A prediction rule for the development of delirium among patients in medical wards: Chi-Square Automatic Interaction Detector (CHAID) decision tree analysis model

The Multidimensional Prognostic Index predicts incident delirium among hospitalized older patients with COVID-19: a multicenter prospective European study

PURPOSE

Incident delirium is a frequent complication among hospitalized older people with COVID-19, associated with increased length of hospital stay, higher morbidity and mortality rates. Although delirium is preventable with early detection, systematic assessment methods and predictive models are not universally defined, thus delirium is often underrated. In this study, we tested the role of the Multidimensional Prognostic Index (MPI), a prognostic tool based on Comprehensive Geriatric Assessment, to predict the risk of incident delirium.

METHODS

Hospitalized older patients (≥ 65 years) with COVID-19 infection were enrolled (n = 502) from ten centers across Europe. At hospital admission, the MPI was administered to all the patients and two already validated delirium prediction models were computed (AWOL delirium risk-stratification score and Martinez model). Delirium occurrence during hospitalization was ascertained using the 4A's Test (4AT). Accuracy of the MPI and the other delirium predictive models was assessed through logistic regression models and the area under the curve (AUC).

RESULTS

We analyzed 293 patients without delirium at hospital admission. Of them 33 (11.3%) developed delirium during hospitalization. Higher MPI score at admission (higher multidimensional frailty) was associated with higher risk of incident delirium also adjusting for the other delirium predictive models and COVID-19 severity (OR = 12.72, 95% CI = 2.11-76.86 for MPI-2 vs MPI-1, and OR = 33.44, 95% CI = 4.55-146.61 for MPI-3 vs MPI-1). The MPI showed good accuracy in predicting incident delirium (AUC = 0.71) also superior to AWOL tool, (AUC = 0.63) and Martinez model (AUC = 0.61) (p < 0.0001 for both comparisons).

CONCLUSIONS

The MPI is a sensitive tool for early identification of older patients with incident delirium.

Non-invasive diagnosis of bacterial and non-bacterial inflammations using a dual-enzyme-responsive fluorescent indicator

Bacterial infections, as the second leading cause of global death, are commonly treated with antibiotics. However, the improper use of antibiotics contributes to the development of bacterial resistance. Therefore, the accurate differentiation between bacterial and non-bacterial inflammations is of utmost importance in the judicious administration of clinical antibiotics and the prevention of bacterial resistance. However, as of now, no fluorescent probes have yet been designed for the relevant assessments. To this end, the present study reports the development of a novel fluorescence probe (CyQ) that exhibits dual-enzyme responsiveness. The designed probe demonstrated excellent sensitivity in detecting NTR and NAD(P)H, which served as critical indicators for bacterial and non-bacterial inflammations. The utilization of CyQ enabled the efficient detection of NTR and NAD(P)H in distinct channels, exhibiting impressive detection limits of 0.26 μg mL-1 for NTR and 5.54 μM for NAD(P)H, respectively. Experimental trials conducted on living cells demonstrated CyQ's ability to differentiate the variations in NTR and NAD(P)H levels between A. baumannii, S. aureus, E. faecium, and P. aeruginosa-infected as well as LPS-stimulated HUVEC cells. Furthermore, in vivo zebrafish experiments demonstrated the efficacy of CyQ in accurately discerning variations in NTR and NAD(P)H levels resulting from bacterial infection or LPS stimulation, thereby facilitating non-invasive detection of both bacterial and non-bacterial inflammations. The outstanding discriminatory ability of CyQ between bacterial and non-bacterial inflammation positions it as a promising clinical diagnostic tool for acute inflammations.

Description of an individualised delirium intervention in intensive care units for critically ill patients delivered by an artificial intelligence-assisted system: using the TIDieR checklist

Background

Delirium is a preventable and reversible complication for intensive care unit (ICU) patients, which can be linked to negative outcomes. Early intervention to cope with the risk factors of delirium is necessary. Yet no specific description of the Artificial Intelligence Assisted Prevention and Management for Delirium (AI-AntiDelirium) following the Template for Intervention Description and Replication (TIDieR) checklist was reported. This is the first study to describe a detailed process for the development of an evidence-based delirium intervention.

Aims

To describe an individualised delirium intervention which is delivered by an artificial intelligence-assisted system in the ICU for critically ill patients.

Methods and results

The TIDieR checklist improved the description of ICU delirium interventions, including several key features for improved implementation of the intervention. This descriptive research describes the AI-assisted ICU delirium interventions for improving cognitive load and adherence of nurses and reducing ICU delirium incidence. Following the TIDieR checklist, we standardised the flow chart of ICU delirium assessment tools; formed an evaluation sheet of ICU delirium risk factors; and translated the evidence-based ABCDEF bundle intervention into practice. Therefore, nurses and researchers would benefit from replicating the interventions for clinical use or experimental research.

Conclusions

The TIDieR checklist provided a systematic approach for reporting the complex ICU delirium interventions delivered in a clinical interventional trial, which contributes to the nursing practice policy for the standardisation of interventions.

Risk Assessment Score and Chi-Square Automatic Interaction Detection Algorithm for Hypertension Among Africans: Models From the SIREN Study

BACKGROUND

This study aimed to develop a risk-scoring model for hypertension among Africans.

METHODS

In this study, 4413 stroke-free controls were used to develop the risk-scoring model for hypertension. Logistic regression models were applied to 13 risk factors. We randomly split the dataset into training and testing data at a ratio of 80:20. Constant and standardized weights were assigned to factors significantly associated with hypertension in the regression model to develop a probability risk score on a scale of 0 to 1 using a logistic regression model. The model accuracy was assessed to estimate the cutoff score for discriminating hypertensives.

RESULTS

Mean age was 59.9±13.3 years, 56.0% were hypertensives, and 8 factors, including diabetes, age ≥65 years, higher waist circumference, (BMI) ≥30 kg/m2, lack of formal education, living in urban residence, family history of cardiovascular diseases, and dyslipidemia use were associated with hypertension. Cohen κ was maximal at ≥0.28, and a total probability risk score of ≥0.60 was adopted for both statistical weighting for risk quantification of hypertension in both datasets. The probability risk score presented a good performance-receiver operating characteristic: 64% (95% CI, 61.0-68.0), a sensitivity of 55.1%, specificity of 71.5%, positive predicted value of 70.9%, and negative predicted value of 55.8%, in the test dataset. Similarly, decision tree had a predictive accuracy of 67.7% (95% CI, 66.1-69.3) for the training set and 64.6% (95% CI, 61.0-68.0) for the testing dataset.

CONCLUSIONS

The novel risk-scoring model discriminated hypertensives with good accuracy and will be helpful in the early identification of community-based Africans vulnerable to hypertension for its primary prevention.

Predictive Rule for Mortality of Inpatients With Escherichia coli Bacteremia: Chi-Square Automatic Interaction Detector Decision Tree Analysis Model

AIM

A predictive rule for risk factors for mortality due to Escherichia coli (E. coli)bacteremia has not been defined, especially using the chi-square automatic interaction detector (CHAID) decision tree analysis. Here we aimed to create the predictive rule for risk factors for in-hospital mortality due to E. coli bacteremia.

METHODS

The outcome of this retrospective cross-sectional survey was death in the hospital due to E. coli bacteremia. Factors potentially predictive of death in the hospital due to E. coli bacteremia were analyzed using the CHAID decision tree analysis.

RESULTS

A total of 420 patients (male:female=196:224; mean±standard deviation [SD] age, 75.81±13.13 years) were included in this study. 56 patients (13.3%) died in the hospital. The CHAID decision tree analysis revealed that patients with total protein level ≤5.10 g/dL (incidence, 46.2%), total protein level ≤5.90 g/dL with disturbance of consciousness (incidence, 39.4%), and total protein level >5.90 g/dL with hemoglobin level ≤11.10 g/dL and lactate dehydrogenase level ≥312.0 IU/L (incidence, 42.3%) were included in the high-risk group.

CONCLUSIONS

Appropriate preventative therapy should be facilitated in patients with E. coliat a high risk of mortality.

Risk of bias in prognostic models of hospital-induced delirium for medical-surgical units: A systematic review

PURPOSE

The purpose of this systematic review was to assess risk of bias in existing prognostic models of hospital-induced delirium for medical-surgical units.

METHODS

APA PsycInfo, CINAHL, MEDLINE, and Web of Science Core Collection were searched on July 8, 2022, to identify original studies which developed and validated prognostic models of hospital-induced delirium for adult patients who were hospitalized in medical-surgical units. The Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies was used for data extraction. The Prediction Model Risk of Bias Assessment Tool was used to assess risk of bias. Risk of bias was assessed across four domains: participants, predictors, outcome, and analysis.

RESULTS

Thirteen studies were included in the qualitative synthesis, including ten model development and validation studies and three model validation only studies. The methods in all of the studies were rated to be at high overall risk of bias. The methods of statistical analysis were the greatest source of bias. External validity of models in the included studies was tested at low levels of transportability.

CONCLUSIONS

Our findings highlight the ongoing scientific challenge of developing a valid prognostic model of hospital-induced delirium for medical-surgical units to tailor preventive interventions to patients who are at high risk of this iatrogenic condition. With limited knowledge about generalizable prognosis of hospital-induced delirium in medical-surgical units, existing prognostic models should be used with caution when creating clinical practice policies. Future research protocols must include robust study designs which take into account the perspectives of clinicians to identify and validate risk factors of hospital-induced delirium for accurate and generalizable prognosis in medical-surgical units.

Clinical prediction rule for bacterial arthritis: Chi-squared automatic interaction detector decision tree analysis model

Objectives:

Differences in demographic factors, symptoms, and laboratory data between bacterial and non-bacterial arthritis have not been defined. We aimed to identify predictors of bacterial arthritis, excluding synovial testing.

Methods:

This retrospective cross-sectional survey was performed at a university hospital. All patients included received arthrocentesis from January 1, 2010, to December 31, 2020. Clinical information was gathered from medical charts from the time of synovial fluid sample collection. Factors potentially predictive of bacterial arthritis were analyzed using the Student’s t-test or chi-squared test, and the chi-squared automatic interaction detector decision tree analysis. The resulting subgroups were divided into three groups according to the risk of bacterial arthritis: low-risk, intermediate-risk, or high-risk groups.

Results:

A total of 460 patients (male/female = 229/231; mean ± standard deviation age, 70.26 ± 17.66 years) were included, of whom 68 patients (14.8%) had bacterial arthritis. The chi-squared automatic interaction detector decision tree analysis revealed that patients with C-reactive protein > 21.09 mg/dL (incidence of septic arthritis: 48.7%) and C-reactive protein ⩽ 21.09 mg/dL plus 27.70 < platelet count ⩽ 30.70 × 10⁴/μL (incidence: 36.1%) were high-risk groups.

Conclusions:

Our results emphasize that patients categorized as high risk of bacterial arthritis, and appropriate treatment could be initiated as soon as possible.

Prediction of Catheter-Associated Urinary Tract Infections Among Neurosurgical Intensive Care Patients: A Decision Tree Analysis

BACKGROUND

Catheter-associated urinary tract infections (CAUTIs) are the most common device-associated infections in hospitals and can be prevented. To identify the risk factors and develop a risk prediction model for CAUTIs among neurosurgical intensive care unit (NICU) patients.

METHODS

All patients admitted to the NICU of a tertiary hospital between January 2019 and January 2020 were enrolled. Two decision tree models were applied to analyze the risk factors associated with CAUTIs in NICU patients. The performance of the decision tree model was evaluated.

RESULTS

A total of 537 patients admitted to the NICU with indwelling catheters were recruited for this study. The rate of CAUTIs was 4.44 per 1000 catheter days, and Escherichia coli was the predominant pathogen causing CAUTIs among indwelling catheter patients. The classification and regression tree model displayed good power of prediction (area under the curve : 0.920). Nine CAUTI risk factors (age ≥60 years (P = 0.004), Glasgow Coma Scale score ≤8 (P = 0.009), epilepsy at admission (P = 0.007), admission to the hospital during the summer (P < 0.001), ventilators use (P = 0.007), receiving less than 2 types of antibiotics (P < 0.001), albumin level <35 g/L (P = 0.002), female gender (P = 0.002), and having an indwelling catheter for 7-14 days (P = 0.001) were also identified.

CONCLUSION

We developed a novel scoring model for predicting the risk of CAUTIs in patients with neuro-critical illness in daily clinical practice. This model identified several risk factors for CAUTI among NICU patients, novel factors including epilepsy and admission during the summer, can be used to help providers prevent and reduce the risk of CAUTI among vulnerable groups.

Chi-square automatic interaction detector decision tree analysis model: Predicting cefmetazole response in intra-abdominal infection

BACKGROUND

Cefmetazole is used as the first-line treatment for intra-abdominal infections. However, only a few studies have investigated the risk factors for cefmetazole treatment failure.

AIMS

This study aimed to develop a decision tree-based predictive model to assess the effectiveness of cefmetazole in initial intra-abdominal infection treatment to improve the clinical treatment strategies.

METHODS

This retrospective cohort study included adult patients who were unexpectedly hospitalized due to intra-abdominal infections between 2003 and 2020 and initially treated with cefmetazole. The primary outcome was clinical intra-abdominal infection improvement. The chi-square automatic interaction detector decision tree analysis was used to create a predictive model for clinical improvement after cefmetazole treatment.

RESULTS

Among 2,194 patients, 1,807 (82.4%) showed clinical improvement post-treatment; their mean age was 48.7 (standard deviation: 18.8) years, and 1,213 (55.3%) patients were men. The intra-abdomせinal infections were appendicitis (n = 1,186, 54.1%), diverticulitis (n = 334, 15.2%), and pancreatitis (n = 285, 13.0%). The chi-square automatic interaction detector decision tree analysis identified the intra-abdominal infection type, C-reactive protein level, heart rate, and body temperature as predictive factors by categorizing patients into seven groups. The area under the receiver operating characteristic curve was 0.71 (95% confidence interval: 0.68-0.73).

CONCLUSION

This predictive model is easily understandable visually and may be applied in clinical practice.

Determinants of compulsory hospitalisation at admission and in the course of inpatient treatment in people with mental disorders-a retrospective analysis of health records of the four psychiatric hospitals of the city of Cologne

BACKGROUND

We aimed to identify differences in predictors of involuntary psychiatric hospitalisation depending on whether the inpatient stay was involuntary right from the beginning since admission or changed from voluntary to involuntary in the course of in-patient treatment.

METHODS

We conducted an analysis of 1,773 mental health records of all cases treated under the Mental Health Act in the city of Cologne in the year 2011. 79.4% cases were admitted involuntarily and 20.6% were initially admitted on their own will and were detained later during the course of in-patient stay. We compared the clinical, sociodemographic, socioeconomic and environmental socioeconomic data (ESED) of the two groups. Finally, we employed two different machine learning decision-tree algorithms, Chi-squared Automatic Interaction Detection (CHAID) and Random Forest.

RESULTS

Most of the investigated variables did not differ and those with significant differences showed consistently low effect sizes. In the CHAID analysis, the first node split was determined by the hospital the patient was treated at. The diagnosis of a psychotic disorder, an affective disorder, age, and previous outpatient treatment as well as the purchasing power per 100 inhabitants in the living area of the patients also played a role in the model. In the Random Forest, age and the treating hospital had the highest impact on the accuracy and decrease in Gini of the model. However, both models achieved a poor balanced accuracy. Overall, the decision-tree analyses did not yield a solid, causally interpretable prediction model.

CONCLUSION

Cases with detention at admission and cases with detention in the course of in-patient treatment were largely similar in respect to the investigated variables. Our findings give no indication for possible differential preventive measures against coercion for the two subgroups. There is no need or rationale to differentiate the two subgroups in future studies.

Development of Artificial Intelligence Methods for Determination of Methane Solubility in Aqueous Systems

Accurate determinations of water (H2O) content in natural gases especially in the methane (CH4) phase are highly important for chemical engineers dealing with natural gas processes. To this end, development of a high performance model is necessary. Due to importance of the solubility of methane in the aqueous solutions for natural gas industries, two novel models based on the Decision Tree (DT) and Adaptive Neuro-Fuzzy Interference System (ANFIS) have been employed. To this end, a total number of 204 real methane solubility points in aqueous solution containing NaCl under different pressure and temperature conditions have been gathered. The comparisons between predicted solubility values and experimental data points have been conducted in visual and mathematical approaches. The R2 values of 1 for training and testing phases express the great ability of proposed models in calculation of methane solubility in pure water systems.

Clinical prediction rule for bacteremia with pyelonephritis and hospitalization judgment: chi-square automatic interaction detector (CHAID) decision tree analysis model

Objective

This study was performed to identify predictive factors for bacteremia among patients with pyelonephritis using a chi-square automatic interaction detector (CHAID) decision tree analysis model.

Methods

This retrospective cross-sectional survey was performed at Juntendo University Nerima Hospital, Tokyo, Japan and included all patients with pyelonephritis from whom blood cultures were taken. At the time of blood culture sample collection, clinical information was extracted from the patients’ medical charts, including vital signs, symptoms, laboratory data, and culture results. Factors potentially predictive of bacteremia among patients with pyelonephritis were analyzed using Student’s t-test or the chi-square test and the CHAID decision tree analysis model.

Results

In total, 198 patients (60 (30.3%) men, 138 (69.7%) women; mean age, 74.69 ± 15.27 years) were included in this study, of whom 92 (46.4%) had positive blood culture results. The CHAID decision tree analysis revealed that patients with a white blood cell count of >21,000/μL had a very high risk (89.5%) of developing bacteremia. Patients with a white blood cell count of ≤21,000/μL plus chills plus an aspartate aminotransferase concentration of >19 IU/L constituted the high-risk group (69.0%).

Conclusion

The present results are extremely useful for predicting the results of bacteremia among patients with pyelonephritis.

Inclusion of interleukin-6 improved performance of postoperative delirium prediction for patients undergoing coronary artery bypass graft (POD-CABG): A derivation and validation study

BACKGROUND

Patients undergoing coronary artery bypass graft (CABG) are at high risk for developing postoperative delirium (POD). A simple prediction rule may benefit patients from early identification of POD followed by adequate preventive strategies. The purpose of the current study was to develop and validate a POD prediction rule for patients undergoing CABG (POD-CABG), by considering all possible perioperative factors.

METHODS

In this prospective cohort study, patients who underwent first elective isolated CABG were continuously enrolled from May 2014 to November 2015 in a tertiary hospital. Delirium was assessed using the Confusion Assessment Method for Intensive Care Unit. Patients' perioperative risk factors were collected through interviews and review of medical records. The area under receiver-operating characteristic curve (AUC) was used to assess the overall performance of the predictive rule.

RESULTS

A total of 242 and 148 patients were enrolled in the derivation and validation cohorts, respectively. Multiple logistic regression analysis identified seven variables that were independently associated with POD: age (≥65 years), gender (female), history of myocardial infarction and diabetes mellitus, postoperative atrial fibrillation, the use of intra-aortic balloon pump, and serum interleukin-6 ≥478 pg/ml at 18 hours after surgery. The AUC of the POD-CABG was 0.84 (95% CI, 0.79-0.90) in the derivation cohort, and was 0.86 (95% CI, 0.80-0.91) after bootstrap resampling. The AUC was 0.81 (95% CI, 0.73-0.88) after the POD-CABG was applied to the validation cohort.

CONCLUSIONS

The POD-CABG with inclusion of interleukin-6 demonstrated good performance in predicting POD.

Do we need to conduct full-thickness closure after endoscopic full-thickness resection of gastric submucosal tumors?

BACKGROUND/AIMS

Successful closure of gastric wall defects is a pivotal step for endoscopic full-thickness resection (EFTR). Our study indicates that for submucosal tumors (SMTs) smaller than 2.5 cm, closing the mucosal layer is safe and feasible when the modified method, ZIP, is used.

MATERIALS AND METHODS

We retrospectively analyzed 37 patients with gastric SMTs arising from the muscularis propria (MP) who underwent EFTR with defect closure of the mucosal layer. The main procedure involved: (1) making a longitudinal incision of the mucosal and submucosal layers above the lesion, (2) fully exposing the lesion and symmetrically punching holes on both sides of the incision into the submucosal layer, (3) en bloc resection of the lesion using an electrosurgical snare or knife, (4) hooking of metallic clips into the holes and clipping of the mucosal layer successively to close the gastric wall defect. This modified method was named ZIP.

RESULTS

Successful complete resection by EFTR was achieved in 37 cases (100%). The median procedure time was 60 min (range: 30-120 min), whereas the closure procedure took a median of 8 min (range: 5-20 min). The median lesion size was 1.0 cm (range: 0.5-2.5 cm). No patients had severe complications. No residual lesions or tumor recurrence were found during the follow-up period.

CONCLUSION

Closing the mucosal layer of gastric wall defects after EFTR by ZIP is feasible and effective.

Establishment of a predictive model for outcomes in patients with severe acute pancreatitis by nucleated red blood cells combined with Charlson complication index and APACHE II score

BACKGROUND/AIMS

Nucleated red blood cell (NRBC) is an immature red blood cell, which can appear in the peripheral blood of newborns but not in normal adults. However, in the presence of hemorrhage, severe hypoxia, or severe infection, NRBCs may exist in adult blood and are associated with prognosis. The aims of this study were to establish a predictive model for the outcome of patients with severe acute pancreatitis (SAP) based on NRBCs.

MATERIALS AND METHODS

Data from 92 patients with SAP were retrospectively collected for the study. We used chi-square automatic interaction detection (CHAID) to explore a prediction model of mortality in patients with SAP by NRBCs.

RESULTS

During the 90-day follow-up, 11 participants (12.0%) died. The NRBC-positive rate of nonsurvivors was much higher than survivors (90.9% vs. 23.5%). Charlson Comorbidity Index (CCI), Acute Physiology and Chronic Health Evaluation II (APACHE II), Ranson score, and serum C-reactive protein were higher in nonsurvivors (5.0, 29.0, 6.0, and 140.0 g/L) than survivors (3.0, 13.0, 4.0, and 54.7 g/L). A CHAID model including NRBC, CCI, APACHE II score, and Ranson score showed that NRBCs differentiated well between nonsurvivors and survivors. All patients with SAP survived when they had a negative test result for NRBCs and CCI was below 7. All patients died when they had a positive test result for NRBCs and APACHE II score exceeded 30. Among patients whose NRBC test result was positive and APACHE II score was below 30, if the Ranson score was less than 5, the mortality rate was only 5.6%, whereas the mortality rate was 66.7% if the Ranson score exceeded 5. A validated population of 32 patients showed that the accuracy of the prediction model was 100%.

CONCLUSION

NRBC combined with CCI, APACHE II, and Ranson score can predict 90-day mortality of patients with SAP.

Development of a Simple and Practical Delirium Screening Tool for Use in Surgical Wards

BACKGROUND

Delirium is an important and common medical condition, particularly in hospitalized patients, that is associated with adverse outcomes. The identification, prevention, and treatment of delirium are increasingly regarded as major public health priorities.

PURPOSE

The aim of this study was to create a simple-to-use screening tool for delirium in hospitalized patients using clinical manifestations of delirium regularly observed by nurses.

METHODS

This study was conducted using data on 2,168 patients who had been admitted to the surgical ward between January 2011 and December 2014. Data were collected retrospectively from medical records. Univariate and multivariate analyses were performed, and a logistic regression model was constructed for the development of a predictive screening tool. After constructing a new screening tool for delirium, a receiver operating characteristic curve was drawn, the most appropriate cutoff value was decided, and the area under the curve was obtained. Bootstrapping was used for the internal model validation.

RESULTS

A screening tool for delirium (Subjective Delirium Screening Scale by Nurse) with a total score of 5 points was constructed as follows: 2 points for disorientation and 1 point each for restlessness, somnolence, and hallucination. The area under the curve for the Subjective Delirium Screening Scale by Nurse was 81.9% (95% CI [77.9%, 85.8%]), and the most appropriate cutoff value was determined to be 2 (sensitivity of 61.0% and specificity of 96.7%). Bootstrapped validation beta coefficients of the predictive factors were similar to the original cohort beta coefficients.

CONCLUSIONS

We created a screening tool for delirium using factors that were regularly observed and recorded by nurses. This tool is simple and practical and has adequate diagnostic accuracy.

Research on diagnosis-related group grouping of inpatient medical expenditure in colorectal cancer patients based on a decision tree model

BACKGROUND

In 2018, the diagnosis-related groups prospective payment system (DRGs-PPS) was introduced in a trial operation in Beijing according to the requirements of medical and health reform. The implementation of the system requires that more than 300 disease types pay through the DRGs-PPS for medical insurance. Colorectal cancer (CRC), as a common malignant tumor with high prevalence in recent years, was among the 300 disease types.

AIM

To investigate the composition and factors related to inpatient medical expenditure in CRC patients based on disease DRGs, and to provide a basis for the rational economic control of hospitalization expenses for the diagnosis and treatment of CRC.

METHODS

The basic material and cost data for 1026 CRC inpatients in a Grade-A tertiary hospital in Beijing during 2014-2018 were collected using the medical record system. A variance analysis of the composition of medical expenditure was carried out, and a multivariate linear regression model was used to select influencing factors with the greatest statistical significance. A decision tree model based on the exhaustive χ² automatic interaction detector (E-CHAID) algorithm for DRG grouping was built by setting chosen factors as separation nodes, and the payment standard of each diagnostic group and upper limit cost were calculated. The correctness and rationality of the data were re-evaluated and verified by clinical practice.

RESULTS

The average hospital stay of the 1026 CRC patients investigated was 18.5 d, and the average hospitalization cost was 57872.4 RMB yuan. Factors including age, gender, length of hospital stay, diagnosis and treatment, as well as clinical operations had significant influence on inpatient expenditure (P < 0.05). By adopting age, diagnosis, treatment, and surgery as the grouping nodes, a decision tree model based on the E-CHAID algorithm was established, and the CRC patients were divided into 12 DRG cost groups. Among these 12 groups, the number of patients aged ≤ 67 years, and underwent surgery and chemotherapy or radiotherapy was largest; while patients aged > 67 years, and underwent surgery and chemotherapy or radiotherapy had the highest medical cost. In addition, the standard cost and upper limit cost in the 12 groups were calculated and re-evaluated.

CONCLUSION

It is important to strengthen the control over the use of drugs and management of the hospitalization process, surgery, diagnosis and treatment to reduce the economic burden on patients. Tailored adjustments to medical payment standards should be made according to the characteristics and treatment of disease types to improve the comprehensiveness and practicability of the DRGs-PPS.

Early Recognition of the Preference for Exclusive Breastfeeding in Current China: A Prediction Model based on Decision Trees

Exclusive breastfeeding (EBF) is affected by multiple risk factors. Therefore, it is difficult for clinical professionals to identify women who will not practice EBF well and provide subsequent medical suggestions and treatments. This study aimed to apply a decision tree (DT) model to predict EBF at two months postpartum. The socio-demographic, clinical and breastfeeding parameters of 1,141 breastfeeding women from Nanjing were evaluated. Decision tree modelling was used to analyse and screen EBF factors and establish a risk assessment model of EBF. The Chinese version of the Breastfeeding Self-Efficacy Scale (CV-BSES) score, early formula supplementation, abnormal nipples, mastitis, neonatal jaundice, cracked or sore nipples and intended duration of breastfeeding were significant risk factors associated with EBF in the DT model. The accuracy, sensitivity and specificity of the DT model were 73.1%, 75.5% and 66.3%, respectively. The DT model showed similar or better performance than the logistic regression model in assessing the risk of early cessation of EBF before two months postpartum. The DT model has potential for application in clinical practice and identifies high-risk subpopulations that need specific prevention.

Delirium in hospitalized older adults

Delirium is a common and underdiagnosed problem in hospitalized older adults. It is associated with an increased risk of poor cognitive and functional outcomes, institutionalization, and death. Timely diagnosis of delirium and non-pharmacological prevention and management strategies can improve patient outcomes. The Confusion Assessment Method (CAM) is the most widely used clinical assessment tool for the diagnosis of delirium. Multiple variations of the CAM have been developed for ease of administration and for the unique needs of specific patient populations, including the 3-min diagnostic CAM (3D CAM), CAM-Intensive Care Unit (CAM-ICU), Delirium Triage Screen (DTS)/Brief CAM (b-CAM), 4AT tool, and ultrabrief delirium assessment. Strong evidence supports the effectiveness of nonpharmacologic strategies as the primary intervention for the prevention of delirium. Multicomponent delirium prevention strategies can reduce the incidence of delirium by 40%. Investigation of underlying medical precipitants and optimization of non-pharmacological interventions are first line in the management of delirium. Despite a lack of evidence supporting use of antipsychotics, low dose antipsychotics remain second line for off-label treatment of distressing psychoses and/or agitated behaviors that are refractory to non-pharmacological behavioral interventions and pose an imminent risk of harm to self or others. Any antipsychotic prescription for delirium should be accompanied by an appropriate taper plan. Follow up with primary care providers on discharge from hospital for ongoing screening of cognitive impairment is important.

Diagnosis of Liver Neoplasms by Computational and Statistical Image Analysis

Background

Distinguishing well-differentiated hepatocellular carcinoma (WD-HCC), hepatocellular adenoma (HA) and non-neoplastic liver tissue (NNLT) solely on morphology is often challenging. The purpose of this study was to evaluate the use of computational image analysis to distinguish WD-HCC, HA and NNLT.

Methods

Seventy-seven cases comprising of WD-HCC (n = 26), HA (n = 23) and NNLT (n = 28) were retrieved and reviewed. A total of 485 hematoxylin and eosin (H&E) photomicrographs (× 400, 0.09 µm²) of WD-HCC (n = 183), HA (n = 173), NNLT (n = 129) and nine whole-slide scans (three of each diagnosis) were obtained, color deconvoluted and digitally transformed. Quantitative data including nuclear density, nuclear sphericity, nuclear perimeter, and nuclear eccentricity from each image were acquired. The data were analyzed by one-way analysis of variance (ANOVA) with Tukey post hoc test, followed by unsupervised and supervised (Chi-square automatic interaction detection (CHAID)) cluster analysis.

Results

Unsupervised cluster analysis identified three well defined clusters of WD-HCC, HA and NNLT. Employing the four most discriminating nuclear features, supervised analysis was performed on a training set of 383 images, and validated on the remaining 102 test images. The analysis identified WD-HCC (sensitivity 100%, specificity 98%), HA (sensitivity 71%, specificity 85%) and NNLT (sensitivity 70%, specificity 86%). An analysis of whole-slide images identified WD-HCC with sensitivity and specificity of 100%.

Conclusions

We have successfully demonstrated that computational image analysis of nuclear features can differentiate WD-HCC from non-malignant liver with high accuracy, and can be used to assist in the histopathological diagnosis of hepatocellular carcinoma.

Using Data Analytics to Predict Hospital Mortality in Sepsis Patients

Predictive analytics can be used to anticipate the risks associated with some patients, and prediction models can be employed to alert physicians and allow timely proactive interventions. Recently, health care providers have been using different types of tools with prediction capabilities. Sepsis is one of the leading causes of in-hospital death in the United States and worldwide. In this study, the authors used a large medical dataset to develop and present a model that predicts in-hospital mortality among Sepsis patients. The predictive model was developed using a dataset of more than one million records of hospitalized patients. The independent predictors of in-hospital mortality were identified using the chi-square automatic interaction detector. The authors found that adding hospital attributes to the predictive model increased the accuracy from 82.08% to 85.3% and the area under the curve from 0.69 to 0.84, which is favorable compared to using only patients' attributes. The authors discuss the practical and research contributions of using a predictive model that incorporates both patient and hospital attributes in identifying high-risk patients.

Are ICTs Really That Important in Driving Industry Performance?

A decision tree is used to investigate how information and communication technologies (ICTs) and financial factors influence the performance of service and manufacturing industries globally. Industry performance is measured by average fixed asset purchases among firms at the industry level. In addition, industry sectors and geographic regions are included in the predictive model. The results show that financial factors are better predictors of performance than ICT factors. For example, access to bank loans or lines of credit is by far the best predictor among the variables included in the study. Having a website is the only ICT factor among the top five predictors. Geography also plays an important role in predicting industry performance.

Delirium risk in non-surgical patients: systematic review of predictive tools

OBJECTIVE

Delirium is a common, serious condition associated with poor hospital outcomes. Guidelines recommend screening for delirium risk to target diagnostic and/or prevention strategies. This study critically reviews multicomponent delirium risk prediction tools in adult non-surgical inpatients.

STUDY DESIGN

Systematic review of studies incorporating at least two clinical factors in a multicomponent tool predicting risk of delirium during hospital admission. Derivation and validation studies were included. Study design, risk factors and tool performance were extracted and tabulated, and study quality was assessed by CHARMS criteria.

DATA SOURCES

PubMed, Embase, PsycINFO, and Cumulative Index to Nursing Health Literature (CINAHL) to 11^th March 2018.

DATA SYNTHESIS

22 derivation studies enrolling 38,874 participants (9 with a validation component) and 4 additional validation studies were identified, from a range of ward types. All studies had at least moderate risk of bias. Older age and cognitive, functional and sensory impairment were important predisposing factors. Precipitating risk factors included infection, illness severity, renal and electrolyte disturbances. Tools mostly did not differentiate between predisposing and precipitating risk factors mathematically or conceptually Most tools showed fair to good discrimination, and identified more than half of older inpatients at risk.

CONCLUSIONS

Several validated delirium risk prediction tools can identify patients at increased risk of delirium, but do not provide clear advice for clinical application. Most recommended cut-points are sensitive but have low specificity. Implementation studies demonstrating how risk screening can better direct clinical interventions in specific clinical settings are needed to define the potential value of these tools.

Development and validation of a dynamic delirium prediction rule in patients admitted to the Intensive Care Units (DYNAMIC-ICU): A prospective cohort study

BACKGROUND

Delirium is one of the most common cognitive complications among patients admitted to the intensive care units (ICU).

OBJECTIVE

To develop and validate a DYNAmic deliriuM predICtion rule for ICU patients (DYNAMIC-ICU) and to stratify patients into different risk levels among patients in various types of ICUs.

DESIGN

Prospective cohort study.

SETTING AND PARTICIPANTS

A total of 560 (median age of 66 years, 62.5% male) consecutively enrolled patients from four ICUs were included in the study. The patients were randomly assigned into either the derivation (n = 336, 60%) or the validation (n = 224, 40%) cohort by stratified randomization based on delirium/non-delirium and types of ICU.

METHODS

The simplified Chinese version of the Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) was used to assess delirium until patients were discharged from the ICUs. Potential predisposing, disease-related, and iatrogenic and environmental risk factors as well as data on patients' outcomes were collected prospectively.

RESULTS

Of the enrolled patients, 20.2% and 20.5% developed delirium in the derivation and validation cohorts, respectively. Predisposing factors (history of chronic diseases, hearing deficits), disease-related factors (infection, higher APACHE II scores at admission), and iatrogenic and environmental factors (the use of sedatives and analgesics, indwelling catheter, and sleep disturbance) were identified as independent predictors of delirium. Points were assigned to each predictor according to their odds ratio to create a prediction rule which was internally validated based on total scores and by bootstrapping (AUCs of 0.907 [95% CI 0. 871 -0.944], 0.888 [95% CI 0.845-0.932], and 0.874 [95% CI 0.828-0.920]), respectively. The total score of the DYNAMIC-ICU ranged from 0 to 33 and patients were divided into low risk (0-9), moderate risk (10-17), high risk (18-33) groups in developing delirium according to their total score with incidence of delirium at 2.8%, 16.8% and 75.9% in the derivation group, respectively. The DYNAMIC-ICU and its performance of risk level stratification were further validated in the validation cohort (AUC = 0.900 [95% CI 0.858-0.941]). The all-cause mortality was increased and the length of hospital stay was prolonged dramatically with the increase of delirium risk levels in both derivation (p = 0.034, p < 0.001) and validation cohorts (p < 0.001, p < 0.001).

CONCLUSIONS

Seven predictors for ICU delirium were identified to create DYNAMIC-ICU, which could well stratify ICU patients into three different delirium risk levels, tailor risk level changes, and predict in-hospital outcomes by a dynamic assessment approach.

Nursing assessment as an effective tool for the identification of delirium risk in older in-patients: A case-control study

AIMS AND OBJECTIVES

To evaluate the usefulness of comprehensive nursing assessment as a strategy for determining the risk of delirium in older in-patients from a model of care needs based on variables easily measured by nurses.

BACKGROUND

There are many scales of assessment and prediction of risk of delirium, but they are little known and infrequently used by professionals. Recognition of delirium by doctors and nurses continues to be limited.

DESIGN AND METHODS

A case-control study. A specific form of data collection was designed to include the risk factors for delirium commonly identified in the literature and the care needs evaluated from the comprehensive nursing assessment based on the Virginia Henderson model of care needs. We studied 454 in-patient units in a basic general hospital. Data were collected from a review of the records of patients' electronic clinical history.

RESULTS

The areas of care that were significant in patients with delirium were dyspnoea, problems with nutrition, elimination, mobility, rest and sleep, self-care, physical safety, communication and relationships. The specific risk factors identified as independent predictors were as follows: age, urinary incontinence, urinary catheter, alcohol abuse, previous history of dementia, being able to get out of bed/not being at rest, habitual insomnia and history of social risk.

CONCLUSIONS

Comprehensive nursing assessment is a valid and consistent strategy with a multifactorial model of delirium, which enables the personalised risk assessment necessary to define a plan of care with specific interventions for each patient to be made.

RELEVANCE TO CLINICAL PRACTICE

The identification of the risk of delirium is particularly important in the context of prevention. In a model of care based on needs, nursing assessment is a useful component in the risk assessment of delirium and one that is necessary for developing an individualised care regime.

Models for Predicting Incident Delirium in Hospitalized Older Adults: A Systematic Review

Purpose

The purpose of this systematic review is to summarize the reported risk prediction models and identify the most prevalent factors for incident delirium in older inpatient populations (age ≥ 65 years). In the future, these risk factors could be used to develop a delirium risk prediction model in the electronic health record that can be used by the Hospital Elder Life Program to reduce the incidence of delirium.

Methods

A medical librarian customized and conducted a search strategy for all published articles on delirium prediction models using an array of electronic databases and specific inclusion and exclusion criteria. Then, a geriatrician and two research associates assessed the quality of the selected studies using the Newcastle-Ottawa Scale (NOS).

Results

A total of 4,351 articles were identified from initial literature search. After review, data were extracted from 12 studies. The quality of these studies was assessed using NOS and ranged from 4 to 8. The most common risk factors reported were dementia, decreased functional status, high blood urea nitrogen-to-creatinine ratio, infection and severe illness.

Conclusions

The most prevalent factors associated with incidence of delirium in hospitalized older patients identified by this systematic review could be used to develop an electronic health record-generated risk prediction model to identify inpatients at risk of developing delirium.

Understanding cognition in older patients with cancer

Cancer and neurocognitive disorders, such as dementia and delirium, are common and serious diseases in the elderly that are accompanied by high degree of morbidity and mortality. Furthermore, evidence supports the under-diagnosis of both dementia and delirium in older adults. Complex questions exist regarding the interaction of dementia and delirium with cancer, beginning with guidelines on how best measure disease severity, the optimal screening test for either disorder, the appropriate level of intervention in the setting of abnormal findings, and strategies aimed at preventing the development or progression of either process. Ethical concerns emerge in the research setting, pertaining to the detection of cognitive dysfunction in participants, validity of consent, disclosure of abnormal results if screening is pursued, and recommended level of intervention by investigators. Furthermore, understanding the ways in which comorbid cognitive dysfunction and cancer impact both cancer and non-cancer-related outcomes is essential in guiding treatment decisions. In the following article, we will discuss what is presently known of the interactions of pre-existing cognitive impairment and delirium with cancer. We will also discuss identified deficits in our knowledge base, and propose ways in which innovative research may address these gaps.

Risk of Pre-and Post-Operative Delirium and the Delirium Elderly At Risk (DEAR) Tool in Hip Fracture Patients

BACKGROUND AND PURPOSE

Delirium is common after hip fracture. Previous work has shown that a simple delirium risk factor tool, the Delirium Elderly At Risk instrument (DEAR), has a high inter-rater reliability in this population. Little research has looked at the ability of risk factor screening tools to identify patients at high risk of pre-operative delirium. This study investigates the ability of the DEAR to identify patients at high risk of pre-operative delirium, as well as reporting its performance in a post-operative validation sample. Associations between delirium risk factors and pre-operative delirium are explored.

METHODS

This prospective cohort study took place on an orthopedic in-patient service at a University-affiliated tertiary care hospital. Patients aged 65 and older who were admitted for surgical repair of hip fracture (N = 283) were assessed pre-operatively for 5 delirium risk factors (cognitive impairment, sensory impairment, functional dependence, substance use, age) using the DEAR. Patients were assessed for delirium using the Mini-Mental State Examination and the Confusion Assessment Method pre-operatively and on post-operative days 1, 3 and 5. Characteristics of patients who developed delirium were compared with the characteristics of those who did not.

RESULTS

Delirium was present in 58% (95% CI = 52-63%) of patients pre-operatively and 42% (95% CI = 36-48%) post-operatively. Individually, sensory impairment (χ(2) = 21.7, p = .0001), functional dependence (χ(2) = 24.1, p = .0001), cognitive impairment (χ(2) = 55.5, p = .0001) and substance use (χ(2) = 7.5, p = .007) were significantly associated with pre-operative delirium, as was wait-time for surgery (t = 3.1, p = .003) and length of stay (t = 2.8, p =.03). In multivariate modeling, the strongest association with pre-operative delirium was cognitive impairment.

CONCLUSIONS

The DEAR, a simple, delirium risk factor screening tool, can be used to identify hip fracture patients at risk of both pre-operative and post-operative delirium, which may allow targeted implementation of delirium prevention strategies.

Predicting delirium: a review of risk-stratification models

BACKGROUND

Delirium is a common condition in hospitalized patients and is associated with multiple adverse outcomes. There is increasing evidence to support interventions that prevent delirium, so the identification of patients at high risk is of significant clinical value. Numerous risk factors have been identified, including both premorbid patient characteristics and acute precipitants. Despite this, predicting the occurrence of delirium remains a clinical challenge.

OBJECTIVE

This article reviews studies of validated risk-stratification models for delirium. We discuss possible barriers to use of these models and future directions for research.

METHODS

A comprehensive review of the literature was completed using PubMed and Embase. The resulting citations were filtered in a structured process. Inclusion criteria were original research, adult medical inpatient population and presence of a validation group in the study design.

RESULTS

Ten cohort studies met inclusion criteria. The quality of the studies was moderate to good. All studies proposed models using clinical data to predict the risk of patients' developing delirium.

CONCLUSION

The most common risk factors identified were preexisting cognitive impairment, medical comorbidity, elevated Blood Urea Nitrogen, and impairment in activities of daily living. While multiple validated predictive models exist, there is substantial heterogeneity between models, and only one replication study has been performed. In addition, difficulties in implementation may be a barrier to broader use of these models. There is limited support for an accurate and reliable tool to predict inpatient delirium. Further research is needed in this clinically important area.

Delirium diagnosis, screening and management

Purpose of review

Our review focuses on recent developments across many settings regarding the diagnosis, screening and management of delirium, so as to inform these aspects in the context of palliative and supportive care.

Recent findings

Delirium diagnostic criteria have been updated in the long-awaited Diagnostic Statistical Manual of Mental Disorders, fifth edition. Studies suggest that poor recognition of delirium relates to its clinical characteristics, inadequate interprofessional communication and lack of systematic screening. Validation studies are published for cognitive and observational tools to screen for delirium. Formal guidelines for delirium screening and management have been rigorously developed for intensive care, and may serve as a model for other settings. Given that palliative sedation is often required for the management of refractory delirium at the end of life, a version of the Richmond Agitation-Sedation Scale, modified for palliative care, has undergone preliminary validation.

Summary

Although formal systematic delirium screening with brief but sensitive tools is strongly advocated for patients in palliative and supportive care, it requires critical evaluation in terms of clinical outcomes, including patient comfort. Randomized controlled trials are needed to inform the development of guidelines for the management of delirium in this setting.

Recursive partitioning analysis of lymph node ratio in breast cancer patients

Lymph node ratio (LNR) is a powerful prognostic factor for breast cancer. We conducted a recursive partitioning analysis (RPA) of the LNR to identify the prognostic risk groups in breast cancer patients. Records of newly diagnosed breast cancer patients between 2002 and 2006 were searched in the Taiwan Cancer Database. The end of follow-up was December 31, 2009. We excluded patients with distant metastases, inflammatory breast cancer, survival <1 month, no mastectomy, or missing lymph node status. Primary outcome was 5-year overall survival (OS). For univariate significant predictors, RPA were used to determine the risk groups. Among the 11,349 eligible patients, we identified 4 prognostic factors (including LNR) for survival, resulting in 8 terminal nodes. The LNR cutoffs were 0.038, 0.259, and 0.738, which divided LNR into 4 categories: very low (LNR ≤ 0.038), low (0.038 < LNR ≤ 0.259), moderate (0.259 < LNR ≤ 0.738), and high (0.738 < LNR). Then, 4 risk groups were determined as follows: Class 1 (very low risk, 8,265 patients), Class 2 (low risk, 1,901 patients), Class 3 (moderate risk, 274 patients), and Class 4 (high risk, 900 patients). The 5-year OS for Class 1, 2, 3, and 4 were 93.2%, 83.1%, 72.3%, and 56.9%, respectively (P< 0.001). The hazard ratio of death was 2.70, 4.52, and 8.59 (95% confidence interval 2.32-3.13, 3.49-5.86, and 7.48-9.88, respectively) times for Class 2, 3, and 4 compared with Class 1 (P < 0.001). In conclusion, we identified the optimal cutoff LNR values based on RPA and determined the related risk groups, which successfully predict 5-year OS in breast cancer patients.

Performance and agreement of risk stratification instruments for postoperative delirium in persons aged 50 years or older

Several risk stratification instruments for postoperative delirium in older people have been developed because early interventions may prevent delirium. We investigated the performance and agreement of nine commonly used risk stratification instruments in an independent validation cohort of consecutive elective and emergency surgical patients aged ≥50 years with ≥1 risk factor for postoperative delirium. Data was collected prospectively. Delirium was diagnosed according to DSM-IV-TR criteria. The observed incidence of postoperative delirium was calculated per risk score per risk stratification instrument. In addition, the risk stratification instruments were compared in terms of area under the receiver operating characteristic (ROC) curve (AUC), and positive and negative predictive value. Finally, the positive agreement between the risk stratification instruments was calculated. When data required for an exact implementation of the original risk stratification instruments was not available, we used alternative data that was comparable. The study population included 292 patients: 60% men; mean age (SD), 66 (8) years; 90% elective surgery. The incidence of postoperative delirium was 9%. The maximum observed incidence per risk score was 50% (95%CI, 15–85%); for eight risk stratification instruments, the maximum observed incidence per risk score was ≤25%. The AUC (95%CI) for the risk stratification instruments varied between 0.50 (0.36–0.64) and 0.66 (0.48–0.83). No AUC was statistically significant from 0.50 (p≥0.11). Positive predictive values of the risk stratification instruments varied between 0–25%, negative predictive values between 89–95%. Positive agreement varied between 0–66%. No risk stratification instrument showed clearly superior performance. In conclusion, in this independent validation cohort, the performance and agreement of commonly used risk stratification instruments for postoperative delirium was poor. Although some caution is needed because the risk stratification instruments were not implemented exactly as described in the original studies, we think that their usefulness in clinical practice can be questioned.

An outbreak of Mycobacterium tuberculosis infection associated with acupuncture in a private clinic of Zhejiang Province, China, 2012

BACKGROUND

Acupuncture carries the potential risk of transmission of pathogenic microorganisms from the environment to the patient, and from one patient to another. An outbreak of tuberculosis at a private clinic in eastern China was investigated to identify the source of infection, mode of transmission, and risk factors for infection.

METHODS

A probable case was one who had the onset of unexplained pain, swelling, or abscess in the area of invasive treatment between January 1, 2011 and February 23, 2012. A confirmed case was a probable case with positive laboratory test results for Mycobacterium tuberculosis. Patient history and the frequency of invasive treatment were compared between 56 probable and confirmed cases and 98 controls in a case-control study.

RESULTS

Fifty-six of 2561 patients (2.2%) who had visited the clinic developed tuberculosis. The odds ratio (OR) of M. tuberculosis infection increased with the frequency of clinic visits (Chi-square for trend=28.943, p=0.000). Multivariate analysis showed that the frequency of acupuncture (Chi-square=24.258, adjusted p-value=0.000) and sharing acupuncture needles (Chi-square=8.936, adjusted p-value=0.003) were risk factors for M. tuberculosis infection. Thirty-two pus sample and nine sputum sample cultures were M. tuberculosis-positive.

CONCLUSIONS

This outbreak was caused by acupuncture and was transmitted through sharing acupuncture needles contaminated with M. tuberculosis.