Clinical outcome prediction normally employs static, one-size-fits-all models that perform well for the average patient but are sub-optimal for individual patients with unique characteristics. In the ...era of digital healthcare, it is feasible to dynamically personalize decision support by identifying and analyzing similar past patients, in a way that is analogous to personalized product recommendation in e-commerce. Our objectives were: 1) to prove that analyzing only similar patients leads to better outcome prediction performance than analyzing all available patients, and 2) to characterize the trade-off between training data size and the degree of similarity between the training data and the index patient for whom prediction is to be made.
We deployed a cosine-similarity-based patient similarity metric (PSM) to an intensive care unit (ICU) database to identify patients that are most similar to each patient and subsequently to custom-build 30-day mortality prediction models. Rich clinical and administrative data from the first day in the ICU from 17,152 adult ICU admissions were analyzed. The results confirmed that using data from only a small subset of most similar patients for training improves predictive performance in comparison with using data from all available patients. The results also showed that when too few similar patients are used for training, predictive performance degrades due to the effects of small sample sizes. Our PSM-based approach outperformed well-known ICU severity of illness scores. Although the improved prediction performance is achieved at the cost of increased computational burden, Big Data technologies can help realize personalized data-driven decision support at the point of care.
The present study provides crucial empirical evidence for the promising potential of personalized data-driven decision support systems. With the increasing adoption of electronic medical record (EMR) systems, our novel medical data analytics contributes to meaningful use of EMR data.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The data missing from patient profiles in intensive care units (ICUs) are substantial and unavoidable. However, this incompleteness is not always random or because of imperfections in the data ...collection process.
This study aimed to investigate the potential hidden information in data missing from electronic health records (EHRs) in an ICU and examine whether the presence or missingness of a variable itself can convey information about the patient health status.
Daily retrieval of laboratory test (LT) measurements from the Medical Information Mart for Intensive Care III database was set as our reference for defining complete patient profiles. Missingness indicators were introduced as a way of representing presence or absence of the LTs in a patient profile. Thereafter, various feature selection methods (filter and embedded feature selection methods) were used to examine the predictive power of missingness indicators. Finally, a set of well-known prediction models (logistic regression LR, decision tree, and random forest) were used to evaluate whether the absence status itself of a variable recording can provide predictive power. We also examined the utility of missingness indicators in improving predictive performance when used with observed laboratory measurements as model input. The outcome of interest was in-hospital mortality and mortality at 30 days after ICU discharge.
Regardless of mortality type or ICU day, more than 40% of the predictors selected by feature selection methods were missingness indicators. Notably, employing missingness indicators as the only predictors achieved reasonable mortality prediction on all days and for all mortality types (for instance, in 30-day mortality prediction with LR, we achieved area under the curve of the receiver operating characteristic AUROC of 0.6836±0.012). Including indicators with observed measurements in the prediction models also improved the AUROC; the maximum improvement was 0.0426. Indicators also improved the AUROC for Simplified Acute Physiology Score II model-a well-known ICU severity of illness score-confirming the additive information of the indicators (AUROC of 0.8045±0.0109 for 30-day mortality prediction for LR).
Our study demonstrated that the presence or absence of LT measurements is informative and can be considered a potential predictor of in-hospital and 30-day mortality. The comparative analysis of prediction models also showed statistically significant prediction improvement when indicators were included. Moreover, missing data might reflect the opinions of examining clinicians. Therefore, the absence of measurements can be informative in ICUs and has predictive power beyond the measured data themselves. This initial case study shows promise for more in-depth analysis of missing data and its informativeness in ICUs. Future studies are needed to generalize these results.
APACHE IVa provides typically useful and accurate predictions on in-hospital mortality and length of stay for patients in critical care. However, there are factors which may preclude APACHE IVa from ...reaching its ceiling of predictive accuracy. Our primary aim was to determine which variables available within the first 24 h of a patient's ICU stay may be indicative of the APACHE IVa scoring system making occasional but potentially illuminating errors in predicting in-hospital mortality. We utilized the publicly available multi-institutional ICU database, eICU, available since 2018, to identify a large observational cohort for our investigation. APACHE IVa scores are provided by eICU for each patient's ICU stay. We used Lasso logistic regression in an aim to build parsimonious final models, using cross-validation to select the penalization parameter, separately for each of our two responses, i.e., errors, of interest, which are APACHE falsely predicting in-hospital death (Type I error), and APACHE falsely predicting in-hospital survival (Type II error). We then assessed the performance of the models with a random holdout validation sample. While the extremeness of the APACHE prediction led to dependable predictions for preventing either type of error, distinct variables were identified as being strongly associated with the two different types of errors occurring. These included a primary set of predictors consisting of mean SpO2 and worst lactate for predicting Type I errors, and worst albumin and mean heart rate for Type II. In addition, a secondary set of predictors including changes recorded in care limitations for the patient's treatment plan, worst pH, whether cardiac arrest occurred at admission, and whether vasopressor was provided for predicting Type I error; age, whether the patient was ventilated in day 1, mean respiratory rate, worst lactate, worst blood urea nitrogen test, and mean aperiodic vitals for Type II. The two models also differed in their performance metrics in their holdout validation samples, in large part due to the lower prevalence of Type II errors compared to Type I. The eICU database was a good resource for evaluating our objective, and important recommendations are provided, particularly identifying key variables that could lead to APACHE prediction errors when APACHE scores are sufficiently low to predict in-hospital survival.
Nursing notes have not been widely used in prediction models for clinical outcomes, despite containing rich information. Advances in natural language processing have made it possible to extract ...information from large scale unstructured data like nursing notes. This study extracted the sentiment-impressions and attitudes-of nurses, and examined how sentiment relates to 30-day mortality and survival.
This study applied a sentiment analysis algorithm to nursing notes extracted from MIMIC-III, a public intensive care unit (ICU) database. A multiple logistic regression model was fitted to the data to correlate measured sentiment with 30-day mortality while controlling for gender, type of ICU, and SAPS-II score. The association between measured sentiment and 30-day mortality was further examined in assessing the predictive performance of sentiment score as a feature in a classifier, and in a survival analysis for different levels of measured sentiment.
Nursing notes from 27,477 ICU patients, with an overall 30-day mortality of 11.02%, were extracted. In the presence of known predictors of 30-day mortality, mean sentiment polarity was a highly significant predictor in a multiple logistic regression model (Adjusted OR = 0.4626, p < 0.001, 95% CI: 0.4244, 0.5041) and led to improved predictive accuracy (AUROC = 0.8189 versus 0.8092, 95% BCI of difference: 0.0070, 0.0126). The Kaplan Meier survival curves showed that mean sentiment polarity quartiles are positively correlated with patient survival (log-rank test: p < 0.001).
This study showed that quantitative measures of unstructured clinical notes, such as sentiment of clinicians, correlate with 30-day mortality and survival, thus can also serve as a predictor of patient outcomes in the ICU. Therefore, further research is warranted to study and make use of the wealth of data that clinical notes have to offer.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Few researchers have the data required to adequately understand how the school environment impacts youth health behaviour development over time.
COMPASS is a prospective cohort study designed to ...annually collect hierarchical longitudinal data from a sample of 90 secondary schools and the 50,000+ grade 9 to 12 students attending those schools. COMPASS uses a rigorous quasi-experimental design to evaluate how changes in school programs, policies, and/or built environment (BE) characteristics are related to changes in multiple youth health behaviours and outcomes over time. These data will allow for the quasi-experimental evaluation of natural experiments that will occur within schools over the course of COMPASS, providing a means for generating "practice based evidence" in school-based prevention programming.
COMPASS is the first study with the infrastructure to robustly evaluate the impact that changes in multiple school-level programs, policies, and BE characteristics within or surrounding a school might have on multiple youth health behaviours or outcomes over time. COMPASS will provide valuable new insight for planning, tailoring and targeting of school-based prevention initiatives where they are most likely to have impact.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Physicians and health policy makers are required to make predictions during their decision making in various medical problems. Many advances have been made in predictive modeling toward outcome ...prediction, but these innovations target an average patient and are insufficiently adjustable for individual patients. One developing idea in this field is individualized predictive analytics based on patient similarity. The goal of this approach is to identify patients who are similar to an index patient and derive insights from the records of similar patients to provide personalized predictions..
The aim is to summarize and review published studies describing computer-based approaches for predicting patients' future health status based on health data and patient similarity, identify gaps, and provide a starting point for related future research.
The method involved (1) conducting the review by performing automated searches in Scopus, PubMed, and ISI Web of Science, selecting relevant studies by first screening titles and abstracts then analyzing full-texts, and (2) documenting by extracting publication details and information on context, predictors, missing data, modeling algorithm, outcome, and evaluation methods into a matrix table, synthesizing data, and reporting results.
After duplicate removal, 1339 articles were screened in abstracts and titles and 67 were selected for full-text review. In total, 22 articles met the inclusion criteria. Within included articles, hospitals were the main source of data (n=10). Cardiovascular disease (n=7) and diabetes (n=4) were the dominant patient diseases. Most studies (n=18) used neighborhood-based approaches in devising prediction models. Two studies showed that patient similarity-based modeling outperformed population-based predictive methods.
Interest in patient similarity-based predictive modeling for diagnosis and prognosis has been growing. In addition to raw/coded health data, wavelet transform and term frequency-inverse document frequency methods were employed to extract predictors. Selecting predictors with potential to highlight special cases and defining new patient similarity metrics were among the gaps identified in the existing literature that provide starting points for future work. Patient status prediction models based on patient similarity and health data offer exciting potential for personalizing and ultimately improving health care, leading to better patient outcomes.
Sepsis is one of the deadliest diseases in North America and in spite of the vast amount of research on this topic there is still uncertainty in the outcome of sepsis treatments. This study aimed at ...investigating the informativeness of temporal electronic health records (EHR) in stratifying septic patients and identifying subpopulations of septic patients with similar trajectories and clinical needs. We performed hierarchical clustering and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) analyses using data from septic patients in the MIMIC III intensive care unit database. The t-Distributed Stochastic Neighbor Embedding (t-SNE) method was utilized to map patients to a two-dimensional space. We utilized silhouette index and cluster-wise stability assessment by resampling to investigate the validity of the clusters. The hierarchical clustering with Euclidean metric identified twelve clinically recognizable subgroups that demonstrated different characteristics in spite of sharing common conditions. Our results demonstrated that data-driven approaches can help in customizing care platforms for septic patients by identifying similar clinically relevant groups.
•Temporal vital signs data are informative in stratifying septic patients.•Cluster analysis can be used to identify subpopulations in Sepsis-3 population.•Identifying subpopulations of septic patients may inform customizing care.
Breast cancer, alcohol, and phosphate toxicity Brown, Ronald B.; Bigelow, Philip; Dubin, Joel A. ...
Journal of applied toxicology,
January 2024, 2024-01-00, 20240101, Letnik:
44, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Alcohol consumption is associated with an increased risk of breast cancer, even at low alcohol intake levels, but public awareness of the breast cancer risk associated with alcohol intake is low. ...Furthermore, the causative mechanisms underlying alcohol's association with breast cancer are unknown. The present theoretical paper uses a modified grounded theory method to review the research literature and propose that alcohol's association with breast cancer is mediated by phosphate toxicity, the accumulation of excess inorganic phosphate in body tissue. Serum levels of inorganic phosphate are regulated through a network of hormones released from the bone, kidneys, parathyroid glands, and intestines. Alcohol burdens renal function, which may disturb the regulation of inorganic phosphate, impair phosphate excretion, and increase phosphate toxicity. In addition to causing cellular dehydration, alcohol is an etiologic factor in nontraumatic rhabdomyolysis, which ruptures cell membranes and releases inorganic phosphate into the serum, leading to hyperphosphatemia. Phosphate toxicity is also associated with tumorigenesis, as high levels of inorganic phosphate within the tumor microenvironment activate cell signaling pathways and promote cancer cell growth. Furthermore, phosphate toxicity potentially links cancer and kidney disease in onco‐nephrology. Insights into the mediating role of phosphate toxicity may lead to future research and interventions that raise public health awareness of breast cancer risk and alcohol consumption.
Public awareness of breast cancer associated with alcohol intake is low, and causative mechanisms are unknown. The present review proposes that alcohol's association with breast cancer is mediated by phosphate toxicity, which is the accumulation of inorganic phosphate in body tissue. Alcohol burdens renal function and causes nontraumatic rhabdomyolysis that releases inorganic phosphate into serum, leading to hyperphosphatemia, phosphate toxicity, and tumorigenesis by stimulating cancer cell growth. Insights in this review may raise awareness of breast cancer risk associated with alcohol consumption.
Background
Ultrasound is a non‐invasive and readily available tool that can be prospectively applied at the bedside to assess muscle mass in clinical settings. The four‐site protocol, which images ...two anatomical sites on each quadriceps, may be a viable bedside method, but its ability to predict musculature has not been compared against whole‐body reference methods. Our primary objectives were to (i) compare the four‐site protocol's ability to predict appendicular lean tissue mass from dual‐energy X‐ray absorptiometry; (ii) optimize the predictability of the four‐site protocol with additional anatomical muscle thicknesses and easily obtained covariates; and (iii) assess the ability of the optimized protocol to identify individuals with low lean tissue mass.
Methods
This observational cross‐sectional study recruited 96 university and community dwelling adults. Participants underwent ultrasound scans for assessment of muscle thickness and whole‐body dual‐energy X‐ray absorptiometry scans for assessment of appendicular lean tissue. Ultrasound protocols included (i) the nine‐site protocol, which images nine anterior and posterior muscle groups in supine and prone positions, and (ii) the four‐site protocol, which images two anterior sites on each quadriceps muscle group in a supine position.
Results
The four‐site protocol was strongly associated (R2 = 0.72) with appendicular lean tissue mass, but Bland–Altman analysis displayed wide limits of agreement (−5.67, 5.67 kg). Incorporating the anterior upper arm muscle thickness, and covariates age and sex, alongside the four‐site protocol, improved the association (R2 = 0.91) with appendicular lean tissue and displayed narrower limits of agreement (−3.18, 3.18 kg). The optimized protocol demonstrated a strong ability to identify low lean tissue mass (area under the curve = 0.89).
Conclusions
The four‐site protocol can be improved with the addition of the anterior upper arm muscle thickness, sex, and age when predicting appendicular lean tissue mass. This optimized protocol can accurately identify low lean tissue mass, while still being easily applied at the bedside.
Foodborne diseases are an important public health issue, and young adults are an important demographic to target with food safety education. Our objective was to assess the food safety knowledge of ...undergraduate students at a Canadian university, to identify potential areas for such education.
In February 2015, we conducted an online survey of 485 undergraduate students at a university in Ontario, Canada. We assessed various food-related factors, including cooking frequency and prior food handling or preparation education. We then modeled the relationship between 'overall knowledge score' and the demographic and food skills/cooking experience predictors using multivariable log-binomial regression, to determine factors associated with relatively higher proportions of correct responses.
Respondents were, on average, 20.5 years old, and the majority (64.8 %) lived off campus. Students cooked from basic ingredients infrequently, with 3 in 4 doing so a few times a year to never. Students averaged 6.2 correct answers to the 11 knowledge questions. Adjusting for other important covariates, older age and being a current food handler were associated with relatively higher knowledge, whereas working/volunteering in a hospital and infrequent cooking were associated with relatively lower knowledge. Males in the Faculty of Science had relatively higher knowledge than females in the Faculty of Science, both of whom had relatively higher knowledge than all students in other Faculties. Among students who had never taken a food preparation course, knowledge increased with self-reported cooking ability; however, among students who had taken such a course, knowledge was highest among those with low self-reported cooking ability.
Consistent with other similar studies, students in Faculties outside of the Faculty of Science, younger students, and those who cook infrequently could benefit from food safety education. Supporting improved hand hygiene, in particular clarifying hand washing versus hand sanitizing messages, may also be important. Universities can play a role in such education, including as part of preparing students for work or volunteer placements, or as general support for student health and success.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
PDF
