Multivariable Analysis of Nutritional and Socio-Economic Profiles Shows Differences in Incident Anemia for Northern and Southern Jiangsu in China

Medication profiling in women with type 1 diabetes highlights the importance of adequate, guideline-based treatment in low-risk groups

Effective treatment may prevent kidney complications, but women might be underprescribed. Novel, data-driven insights into prescriptions and their relationship with kidney health in women with type 1 diabetes may help to optimize treatment. We identified six medication profiles in 1164 women from the FinnDiane Study with normal albumin excretion rate based on clusters of their baseline prescription data using a self-organizing map. Future rapid kidney function decline was defined as an annual estimated glomerular filtration rate (eGFR) loss > 3 ml/min/1.73 m2 after baseline. Two profiles were associated with future decline: Profile ARB with the highest proportion of angiotensin receptor blockers (odds ratio [OR] 2.75, P = 0.02) and highly medicated women in profile HighMed (OR 2.55, P = 0.03). Compared with profile LowMed (low purchases of all), profile HighMed had worse clinical characteristics, whereas in profile ARB only systolic blood pressure was elevated. Importantly, the younger women in profile ARB with fewer kidney protective treatments developed a rapid decline despite otherwise similar baseline characteristics to profile ACE & Lipids (the highest proportions of ACE inhibitors and lipid-modifying agents) without a future rapid decline. In conclusion, medication profiles identified different future eGFR trajectories in women with type 1 diabetes revealing potential treatment gaps for younger women.

Anemia and frailty in the aging population: implications of dietary fiber intake (findings of the US NHANES from 2007-2018)

BACKGROUND

Frailty has long been seen as an indicator of reduced physical functions in the elderly, which may be caused by a variety of chronic illnesses or cancerous tumors. Dietary fiber was connected with anemia and frailty, whereas it was uncertain if dietary fiber consumption modifies the impact of anemia on frailty in elderly adults.

METHODS

We performed a secondary analysis using older adults aged 60 years and over from the National Health and Nutrition Examination Survey (NHANES) 2007-2018 cycles. Dietary fiber intake was estimated using two 24-h dietary recalls. Participants were dichotomized as frail or non-frail based on a modified Fried physical frailty phenotype from previous NHANES studies. The weighted logistic regression was used to estimate the odds ratio (OR) and confidence interval (CI) for the associations between hemoglobin levels and frailty at high- and low-dietary fiber intake levels.

RESULTS

A total of 9644 older adults were included in this study, and the weighted sample was 56,403,031, of whom 3,569,186 (6.3%) were deemed to be frail, and the remainder were deemed to be non-frail. Among the low dietary fiber intake group, higher hemoglobin was significantly associated with a lower risk of frailty (OR = 0.79, 95% CI: 0.71-0.87), and anemia was associated with an almost threefold elevated risk of frailty (OR = 3.24, 95% CI:1.98-5.29) in the fully adjusted model. However, this phenomenon was not observed in groups with high dietary fiber intake. In addition, L-shaped dose response relationship was found in the high dietary fiber intake group (P overall association < 0.001; P non-linear association = 0.076). Whereas the dose response relationship was not significant in the high dietary fiber intake group (P overall association 0.752; P non-linear association = 0.734).

CONCLUSIONS

Frailty was positively associated with the severity of anemia in older adults with low, but not high, dietary fiber intake. Adequate fiber intake may be an innovative dietary strategy to reduce frailty in older adults.

A scoping review of the clinical application of machine learning in data-driven population segmentation analysis

OBJECTIVE

Data-driven population segmentation is commonly used in clinical settings to separate the heterogeneous population into multiple relatively homogenous groups with similar healthcare features. In recent years, machine learning (ML) based segmentation algorithms have garnered interest for their potential to speed up and improve algorithm development across many phenotypes and healthcare situations. This study evaluates ML-based segmentation with respect to (1) the populations applied, (2) the segmentation details, and (3) the outcome evaluations.

MATERIALS AND METHODS

MEDLINE, Embase, Web of Science, and Scopus were used following the PRISMA-ScR criteria. Peer-reviewed studies in the English language that used data-driven population segmentation analysis on structured data from January 2000 to October 2022 were included.

RESULTS

We identified 6077 articles and included 79 for the final analysis. Data-driven population segmentation analysis was employed in various clinical settings. K-means clustering is the most prevalent unsupervised ML paradigm. The most common settings were healthcare institutions. The most common targeted population was the general population.

DISCUSSION

Although all the studies did internal validation, only 11 papers (13.9%) did external validation, and 23 papers (29.1%) conducted methods comparison. The existing papers discussed little validating the robustness of ML modeling.

CONCLUSION

Existing ML applications on population segmentation need more evaluations regarding giving tailored, efficient integrated healthcare solutions compared to traditional segmentation analysis. Future ML applications in the field should emphasize methods' comparisons and external validation and investigate approaches to evaluate individual consistency using different methods.

Prevalence, treatment status, and predictors of anemia and erythropoietin hyporesponsiveness in Japanese patients with non-dialysis-dependent chronic kidney disease: a cross-sectional study

BACKGROUND

Hyporesponsiveness to erythropoiesis-stimulating agents (ESAs) has been highlighted as a potential risk factor for cardiovascular disease in patients with chronic kidney disease (CKD).

METHODS

We assessed cross-sectionally the prevalence, associated factors, and treatment status of anemia and ESA hyporesponsiveness in 4460 non-dialysis-dependent CKD patients enrolled in a multicenter cohort in Japan. Anemia was defined as a hemoglobin (Hb) level of less than 11 g/dL or receiving ESA therapy. ESA hyporesponsiveness was defined by the erythropoietin-resistance index (ERI), which was the erythropoietin dose per week divided by body weight and Hb level (U/kg/week/g/dl).

RESULTS

Of the 4460 patients, 1050 (23.5%) had anemia. ESAs were administered to 626 patients, reaching a percentage of 57.5% of patients with stage G5 CKD. However, the ESA treatment rate was only 49.0% in patients with a hemoglobin level of < 11 g/dL. The proportion of patients receiving iron supplementation was lower than that of patients receiving ESAs regardless of CKD stage or hemoglobin level, and a significant proportion of patients did not receive iron supplementation, even those with iron deficiency. The ERI increased with CKD stage progression, and the multiple regression analysis showed that age, female sex, body mass index, cholesterol, glomerular filtration rate, and intact parathyroid hormone level were independent contributors.

CONCLUSIONS

Our findings demonstrate that many Japanese patients with non-dialysis-dependent CKD receiving ESAs fail to maintain adequate hemoglobin levels. These results suggest the need for interventions for ESA hyporesponsiveness factors in addition to iron supplementation.

Applicability of machine learning techniques in food intake assessment: A systematic review

The evaluation of food intake is important in scientific research and clinical practice to understand the relationship between diet and health conditions of an individual or a population. Large volumes of data are generated daily in the health sector. In this sense, Artificial Intelligence (AI) tools have been increasingly used, for example, the application of Machine Learning (ML) algorithms to extract useful information, find patterns, and predict diseases. This systematic review aimed to identify studies that used ML algorithms to assess food intake in different populations. A literature search was conducted using five electronic databases, and 36 studies met all criteria and were included. According to the results, there has been a growing interest in the use of ML algorithms in the area of nutrition in recent years. Also, supervised learning algorithms were the most used, and the most widely used method of nutritional assessment was the food frequency questionnaire. We observed a trend in using the data analysis programs, such as R and WEKA. The use of ML in nutrition is recent and challenging. Therefore, it is encouraged that more studies are carried out relating these themes for the development of food reeducation programs and public policies.

Prevalence of anemia in predialysis chronic kidney disease: Is the study center a significant factor?

OBJECTIVES

Anemia is highly prevalent in chronic kidney disease patients; however, its identification and management have been reported to be suboptimal. In this study we aimed to describe the prevalence, severity, risk factors, and treatment of anemia in different nephrology centers, among chronic kidney disease patients who were not given renal replacement therapy.

MATERIALS AND METHODS

We performed a multicenter cross-sectional study in three different nephrology clinics. Adult (>18 years of age) chronic kidney disease patients with an estimated glomerular filtration rate (eGFR) below 60 ml/min, and who were not started dialysis were recruited. Demographic, clinical and laboratory data regarding anemia and its management were collected using a standard data form. Anemia was defined as a hemoglobin level below 12g/dL and severe anemia as a hemoglobin level below 10g/dl.

RESULTS

A total of 1066 patients were enrolled in the study. Anemia and severe anemia were present in 55.9% and 14.9% of the patients, respectively. The mean hemoglobin level for the whole cohort was 11.8±1.8 g/dL. Univariate analyses revealed that the mean hemoglobin level was significantly different among the centers. Moreover, the frequency of the presence of anemia stratified by severity was also significantly different among the centers. According to binary logistic regression analysis, gender, levels of eGFR and iron, ferritin ≥ 100 ng/mL, and the nephrology center were independent determinants of severe anemia.

CONCLUSIONS

We found a high prevalence of anemia among chronic kidney disease patients who were not on renal replacement therapy. Each center should determine the treatment strategy according to the patient's characteristics. According to our results, the center-specific management of anemia seems to be important.