive, structured lifestyle interventions for individuals with impaired glucose tolerance. The evidence for those with impaired fasting glucose or elevated HbA1c is less clear, but individuals should still be provided with generalised healthy lifestyle strategies. A multidisciplinary approach is recommended to implement healthy lifestyle changes through education, nutrition and physical activity. Individuals should aim to lose weight (5-10% of body mass) using realistic and sustainable dietary approaches supported by an accredited practising dietitian, where possible. Physical activity and exercise should be used to facilitate weight maintenance and reduce blood glucose. Moderate-vigorous intensity aerobic exercise and resistance training should be prescribed by an accredited exercise physiologist, where possible. When indicated, pharmacotherapy, metabolic surgery and psychosocial care should be considered, in order to enhance the outcomes associated with lifestyle change. Individuals with prediabetes should generally be evaluated annually for their diabetes status.
-
9.
Comparative Effectiveness of Two Interventions to Increase Colorectal Cancer Screening for Those at Increased Risk Based on Family History: Results of a Randomized Trial.
Paskett, ED, Bernardo, BM, Young, GS, Katz, ML, Reiter, PL, Tatum, CM, Oliveri, JM, DeGraffinreid, CR, Gray, DM, Pearlman, R, et al
Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology. 2020;(1):3-9
-
-
Free full text
-
Abstract
BACKGROUND First-degree relatives (FDR) of patients with colorectal cancer are at risk for colorectal cancer, but may not be up to date with colorectal cancer screening. We sought to determine whether a one-time recommendation about needing colorectal cancer screening using patient navigation (PN) was better than just receiving the recommendation only. METHODS Participants were FDRs of patients with Lynch syndrome-negative colorectal cancer from participating Ohio hospitals. FDRs from 259 families were randomized to a website intervention (528 individuals), which included a survey and personal colorectal cancer screening recommendation, while those from 254 families were randomized to the website plus telephonic PN intervention (515 individuals). Primary outcome was adherence to the personal screening recommendation (to get screened or not to get screened) received from the website. Secondary outcomes examined who benefited from adding PN. RESULTS At the end of the 14-month follow-up, 78.6% of participants were adherent to their recommendation for colorectal cancer screening with adherence similar between arms (P = 0.14). Among those who received a recommendation to have a colonoscopy immediately, the website plus PN intervention significantly increased the odds of receiving screening, compared with the website intervention (OR: 2.98; 95% confidence interval, 1.68-5.28). CONCLUSIONS Addition of PN to a website intervention did not improve adherence to a colorectal cancer screening recommendation overall; however, the addition of PN was more effective in increasing adherence among FDRs who needed screening immediately. IMPACT These findings provide important information as to when the additional costs of PN are needed to assure colorectal cancer screening among those at high risk for colorectal cancer.
-
10.
The Symptom-Checklist-K-9 (SCL-K-9) Discriminates between Overweight/Obese Patients with and without Significant Binge Eating Pathology: Psychometric Properties of an Italian Version.
Imperatori, C, Bianciardi, E, Niolu, C, Fabbricatore, M, Gentileschi, P, Di Lorenzo, G, Siracusano, A, Innamorati, M
Nutrients. 2020;(3)
Abstract
A general personality and psychopathology evaluation is considered to be crucial part of the multidisciplinary assessment for weight-related problems. The Symptom Checklist-90-Revised (SCL-90-R) is commonly used to assess general psychopathology in both overweight and obese patients seeking weight-loss treatment. The main purpose of the present research was to investigate the psychometric properties of the brief form of the SCL-90-R (i.e., the SCL-K-9) in a clinical sample (N = 397) of patients seeking weight-loss treatment (i.e., bariatric surgery and a nutritional weight-loss program). The results of the confirmatory factor analysis supported a one-factor solution of the SCL-K-9, with all nine items loading significantly on the common latent factor (lambdas ≥ 0.587). The ordinal α (= 0.91), the inter-item mean indices of correlation (rii = 0.53), and the convergent validity were also satisfactory. A receiver operating characteristic curves procedure showed that both SCL-90-R and SCL-K-9 were able to classify patients with and without significant binge eating pathology according to the Binge Eating Scale (BES) total score. Overall, our results suggest that the SCL-K-9 has adequate psychometric properties and can be applied as a short screening tool to assess general psychopathology in overweight/obese individuals seeking weight-loss treatment and at follow-up interviews when time restraints preclude the use of the full-length form.