Ensemble Learning for Disease Prediction: A Review.

Machine learning models are used to create and enhance various disease prediction frameworks. Ensemble learning is a machine learning technique that combines multiple classifiers to improve performance by making more accurate predictions than a single classifier. Although numerous studies have employed ensemble approaches for disease prediction, there is a lack of thorough assessment of commonly used ensemble approaches against highly researched diseases. Consequently, this study aims to identify significant trends in the performance accuracies of ensemble techniques (i.e., bagging, boosting, stacking, and voting) against five hugely researched diseases (i.e., diabetes, skin disease, kidney disease, liver disease, and heart conditions). Using a well-defined search strategy, we first identified 45 articles from the current literature that applied two or more of the four ensemble approaches to any of these five diseases and were published in 2016-2023. Although stacking has been used the fewest number of times (23) compared with bagging (41) and boosting (37), it showed the most accurate performance the most times (19 out of 23). The voting approach is the second-best ensemble approach, as revealed in this review. Stacking always revealed the most accurate performance in the reviewed articles for skin disease and diabetes. Bagging demonstrated the best performance for kidney disease (five out of six times) and boosting for liver and diabetes (four out of six times). The results show that stacking has demonstrated greater accuracy in disease prediction than the other three candidate algorithms. Our study also demonstrates variability in the perceived performance of different ensemble approaches against frequently used disease datasets. The findings of this work will assist researchers in better understanding current trends and hotspots in disease prediction models that employ ensemble learning, as well as in determining a more suitable ensemble model for predictive disease analytics. This article also discusses variability in the perceived performance of different ensemble approaches against frequently used disease datasets.

Food physics insight: the structural design of foods.

Understanding food materials from the classical realm of physics including soft condensed matter physics has been an area of interest especially in the structural design engineering of food products. The contents of this review would help the reader in understanding the thermodynamics of food polymer, structural design principles, structural hierarchy, steps involved in food structuring, newer structural design technologies, and structure measurement techniques. Understanding the concepts of free volume would help the food engineers and technologists to study the food structural changes, manipulate process parameters and, the optimum amount of nutraceuticals/ingredients to be loaded in the food matrix. Such understanding helps in reducing food ingredient wastage while designing a food product.

Test and Treat Model for Tuberculosis Preventive Treatment among Household Contacts of Pulmonary Tuberculosis Patients in Selected Districts of Maharashtra: A Mixed-Methods Study on Care Cascade, Timeliness, and Early Implementation Challenges.

Tuberculosis preventive treatment (TPT) is an important intervention in preventing infection and reducing TB incidence among household contacts (HHCs). A mixed-methods study was conducted to assess the "Test and Treat" model of TPT care cascade among HHCs aged ≥5 years of pulmonary tuberculosis (PTB) patients (bacteriologically/clinically confirmed) being provided TPT care under Project Axshya Plus implemented in Maharashtra (India). A quantitative phase cohort study based on record review and qualitative interviews to understand the challenges and solutions in the TPT care cascade were used. Of the total 4181 index patients, 14,172 HHCs were screened, of whom 36 (0.3%) HHCs were diagnosed with tuberculosis. Among 14,133 eligible HHCs, 10,777 (76.3%) underwent an IGRA test. Of them, 2468 (22.9%) tested positive for IGRA and were suggested for chest X-ray. Of the eligible 2353 HHCs, 2159 (91.7%) were started on TPT, of whom 1958 (90.6%) completed the treatment. The median time between treatment initiation of index PTB patient and (a) HHC screening was 31 days; (b) TPT initiation was 64 days. The challenges in and suggested solutions for improving the TPT care cascade linked to subthemes were tuberculosis infection testing, chest X-ray, human resources, awareness and engagement, accessibility to healthcare facilities, TPT drugs, follow-up, and assessment. A systematic monitoring and time-based evaluation of TPT cascade care delivery followed by prompt corrective actions/interventions could be a crucial strategy for its effective implementation and for the prevention of tuberculosis.

Modification of Kutki millet (Panicum sumatrense) starch properties by the addition of amino acids for the preparation of hydrogels and its characterization.

Starch is a biopolymer containing hydrophilic groups and is used in hydrogels preparation. Amino acids are multifunctional monomers of proteins that can be used as a cross linker to modify the starch by incorporating new functional groups into its chains. In this study, the Kutki millet starch was isolated and modified with lysine (positively charged), aspartic acid (negatively charged), and threonine (neutral) at varying pH levels. These modified starches were characterized for their various functional, structural, pasting, and textural properties. Hydrogels prepared from Lys9-KMS, Thr9-KMS, and AA11-KMS, possessing less adhesiveness, strong integrity, and hardness were then characterized for their XRD and morphological characterization. The principal component analysis (PCA) biplot showed that the samples modified at higher pH levels are positively correlated with the textural properties, swelling power and amylose content (I and IV quadrants), than those modified at lower pH. It may be inferred that starch modified with amino acid at higher pH have good textural properties than those at lower pH. Results of the overall investigation indicated that among these three amino acids, lysine could be a better cross linker for modification of Kutki millet starch and preparation of their gels for the delivery of nutraceuticals.

Millet starch: A review.

The demand for millets and their products is becoming popular globally due to their various health-promoting properties. The major constituent of the millet is its starch which contributes about 70% of total millet grain and decides the quality of millet-based food products. The application of starch for various purposes is dependent upon its physicochemical, structural, and functional properties. A native starch does not possess all the required properties for a specific use. However, product-specific properties can be achieved by modifying the structure of starches. Information deficit on millet starch has undermined its potential use in new food product design. The objective of this review is to examine the chemical composition, characterization, structural chemistry, digestibility, hydrolysis, and modification techniques of the millet starches. The review paper also discusses the various applications of native and modified starches in the food industry.