Evaluation of the Resources and Inequities Among Pediatric Critical Care Facilities in Pakistan.

OBJECTIVES: To evaluate nationwide pediatric critical care facilities and resources in Pakistan. DESIGN: Cross-sectional observational study. SETTING: Accredited pediatric training facilities in Pakistan. PATIENTS: None. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A survey was conducted using the Partners in Health 4S (space, staff, stuff, systems) framework, via email or telephone correspondence. We used a scoring system in which each item in our checklist was given a score of 1, if available. Total scores were added up for each component. Additionally, we stratified and analyzed the data between the public and private healthcare sectors. Out of 114 hospitals (accredited for pediatric training), 76 (67%) responded. Fifty-three (70%) of these hospitals had a PICU, with a total of 667 specialized beds and 217 mechanical ventilators. There were 38 (72%) public hospitals and 15 (28%) private hospitals. There were 20 trained intensivists in 16 of 53 PICUs (30%), while 25 of 53 PICUs (47%) had a nurse-patient ratio less than 1:3. Overall, private hospitals were better resourced in many domains of our four Partners in Health framework. The Stuff component scored more than the other three components using analysis of variance testing ( p = 0.003). On cluster analysis, private hospitals ranked higher in Space and Stuff, along with the overall scoring. CONCLUSIONS: There is a general lack of resources, seen disproportionately in the public sector. The scarcity of qualified intensivists and nursing staff poses a challenge to Pakistan's PICU infrastructure.

Multitask Deep Learning for Cost-Effective Prediction of Patient's Length of Stay and Readmission State Using Multimodal Physical Activity Sensory Data.

In a hospital, accurate and rapid mortality prediction of Length of Stay (LOS) is essential since it is one of the essential measures in treating patients with severe diseases. When predictions of patient mortality and readmission are combined, these models gain a new level of significance. Therefore, the most expensive components of patient care are LOS and readmission rates. Several studies have assessed readmission to the hospital as a single-task issue. The performance, robustness, and stability of the model increase when many correlated tasks are optimized. This study develops multimodal multitasking Long Short-Term Memory (LSTM) Deep Learning (DL) model that can predict both LOS and readmission for patients using multi-sensory data from 47 patients. Continuous sensory data is divided into eight sections, each of which is recorded for an hour. The time steps are constructed using a dual 10-second window-based technique, resulting in six steps per hour. The 30 statistical features are computed by transforming the sensory input into the resulting vector. The proposed multitasking model predicts 30-day readmission as a binary classification problem and LOS as a regression task by constructing discrete time-step data based on the length of physical activity during a hospital stay. The proposed model is compared to a random forest for a single-task problem (classification or regression) because typical machine learning algorithms are unable to handle the multitasking challenge. In addition, sensory data combined with other cost-effective modalities such as demographics, laboratory tests, and comorbidities to construct reliable models for personalized, cost-effective, and medically acceptable prediction. With a high accuracy of 94.84%, the proposed multitask multimodal DL model classifies the patient's readmission status and determines the patient's LOS in hospital with a minimal Mean Square Error (MSE) of 0.025 and Root Mean Square Error (RMSE) of 0.077, which is promising, effective, and trustworthy.

Toxicological risk assessment of some commonly used insecticides on Cotesia flavipes, a larval parasitoid of the spotted stem borer Chilo partellus.

Cotesia flavipes Cameron is an important larval parasitoid exploited for the control of the spotted stem borer, Chilo partellus (Swinhoe). Several studies have evaluated the toxic effects of insecticides on C. partellus, however, little is known about non-target effects of insecticides on this parasitoid, when used to control C. partellus. This laboratory study evaluated the lethal and sublethal effects of twelve insecticides on C. flavipes. Residual toxicity tests showed that organophosphates (chlorpyrifos, triazophos and profenofos) exhibited highest contact toxicity to C. flavipes adults with a LC50 range from 0.63 to 1.05 mg a.i/l, while neonicotinoids (nitenpyram, acetamiprid and imidacloprid) were less toxic to C. flavipes with a LC50 range from 1.27 to 139.48 mg a.i/l. Sugar-insecticide feeding bioassays showed that organophosphates, pyrethroids (cypermethrin, bifenthrin and lambda-cyhalothrin) and carbamates (thiodicarb, carbaryl and methomyl) were highly toxic to C. flavipes adults and caused 100% mortality at 48 h of exposure, while imidacloprid caused 66% mortality at 48 h of exposure. Risk quotient analysis showed that among all tested insecticides, imidacloprid and acetamiprid were less toxic to C. flavipes adults with a risk quotient value of 0.88 and 1.6, respectively. Furthermore, exposure of immature C. flavipes through their host bodies significantly decreased the parasitism rate at their F1 and F2 generations. Risk quotient analysis of insecticides indicated that imidacloprid and acetamiprid were the least toxic to C. flavipes. This study provides important information that will be used in incorporating the most suitable insecticides in integrated pest management programs with reduced negative impacts on non-target beneficial arthropods.

TargetCPP: accurate prediction of cell-penetrating peptides from optimized multi-scale features using gradient boost decision tree.

Cell-penetrating peptides (CPPs) are short length permeable proteins have emerged as drugs delivery tool of therapeutic agents including genetic materials and macromolecules into cells. Recently, CPP has become a hotspot avenue for life science research and paved a new way of disease treatment without harmful impact on cell viability due to nontoxic characteristic. Therefore, the correct identification of CPPs will provide hints for medical applications. Considering the shortcomings of traditional experimental CPPs identification, it is urgently needed to design intelligent predictor for accurate identification of CPPs for the large scale uncharacterized sequences. We develop a novel computational method, called TargetCPP, to discriminate CPPs from Non-CPPs with improved accuracy. In TargetCPP, first the peptide sequences are formulated with four distinct encoding methods i.e., composite protein sequence representation, composition transition and distribution, split amino acid composition, and information theory features. These dominant feature vectors were fused and applied intelligent minimum redundancy and maximum relevancy feature selection method to choose an optimal subset of features. Finally, the predictive model is learned through different classification algorithms on the optimized features. Among these classifiers, gradient boost decision tree algorithm achieved excellent performance throughout the experiments. Notably, the TargetCPP tool attained high prediction Accuracy of 93.54% and 88.28% using jackknife and independent test, respectively. Empirical outcomes prove the superiority and potency of proposed bioinformatics method over state-of-the-art methods. It is highly anticipated that the outcomes of this study will provide a strong background for large scale prediction of CPPs and instructive guidance in clinical therapy and medical applications.

A mobile health monitoring-and-treatment system based on integration of the SSN sensor ontology and the HL7 FHIR standard.

BACKGROUND: Mobile health (MH) technologies including clinical decision support systems (CDSS) provide an efficient method for patient monitoring and treatment. A mobile CDSS is based on real-time sensor data and historical electronic health record (EHR) data. Raw sensor data have no semantics of their own; therefore, a computer system cannot interpret these data automatically. In addition, the interoperability of sensor data and EHR medical data is a challenge. EHR data collected from distributed systems have different structures, semantics, and coding mechanisms. As a result, building a transparent CDSS that can work as a portable plug-and-play component in any existing EHR ecosystem requires a careful design process. Ontology and medical standards support the construction of semantically intelligent CDSSs. METHODS: This paper proposes a comprehensive MH framework with an integrated CDSS capability. This cloud-based system monitors and manages type 1 diabetes mellitus. The efficiency of any CDSS depends mainly on the quality of its knowledge and its semantic interoperability with different data sources. To this end, this paper concentrates on constructing a semantic CDSS based on proposed FASTO ontology. RESULTS: This realistic ontology is able to collect, formalize, integrate, analyze, and manipulate all types of patient data. It provides patients with complete, personalized, and medically intuitive care plans, including insulin regimens, diets, exercises, and education sub-plans. These plans are based on the complete patient profile. In addition, the proposed CDSS provides real-time patient monitoring based on vital signs collected from patients' wireless body area networks. These monitoring include real-time insulin adjustments, mealtime carbohydrate calculations, and exercise recommendations. FASTO integrates the well-known standards of HL7 fast healthcare interoperability resources (FHIR), semantic sensor network (SSN) ontology, basic formal ontology (BFO) 2.0, and clinical practice guidelines. The current version of FASTO includes 9577 classes, 658 object properties, 164 data properties, 460 individuals, and 140 SWRL rules. FASTO is publicly available through the National Center for Biomedical Ontology BioPortal at https://bioportal.bioontology.org/ontologies/FASTO . CONCLUSIONS: The resulting CDSS system can help physicians to monitor more patients efficiently and accurately. In addition, patients in rural areas can depend on the system to manage their diabetes and emergencies.