Prognostic factors and clinical nomogram for in-hospital mortality in traumatic brain injury

BACKGROUND

Traumatic brain injury (TBI) is a major cause of death and functional disability in the general population. The nomogram is a clinical prediction tool that has been researched for a wide range of medical conditions. The purpose of this study was to identify prognostic factors associated with in-hospital mortality. The secondary objective was to develop a clinical nomogram for TBI patients' in-hospital mortality based on prognostic factors.

METHODS

A retrospective cohort study was conducted to analyze 14,075 TBI patients who were admitted to a tertiary hospital in southern Thailand. The total dataset was divided into the training and validation datasets. Several clinical characteristics and imaging findings were analyzed for in-hospital mortality in both univariate and multivariable analyses using the training dataset. Based on binary logistic regression, the nomogram was developed and internally validated using the final predictive model. Therefore, the predictive performances of the nomogram were estimated by the validation dataset.

RESULTS

Prognostic factors associated with in-hospital mortality comprised age, hypotension, antiplatelet, Glasgow coma scale score, pupillary light reflex, basilar skull fracture, acute subdural hematoma, subarachnoid hemorrhage, midline shift, and basal cistern obliteration that were used for building nomogram. The predictive performance of the nomogram was estimated by the training dataset; the area under the receiver operating characteristic curve (AUC) was 0.981. In addition, the AUCs of bootstrapping and cross-validation methods were 0.980 and 0.981, respectively. For the temporal validation with an unseen dataset, the sensitivity, specificity, accuracy, and AUC of the nomogram were 0.90, 0.88, 0.88, and 0.89, respectively.

CONCLUSION

A nomogram developed from prognostic factors had excellent performance; thus, the tool had the potential to serve as a screening tool for prognostication in TBI patients. Furthermore, future research should involve geographic validation to examine the predictive performances of the clinical prediction tool.

Clinical prediction tool to identify children at risk of pulmonary embolism

INTRODUCTION

The diagnosis of pediatric pulmonary embolism (PE) is often delayed due to non-specific symptoms, and clinical prediction tools designed for adults are unsuitable for children. This study aimed to create a PE predictive model and to evaluate the reported tools in the Thai pediatric population.

MATERIALS AND METHODS

A multi-center retrospective study from 4 university hospitals included children ≤18 years of age undergoing computed tomography pulmonary angiogram from 2000 to 2020 with the suspicion of PE. Patients' clinical presentations and risk factors of venous thromboembolism (VTE) were compared between the PE-positive and PE-negative groups. Significant risk factors from univariate and multivariate logistic regression were included to create a clinical prediction tool. The performance of the model was demonstrated by sensitivity, specificity, area under the curve (AUC), Hosmer Lemeshow test, ratio of observed and expected outcomes and bootstrapping.

RESULTS

Of the 104 patients included, 43 (41.3 %) were grouped as PE-positive and 61 (58.7 %) as PE-negative. Five parameters, including congenital heart disease/pulmonary surgery, known thrombophilia, previous VTE, nephrotic syndrome and chest pain showed significant differences between the two groups. Score ≥ 2 yielded a 74.4 % sensitivity and a 75.4 % specificity with an AUC of the model of 0.809. The model performance and validation results were within satisfactory ranges.

CONCLUSION

The study created a clinical prediction tool indicating the likelihood of PE among Thai children. A score ≥2 was suggestive of PE.

The impact of a clinical prediction tool (BuRN-Tool) for child maltreatment on social care outcomes for children attending hospital with a burn or scald injury

Burns are common childhood injuries and 10-20% are associated with maltreatment. This prospective before/after study investigated the impact of introducing the BuRN-Tool (a child maltreatment clinical prediction tool), on actions taken by children's social care department (CSC). Before introduction (pre-intervention): we collected standardised data on cause and characteristics of burns, in four regional hospitals. A BuRN-Tool-score was calculated retrospectively pre-intervention and by the attending clinician post-intervention. CSC involvement and actions taken relative to BuRN-Tool-score were compared pre- and post-BuRN-Tool. Data were collected for 1688 children from 17 local authorities. The percentage that received a CSC action decreased post-BuRN-Tool (pre: 58.0%, 51/88; post: 37.5%, 33/88, p = 0.007). A greater percentage of cases with a BuRN-Tool-score of ≥ 3 had a CSC action, than those with a BuRN-Tool-score 3, pre-intervention (≥3 70.0%, 35/50; = 0.04) and post-intervention (≥3 50.0%, 21/42; = 0.01). Children with a BuRN-Tool-score ≥ 3 but no contact/referral recorded by CSC for the burn, and those who had a contact/referral but no action taken, were significantly more likely than those scoring 3 to have new CSC involvement within six months following the burn. The BuRN-Tool-score ≥ 3 has the potential to alert clinicians to maltreatment concerns.

Use of machine learning in pediatric surgical clinical prediction tools: A systematic review

PURPOSE

Clinical prediction tools (CPTs) are decision-making instruments utilizing patient data to predict specific clinical outcomes, risk-stratify patients, or suggest personalized diagnostic or therapeutic options. Recent advancements in artificial intelligence have resulted in a proliferation of CPTs created using machine learning (ML)-yet the clinical applicability of ML-based CPTs and their validation in clinical settings remain unclear. This systematic review aims to compare the validity and clinical efficacy of ML-based to traditional CPTs in pediatric surgery.

METHODS

Nine databases were searched from 2000 until July 9, 2021 to retrieve articles reporting on CPTs and ML for pediatric surgical conditions. PRISMA standards were followed, and screening was performed by two independent reviewers in Rayyan, with a third reviewer resolving conflicts. Risk of bias was assessed using the PROBAST.

RESULTS

Out of 8300 studies, 48 met the inclusion criteria. The most represented surgical specialties were pediatric general (14), neurosurgery (13) and cardiac surgery (12). Prognostic (26) CPTs were the most represented type of surgical pediatric CPTs followed by diagnostic (10), interventional (9), and risk stratifying (2). One study included a CPT for diagnostic, interventional and prognostic purposes. 81% of studies compared their CPT to ML-based CPTs, statistical CPTs, or the unaided clinician, but lacked external validation and/or evidence of clinical implementation.

CONCLUSIONS

While most studies claim significant potential improvements by incorporating ML-based CPTs in pediatric surgical decision-making, both external validation and clinical application remains limited. Further studies must focus on validating existing instruments or developing validated tools, and incorporating them in the clinical workflow.

TYPE OF STUDY

Systematic Review LEVEL OF EVIDENCE: Level III.

Development and validation of a point-of-care clinical risk score to predict surgical site infection following open spinal fusion

Background

Surgical site infection (SSI) after open spine surgery increases healthcare costs and patient morbidity. Predictive analytics using large databases can be used to develop prediction tools to aid surgeons in identifying high-risk patients and strategies for optimization. The purpose of this study was to develop and validate an SSI risk-assessment score for patients undergoing open spine surgery.

Methods

The Premier Healthcare Database of adult open spine surgery patients (n = 157,664; 2,650 SSIs) was used to create an SSI risk scoring system using mixed effects logistic regression modeling. Full and reduced multilevel logistic regression models were developed using patient, surgery or facility predictors. The full model used 38 predictors and the reduced used 16 predictors. The resulting risk score was the sum of points assigned to 16 predictors.

Results

The reduced model showed good discriminatory capability (C-statistic = 0.75) and good fit of the model ([Pearson Chi-square/DF] = 0.90, CAIC=25,517) compared to the full model (C-statistic = 0.75, [Pearson Chi-square/DF] =0.90, CAIC=25,578). The risk scoring system, based on the reduced model, included the following: female (5 points), hypertension (4), blood disorder (8), peripheral vascular disease (9), chronic pulmonary disease (6), rheumatic disease (16), obesity (12), nicotine dependence (5), Charlson Comorbidity Index (2 per point), revision surgery (14), number of ICD-10 procedures (1 per procedure), operative time (1 per hour), and emergency/urgent surgery (12). A final risk score as the sum of the points for each surgery was validated using a 1,000-surgery random hold-out (independent from the study cohort) sample (C-statistic = 0.77).

Conclusions

The resulting SSI risk score composed of readily obtainable clinical information could serve as a strong prediction tool for SSI in preoperative settings when open spine surgery is considered.

Potential impact of the validated Predicting Abusive Head Trauma (PredAHT) clinical prediction tool: A clinical vignette study

BACKGROUND

The validated Predicting Abusive Head Trauma (PredAHT) tool estimates the probability of abusive head trauma (AHT) in children <3 years old with intracranial injury.

OBJECTIVE

To explore the impact of PredAHT on clinicians' AHT probability estimates and child protection (CP) actions, and assess inter-rater agreement between their estimates and between their CP actions, before and after PredAHT.

PARTICIPANTS AND SETTING

Twenty-nine clinicians from different specialties, at teaching and community hospitals.

METHODS

Clinicians estimated the probability of AHT and indicated their CP actions in six clinical vignettes. One vignette described a child with AHT, another described a child with non-AHT, and four represented "gray" cases, where the diagnosis was uncertain. Clinicians calculated the PredAHT score, and reported whether this altered their estimate/actions. The 'think-aloud' method was used to capture the reasoning behind their responses. Analysis included linear modelling, linear mixed-effects modelling, chi-square tests, Fisher's exact tests, intraclass correlation, Gwet's AC₁ coefficient and thematic analysis.

RESULTS

Overall, PredAHT significantly influenced clinicians' probability estimates in all vignettes (p < 0.001), although the impact on individual clinicians varied. However, the influence of PredAHT on clinicians' CP actions was limited; after using PredAHT, 9/29 clinicians changed their CP actions in only 11/174 instances. Clinicians' AHT probability estimates and CP actions varied somewhat both before and after PredAHT. Qualitative data suggested that PredAHT may increase clinicians' confidence in their decisions when considered alongside other associated clinical, historical and social factors.

CONCLUSIONS

PredAHT significantly influenced clinicians' AHT probability estimates, but had minimal impact on their CP actions.

Acceptability of the Predicting Abusive Head Trauma (PredAHT) clinical prediction tool: A qualitative study with child protection professionals

The validated Predicting Abusive Head Trauma (PredAHT) tool estimates the probability of abusive head trauma (AHT) based on combinations of six clinical features: head/neck bruising; apnea; seizures; rib/long-bone fractures; retinal hemorrhages. We aimed to determine the acceptability of PredAHT to child protection professionals. We conducted qualitative semi-structured interviews with 56 participants: clinicians (25), child protection social workers (10), legal practitioners (9, including 4 judges), police officers (8), and pathologists (4), purposively sampled across southwest United Kingdom. Interviews were recorded, transcribed and imported into NVivo for thematic analysis (38% double-coded). We explored participants' evaluations of PredAHT, their opinions about the optimal way to present the calculated probabilities, and their interpretation of probabilities in the context of suspected AHT. Clinicians, child protection social workers and police thought PredAHT would be beneficial as an objective adjunct to their professional judgment, to give them greater confidence in their decisions. Lawyers and pathologists appreciated its value for prompting multidisciplinary investigations, but were uncertain of its usefulness in court. Perceived disadvantages included: possible over-reliance and false reassurance from a low score. Interpretations regarding which percentages equate to 'low', 'medium' or 'high' likelihood of AHT varied; participants preferred a precise % probability over these general terms. Participants would use PredAHT with provisos: if they received multi-agency training to define accepted risk thresholds for consistent interpretation; with knowledge of its development; if it was accepted by colleagues. PredAHT may therefore increase professionals' confidence in their decision-making when investigating suspected AHT, but may be of less value in court.

Prediction of recurrent clostridium difficile infection at the bedside: the GEIH-CDI score

Recurrence of Clostridium difficile infection (CDI) has major consequences for both patients and the health system. The ability to predict which patients are at increased risk of recurrent CDI makes it possible to select candidates for treatment with new drugs and therapies (including fecal microbiota transplantation) that have proven to reduce the incidence of recurrence of CDI. Our objective was to develop a clinical prediction tool, the GEIH-CDI score, to determine the risk of recurrence of CDI. Predictors of recurrence of CDI were investigated using logistic regression in a prospective cohort of 274 patients diagnosed with CDI. The model was calibrated using the Hosmer-Lemeshow test. The tool comprises four factors: age (70-79 years and ≥80 years), history of CDI during the previous year, direct detection of toxin in stool, and persistence of diarrhea on the fifth day of treatment. The functioning of the GEIH-CDI score was validated in a prospective cohort of 183 patients. The area under the ROC curve was 0.72 (0.65-0.79). Application of the tool makes it possible to select patients at high risk (>50%) of recurrence and patients at low risk (<10%) of recurrence. GEIH-CDI score may be useful for clinicians treating patients with CDI.

Fetal Right Ventricular Prominence: Associated Postnatal Abnormalities and Coarctation Clinical Prediction Tool

Fetal right ventricular (RV) prominence is a known indicator of possible left-sided structural heart disease with a low positive predictive value for aortic coarctation. There is a paucity of data on identifying which fetuses with RV prominence will have postnatal arch obstruction. Our study objectives were to create a clinical prediction tool for coarctation and to describe the diagnostic outcomes of our cohort with fetal RV prominence. We performed a retrospective review of patients referred with fetal RV prominence from January 2009 to October 2015. Recorded fetal echocardiographic variables included gestational age, semilunar and atrioventricular valve dimensions, left and right ventricular mid-cavitary dimensions, foramen ovale and aortic arch flow direction, and isthmal diameter. Postnatal cardiac and non-cardiac diagnoses were documented. We performed descriptive analysis for postnatal outcomes and classification tree analysis to create a clinical prediction tool. Eighty-eight patients were reviewed; 58 (66%) had abnormal postnatal echocardiograms, 45 (51%) had left-sided lesions, including 26 (30%) with coarctation, and 6 (7%) had pulmonary hypertension. Our clinical prediction tool employs gestational age, RV mid-cavitary dimension z-score, and isthmal diameter z-score to predict coarctation with 85% accuracy, 95% confidence interval [75.3, 92.4%]. Our model correctly classified 45/54 non-coarctation and 19/21 coarctation cases, with 90% sensitivity and 83% specificity. Developing an accurate prediction tool for coarctation in cases of fetal RV prominence is an important first step in improving our management of these challenging cases.

Prediction of recurrent clostridium difficile infection at the bedside: the GEIH-CDI score

Recurrence of Clostridium difficile infection (CDI) has major consequences for both patients and the health system. The ability to predict which patients are at increased risk of recurrent CDI makes it possible to select candidates for treatment with new drugs and therapies (including fecal microbiota transplantation) that have proven to reduce the incidence of recurrence of CDI. Our objective was to develop a clinical prediction tool, the GEIH-CDI score, to determine the risk of recurrence of CDI. Predictors of recurrence of CDI were investigated using logistic regression in a prospective cohort of 274 patients diagnosed with CDI. The model was calibrated using the Hosmer-Lemeshow test. The tool comprises four factors: age (70-79 years and ≥80 years), history of CDI during the previous year, direct detection of toxin in stool, and persistence of diarrhea on the fifth day of treatment. The functioning of the GEIH-CDI score was validated in a prospective cohort of 183 patients. The area under the ROC curve was 0.72 (0.65-0.79). Application of the tool makes it possible to select patients at high risk (>50%) of recurrence and patients at low risk (<10%) of recurrence. GEIH-CDI score may be useful for clinicians treating patients with CDI.

Target-D: a stratified individually randomized controlled trial of the diamond clinical prediction tool to triage and target treatment for depressive symptoms in general practice: study protocol for a randomized controlled trial

BACKGROUND

Depression is a highly prevalent and costly disorder. Effective treatments are available but are not always delivered to the right person at the right time, with both under- and over-treatment a problem. Up to half the patients presenting to general practice report symptoms of depression, but general practitioners have no systematic way of efficiently identifying level of need and allocating treatment accordingly. Therefore, our team developed a new clinical prediction tool (CPT) to assist with this task. The CPT predicts depressive symptom severity in three months' time and based on these scores classifies individuals into three groups (minimal/mild, moderate, severe), then provides a matched treatment recommendation. This study aims to test whether using the CPT reduces depressive symptoms at three months compared with usual care.

METHODS

The Target-D study is an individually randomized controlled trial. Participants will be 1320 general practice patients with depressive symptoms who will be approached in the practice waiting room by a research assistant and invited to complete eligibility screening on an iPad. Eligible patients will provide informed consent and complete the CPT on a purpose-built website. A computer-generated allocation sequence stratified by practice and depressive symptom severity group, will randomly assign participants to intervention (treatment recommendation matched to predicted depressive symptom severity group) or comparison (usual care plus Target-D attention control) arms. Follow-up assessments will be completed online at three and 12 months. The primary outcome is depressive symptom severity at three months. Secondary outcomes include anxiety, mental health self-efficacy, quality of life, and cost-effectiveness. Intention-to-treat analyses will test for differences in outcome means between study arms overall and by depressive symptom severity group.

DISCUSSION

To our knowledge, this is the first depressive symptom stratification tool designed for primary care which takes a prognosis-based approach to provide a tailored treatment recommendation. If shown to be effective, this tool could be used to assist general practitioners to implement stepped mental-healthcare models and contribute to a more efficient and effective mental health system.

TRIAL REGISTRATION

Australian New Zealand Clinical Trials Registry (ANZCTR 12616000537459 ). Retrospectively registered on 27 April 2016. See Additional file 1 for trial registration data.