Nonlinear Associations between Medical Expenditure, Perceived Medical Attitude, and Sociodemographics, and Older Adults’ Self-Rated Health in China: Applying the Extreme Gradient Boosting Model

Background: although China’s total health expenditure has been dramatically increased so that the country can cope with its aging population, inequalities among individuals in terms of their medical expenditures (relative to their income level) have exacerbated health problems among older adults. This study aims to examine the nonlinear associations between each of medical expenditure, perceived medical attitude, and sociodemographics, and older adults’ self-rated health (SRH); it does so by using data from the 2018 China Family Panel Studies survey. Method: we used the extreme gradient boosting model to explore the nonlinear association between various factors and older adults’ SRH outcomes. We then conducted partial dependence plots to examine the threshold effects of each factor on older adults’ SRH. Results: older adults’ medical expenditure exceeded their overall income. Body mass index (BMI) and personal health expenditure play an essential role in predicting older adults’ SRH outcomes. We found older adult age, physical exercise status, and residential location to be robust predictors of SRH outcomes in older adults. Partial dependence plots of the results visualized the nonlinear association between variables and the threshold effects of factors on older adults’ SRH outcomes. Conclusions: findings from this study underscore the importance of medical expenditure, perceived medical attitudes, and BMI as important predictors of health benefits in older adults. The potential threshold effects of medical expenditure on older adults’ SRH outcomes provide a better understanding of the formation of appropriate medical policy interventions by balancing the government and personal medical expenditure to promote health benefits among older adults.

Immature granulocyte percentage for prediction of sepsis in severe burn patients: a machine leaning-based approach

Background Of the existing sepsis markers, immature granulocytes (IG) most frequently reflect the presence of an infection. The importance of IG as an early predictor of sepsis and bacteremia is evaluated differently for each study. This study aimed to evaluate the effectiveness of the Sysmex XN series’ IG% as an independent prognostic indicator of sepsis using machine learning. Methods A total of 2465 IG% results from 117 severe burn patients in the intensive care unit of one institution were retrospectively analyzed. We evaluated the IG% for sepsis using the receiver operating characteristic, logistic regression, and partial dependence plot analyses. Clinical characteristics and other laboratory markers associated with sepsis, including WBC, procalcitonin, and C-reactive protein, were compared with the IG% values. Results Twenty-six of the 117 patients were diagnosed with sepsis. The median IG% value was 2.6% (95% CI: 1.4–3.1). The area under the receiver operating characteristic curve was 0.77 (95% CI: 0.78–0.84) and the optimal cut-off value was 3%, with a sensitivity of 76.9% and specificity of 68.1%. The partial dependence plot of IG% on predicting sepsis showed that an IG% < 4% had low predictability, but increased thereafter. The interaction plot of IG% and C-reactive protein showed an increase in sepsis probability at an IG% of 6% and C-reactive protein of 160 mg/L. Conclusions IG% is moderately useful for predicting sepsis. However, since it can be determined from routine laboratory test results and requires no additional intervention or cost, it could be particularly useful as an auxiliary marker.

Some results on fuzzy relations

Fuzzy relation is one of the main research contents of fuzzy set theory. This paper obtains some results on fuzzy relations by studying relationships between fuzzy relations and their uncertainty measurement. The concepts of equality, dependence, partial dependence and independence between fuzzy relations are first introduced. Then, uncertainty measurement for a fuzzy relation is investigated by using dependence between fuzzy relations. Moreover, the basic properties of uncertainty measurement are obtained. Next, effectiveness analysis is carried out. Finally, an application of the proposed measures in attribute reduction for heterogeneous data is given. These results will be helpful for understanding the essence of a fuzzy relation.

Mortality Prediction Using SaO2/FiO2 Ratio Based on eICU Database Analysis

Purpose. PaO2 to FiO2 ratio (P/F) is used to assess the degree of hypoxemia adjusted for oxygen requirements. The Berlin definition of Acute Respiratory Distress Syndrome (ARDS) includes P/F as a diagnostic criterion. P/F is invasive and cost-prohibitive for resource-limited settings. SaO2/FiO2 (S/F) ratio has the advantages of being easy to calculate, noninvasive, continuous, cost-effective, and reliable, as well as lower infection exposure potential for staff, and avoids iatrogenic anemia. Previous work suggests that the SaO2/FiO2 ratio (S/F) correlates with P/F and can be used as a surrogate in ARDS. Quantitative correlation between S/F and P/F has been verified, but the data for the relative predictive ability for ICU mortality remains in question. We hypothesize that S/F is noninferior to P/F as a predictive feature for ICU mortality. Using a machine-learning approach, we hope to demonstrate the relative mortality predictive capacities of S/F and P/F. Methods. We extracted data from the eICU Collaborative Research Database. The features age, gender, SaO2, PaO2, FIO2, admission diagnosis, Apache IV, mechanical ventilation (MV), and ICU mortality were extracted. Mortality was the dependent variable for our prediction models. Exploratory data analysis was performed in Python. Missing data was imputed with Sklearn Iterative Imputer. Random assignment of all the encounters, 80% to the training (n = 26690) and 20% to testing (n = 6741), was stratified by positive and negative classes to ensure a balanced distribution. We scaled the data using the Sklearn Standard Scaler. Categorical values were encoded using Target Encoding. We used a gradient boosting decision tree algorithm variant called XGBoost as our model. Model hyperparameters were tuned using the Sklearn RandomizedSearchCV with tenfold cross-validation. We used AUC as our metric for model performance. Feature importance was assessed using SHAP, ELI5 (permutation importance), and a built-in XGBoost feature importance method. We constructed partial dependence plots to illustrate the relationship between mortality probability and S/F values. Results. The XGBoost hyperparameter optimized model had an AUC score of .85 on the test set. The hyperparameters selected to train the final models were as follows: colsample_bytree of 0.8, gamma of 1, max_depth of 3, subsample of 1, min_child_weight of 10, and scale_pos_weight of 3. The SHAP, ELI5, and XGBoost feature importance analysis demonstrates that the S/F ratio ranks as the strongest predictor for mortality amongst the physiologic variables. The partial dependence plots illustrate that mortality rises significantly above S/F values of 200. Conclusion. S/F was a stronger predictor of mortality than P/F based upon feature importance evaluation of our data. Our study is hypothesis-generating and a prospective evaluation is warranted. Take-Home Points. S/F ratio is a noninvasive continuous method of measuring hypoxemia as compared to P/F ratio. Our study shows that the S/F ratio is a better predictor of mortality than the more widely used P/F ratio to monitor and manage hypoxemia.

Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance

This paper reviews and advocates against the use of permute-and-predict (PaP) methods for interpreting black box functions. Methods such as the variable importance measures proposed for random forests, partial dependence plots, and individual conditional expectation plots remain popular because they are both model-agnostic and depend only on the pre-trained model output, making them computationally efficient and widely available in software. However, numerous studies have found that these tools can produce diagnostics that are highly misleading, particularly when there is strong dependence among features. The purpose of our work here is to (i) review this growing body of literature, (ii) provide further demonstrations of these drawbacks along with a detailed explanation as to why they occur, and (iii) advocate for alternative measures that involve additional modeling. In particular, we describe how breaking dependencies between features in hold-out data places undue emphasis on sparse regions of the feature space by forcing the original model to extrapolate to regions where there is little to no data. We explore these effects across various model setups and find support for previous claims in the literature that PaP metrics can vastly over-emphasize correlated features in both variable importance measures and partial dependence plots. As an alternative, we discuss and recommend more direct approaches that involve measuring the change in model performance after muting the effects of the features under investigation.

Fulfillment Of Activity Daily Living (ADL) In Breast Cancer Patients Undergoing Chemotherapy At Haji Adam Malik Hospital Medan

Breast cancer arises as a result of abnormal cells forming in the breast at an uncontrolled and irregular rate. There are several types of treatment for breast cancer patients and one of them is chemotherapy. The frequency of chemotherapy can cause several effects that can worsen the patient's functional status. Functional status is an ability to perform daily tasks that include work, self-care, and maintenance of family or social roles. This study aims to identify ADL compliance in breast cancer patients undergoing chemotherapy. This study used a descriptive design, the sample was taken using a non-probability sampling method, namely accidental sampling and the instrument used was a questionnaire compiled using a Likert scale. The reliability test of this study used a Cronbach Alpha of 0.917. Data collection was carried out from September 2015 to August 2016. The description of ADL fulfillment of breast cancer patients undergoing chemotherapy was described to determine the frequency and percentage. The results showed that the fulfillment of ADL in breast cancer patients undergoing chemotherapy was independent (20 people, 54.1%), partial dependence (10 people, 27%), and total dependence (7 people, 18.9%). It can be concluded that most breast cancer patients undergoing chemotherapy can carry out their Activity Daily Living with an independent level of ability. The description of ADL fulfillment of breast cancer patients undergoing chemotherapy is described to determine the frequency and percentage. The results showed that the fulfillment of ADL in breast cancer patients undergoing chemotherapy was independent (20 people, 54.1%), partial dependence (10 people, 27%), and total dependence (7 people, 18.9%). It can be concluded that most breast cancer patients undergoing chemotherapy can carry out their Activity Daily Living with an independent level of ability. The description of ADL fulfillment of breast cancer patients undergoing chemotherapy is described to determine the frequency and percentage. The results showed that the fulfillment of ADL in breast cancer patients undergoing chemotherapy was independent (20 people, 54.1%), partial dependence (10 people, 27%), and total dependence (7 people, 18.9%). It can be concluded that most breast cancer patients undergoing chemotherapy can carry out their Activity Daily Living with an independent level of ability.

The Comparison and Interpretation of Machine-Learning Models in Post-Stroke Functional Outcome Prediction

Prediction of post-stroke functional outcomes is crucial for allocating medical resources. In this study, a total of 577 patients were enrolled in the Post-Acute Care-Cerebrovascular Disease (PAC-CVD) program, and 77 predictors were collected at admission. The outcome was whether a patient could achieve a Barthel Index (BI) score of >60 upon discharge. Eight machine-learning (ML) methods were applied, and their results were integrated by stacking method. The area under the curve (AUC) of the eight ML models ranged from 0.83 to 0.887, with random forest, stacking, logistic regression, and support vector machine demonstrating superior performance. The feature importance analysis indicated that the initial Berg Balance Test (BBS-I), initial BI (BI-I), and initial Concise Chinese Aphasia Test (CCAT-I) were the top three predictors of BI scores at discharge. The partial dependence plot (PDP) and individual conditional expectation (ICE) plot indicated that the predictors’ ability to predict outcomes was the most pronounced within a specific value range (e.g., BBS-I < 40 and BI-I < 60). BI at discharge could be predicted by information collected at admission with the aid of various ML models, and the PDP and ICE plots indicated that the predictors could predict outcomes at a certain value range.

Sarcospan increases laminin binding capacity of α-dystroglycan to ameliorate DMD independent of Galgt2

In Duchenne muscular dystrophy (DMD), mutations in dystrophin result in a loss of the dystrophin-glycoprotein complex at the myofiber membrane, which functions to connect the extracellular matrix with the intracellular actin cytoskeleton. The dystroglycan subcomplex interacts with dystrophin and spans the sarcolemma where its extensive carbohydrates (matriglycan and CT2 glycan) directly interact with the extracellular matrix. In the current manuscript, we show that sarcospan overexpression enhances the laminin-binding capacity of dystroglycan in DMD muscle by increasing matriglycan glycosylation of α-dystroglycan. Furthermore, we find that this modification is not affected by loss of Galgt2, a glycotransferase which catalyzes the CT2 glycan. Our findings reveal that the matriglycan carbohydrates, and not the CT2 glycan, are necessary for sarcospan-mediated amelioration of DMD. Overexpression of Galgt2 in the DMD mdx murine model prevents muscle pathology by increasing CT2 modified α-dystroglycan. Galgt2 also increases expression of utrophin, which compensates for the loss of dystrophin in DMD muscle. We found that combined loss of Galgt2 and dystrophin reduced utrophin expression; however, it did not interfere with sarcospan rescue of disease. These data reveal a partial dependence of sarcospan on Galgt2 for utrophin upregulation. In addition, sarcospan alters the cross-talk between the adhesion complexes by decreasing the association of integrin β1D with dystroglycan complexes. In conclusion, sarcospan functions to re-wire the cell to matrix connections by strengthening the cellular adhesion and signaling which, in turn, increases the resilience of the myofiber membrane.