BACKGROUND: Postoperative infections remain a crucial challenge in health care, resulting in high morbidity, mortality, and costs. Accurate identification and labeling of patients with postoperative bacterial infections is crucial for developing prediction models, validating biomarkers, and implementing surveillance systems in clinical practice.
OBJECTIVE: This scoping review aimed to explore methods for identifying patients with postoperative infections using electronic health record (EHR) data to go beyond the reference standard of manual chart review.
METHODS: We performed a systematic search strategy across PubMed, Embase, Web of Science (Core Collection), the Cochrane Library, and Emcare (Ovid), targeting studies addressing the prediction and fully automated surveillance (ie, without manual check) of diverse bacterial infections in the postoperative setting. For prediction modeling studies, we assessed the labeling methods used, categorizing them as either manual or automated. We evaluated the different types of EHR data needed for the surveillance and labeling of postoperative infections, as well as the performance of fully automated surveillance systems compared with manual chart review.
RESULTS: We identified 75 different methods and definitions used to identify patients with postoperative infections in studies published between 2003 and 2023. Manual labeling was the predominant method in prediction modeling research, 65% (49/75) of the identified methods use structured data, and 45% (34/75) use free text and clinical notes as one of their data sources. Fully automated surveillance systems should be used with caution because the reported positive predictive values are between 0.31 and 0.76.
CONCLUSIONS: There is currently no evidence to support fully automated labeling and identification of patients with infections based solely on structured EHR data. Future research should focus on defining uniform definitions, as well as prioritizing the development of more scalable, automated methods for infection detection using structured EHR data.

BACKGROUND: Acute exacerbations of chronic obstructive pulmonary disease (AECOPD) are associated with high mortality, morbidity, and poor quality of life and constitute a substantial burden to patients and health care systems. New approaches to prevent or reduce the severity of AECOPD are urgently needed. Internationally, this has prompted increased interest in the potential of remote patient monitoring (RPM) and digital medicine. RPM refers to the direct transmission of patient-reported outcomes, physiological, and functional data, including heart rate, weight, blood pressure, oxygen saturation, physical activity, and lung function (spirometry), directly to health care professionals through automation, web-based data entry, or phone-based data entry. Machine learning has the potential to enhance RPM in chronic obstructive pulmonary disease by increasing the accuracy and precision of AECOPD prediction systems.
OBJECTIVE: This study aimed to conduct a dual systematic review. The first review focuses on randomized controlled trials where RPM was used as an intervention to treat or improve AECOPD. The second review examines studies that combined machine learning with RPM to predict AECOPD. We review the evidence and concepts behind RPM and machine learning and discuss the strengths, limitations, and clinical use of available systems. We have generated a list of recommendations needed to deliver patient and health care system benefits.
METHODS: A comprehensive search strategy, encompassing the Scopus and Web of Science databases, was used to identify relevant studies. A total of 2 independent reviewers (HMGG and CM) conducted study selection, data extraction, and quality assessment, with discrepancies resolved through consensus. Data synthesis involved evidence assessment using a Critical Appraisal Skills Programme checklist and a narrative synthesis. Reporting followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.
RESULTS: These narrative syntheses suggest that 57% (16/28) of the randomized controlled trials for RPM interventions fail to achieve the required level of evidence for better outcomes in AECOPD. However, the integration of machine learning into RPM demonstrates promise for increasing the predictive accuracy of AECOPD and, therefore, early intervention.
CONCLUSIONS: This review suggests a transition toward the integration of machine learning into RPM for predicting AECOPD. We discuss particular RPM indices that have the potential to improve AECOPD prediction and highlight research gaps concerning patient factors and the maintained adoption of RPM. Furthermore, we emphasize the importance of a more comprehensive examination of patient and health care burdens associated with RPM, along with the development of practical solutions.

暂无摘要。

Caudal type homeobox transcription factor 2 (CDX2) is a gastrointestinal cancer biomarker that regulates epithelial development and differentiation. Absence or low levels of CDX2 have been associated with poor prognosis and proposed as a chemotherapy response predictor. Tumour tissue samples from 668 patients with stage I-IV colorectal cancer were stained for CDX2 and stratified into two subgroups according to expression levels. Statistical tests were used to evaluate CDX2\'s relationship with survival and chemotherapy response. Of 646 samples successfully stained, 51 (7.9%) had low CDX2 levels, and 595 (92.1%) had high levels. Low CDX2 staining was associated with poor differentiation and the presence of lymphovascular or perineural invasion and was more common in colon and right-sided tumours. Overall survival (p < 0.001) and disease-free survival (p = 0.009) were reduced in patients with low CDX2 expression. Multivariable analysis validated CDX2 as an independent poor prognostic factor after excluding confounding variables. There was no statistically significant improvement in survival with adjuvant chemotherapy in stage II colon cancer (p = 0.11). In the rectal cohort, there was no relationship between CDX2 levels and therapy response. While confirming the prognostic utility of CDX2 in colorectal cancer, our study highlights that larger studies are required to confirm its utility as a predictive chemotherapy biomarker, especially in left-sided and rectal cancers.

Postacute sequelae of COVID-19 (PASC), also known as long COVID, is a broad grouping of a range of long-term symptoms following acute COVID-19. These symptoms can occur across a range of biological systems, leading to challenges in determining risk factors for PASC and the causal etiology of this disorder. An understanding of characteristics that are predictive of future PASC is valuable, as this can inform the identification of high-risk individuals and future preventative efforts. However, current knowledge regarding PASC risk factors is limited.
Using a sample of 55,257 patients (at a ratio of 1 patient with PASC to 4 matched controls) from the National COVID Cohort Collaborative, as part of the National Institutes of Health Long COVID Computational Challenge, we sought to predict individual risk of PASC diagnosis from a curated set of clinically informed covariates. The National COVID Cohort Collaborative includes electronic health records for more than 22 million patients from 84 sites across the United States.
We predicted individual PASC status, given covariate information, using Super Learner (an ensemble machine learning algorithm also known as stacking) to learn the optimal combination of gradient boosting and random forest algorithms to maximize the area under the receiver operator curve. We evaluated variable importance (Shapley values) based on 3 levels: individual features, temporal windows, and clinical domains. We externally validated these findings using a holdout set of randomly selected study sites.
We were able to predict individual PASC diagnoses accurately (area under the curve 0.874). The individual features of the length of observation period, number of health care interactions during acute COVID-19, and viral lower respiratory infection were the most predictive of subsequent PASC diagnosis. Temporally, we found that baseline characteristics were the most predictive of future PASC diagnosis, compared with characteristics immediately before, during, or after acute COVID-19. We found that the clinical domains of health care use, demographics or anthropometry, and respiratory factors were the most predictive of PASC diagnosis.
The methods outlined here provide an open-source, applied example of using Super Learner to predict PASC status using electronic health record data, which can be replicated across a variety of settings. Across individual predictors and clinical domains, we consistently found that factors related to health care use were the strongest predictors of PASC diagnosis. This indicates that any observational studies using PASC diagnosis as a primary outcome must rigorously account for heterogeneous health care use. Our temporal findings support the hypothesis that clinicians may be able to accurately assess the risk of PASC in patients before acute COVID-19 diagnosis, which could improve early interventions and preventive care. Our findings also highlight the importance of respiratory characteristics in PASC risk assessment.
RR2-10.1101/2023.07.27.23293272.

BACKGROUND: Telecare and telehealth are important care-at-home services used to support individuals to live more independently at home. Historically, these technologies have reactively responded to issues. However, there has been a recent drive to make better use of the data from these services to facilitate more proactive and predictive care.
OBJECTIVE: This review seeks to explore the ways in which predictive data analytics techniques have been applied in telecare and telehealth in at-home settings.
METHODS: The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist was adhered to alongside Arksey and O\'Malley\'s methodological framework. English language papers published in MEDLINE, Embase, and Social Science Premium Collection between 2012 and 2022 were considered and results were screened against inclusion or exclusion criteria.
RESULTS: In total, 86 papers were included in this review. The types of analytics featuring in this review can be categorized as anomaly detection (n=21), diagnosis (n=32), prediction (n=22), and activity recognition (n=11). The most common health conditions represented were Parkinson disease (n=12) and cardiovascular conditions (n=11). The main findings include: a lack of use of routinely collected data; a dominance of diagnostic tools; and barriers and opportunities that exist, such as including patient-reported outcomes, for future predictive analytics in telecare and telehealth.
CONCLUSIONS: All papers in this review were small-scale pilots and, as such, future research should seek to apply these predictive techniques into larger trials. Additionally, further integration of routinely collected care data and patient-reported outcomes into predictive models in telecare and telehealth offer significant opportunities to improve the analytics being performed and should be explored further. Data sets used must be of suitable size and diversity, ensuring that models are generalizable to a wider population and can be appropriately trained, validated, and tested.

BACKGROUND: Diabetic ketoacidosis (DKA) is the leading cause of morbidity and mortality in pediatric type 1 diabetes (T1D), occurring in approximately 20% of patients, with an economic cost of $5.1 billion/year in the United States. Despite multiple risk factors for postdiagnosis DKA, there is still a need for explainable, clinic-ready models that accurately predict DKA hospitalization in established patients with pediatric T1D.
OBJECTIVE: We aimed to develop an interpretable machine learning model to predict the risk of postdiagnosis DKA hospitalization in children with T1D using routinely collected time-series of electronic health record (EHR) data.
METHODS: We conducted a retrospective case-control study using EHR data from 1787 patients from among 3794 patients with T1D treated at a large tertiary care US pediatric health system from January 2010 to June 2018. We trained a state-of-the-art; explainable, gradient-boosted ensemble (XGBoost) of decision trees with 44 regularly collected EHR features to predict postdiagnosis DKA. We measured the model\'s predictive performance using the area under the receiver operating characteristic curve-weighted F1-score, weighted precision, and recall, in a 5-fold cross-validation setting. We analyzed Shapley values to interpret the learned model and gain insight into its predictions.
RESULTS: Our model distinguished the cohort that develops DKA postdiagnosis from the one that does not (P<.001). It predicted postdiagnosis DKA risk with an area under the receiver operating characteristic curve of 0.80 (SD 0.04), a weighted F1-score of 0.78 (SD 0.04), and a weighted precision and recall of 0.83 (SD 0.03) and 0.76 (SD 0.05) respectively, using a relatively short history of data from routine clinic follow-ups post diagnosis. On analyzing Shapley values of the model output, we identified key risk factors predicting postdiagnosis DKA both at the cohort and individual levels. We observed sharp changes in postdiagnosis DKA risk with respect to 2 key features (diabetes age and glycated hemoglobin at 12 months), yielding time intervals and glycated hemoglobin cutoffs for potential intervention. By clustering model-generated Shapley values, we automatically stratified the cohort into 3 groups with 5%, 20%, and 48% risk of postdiagnosis DKA.
CONCLUSIONS: We have built an explainable, predictive, machine learning model with potential for integration into clinical workflow. The model risk-stratifies patients with pediatric T1D and identifies patients with the highest postdiagnosis DKA risk using limited follow-up data starting from the time of diagnosis. The model identifies key time points and risk factors to direct clinical interventions at both the individual and cohort levels. Further research with data from multiple hospital systems can help us assess how well our model generalizes to other populations. The clinical importance of our work is that the model can predict patients most at risk for postdiagnosis DKA and identify preventive interventions based on mitigation of individualized risk factors.

The aetiological mechanism of gestational diabetes mellitus (GDM) has still not been fully understood. The aim of this study was to explore the associations between functional genetic variants screened from a genome-wide association study (GWAS) and GDM risk among 554 GDM patients and 641 healthy controls in China. Functional analysis of single nucleotide polymorphisms (SNPs) positively associated with GDM was further performed. Univariate regression and multivariate logistic regression analyses were used to screen clinical risk factors, and a predictive nomogram model was established. After adjusting for age and prepregnancy BMI, rs9283638 was significantly associated with GDM susceptibility (P < 0.05). Moreover, an obvious interaction between rs9283638 and clinical variables was detected (Pinteraction < 0.05). Functional analysis confirmed that rs9283638 can regulate not only target gene transcription factor binding, but it also regulates the mRNA levels of SAMD7 (P < 0.05). The nomogram model constructed with the factors of age, FPG, 1hPG, 2hPG, HbA1c, TG and rs9283638 revealed an area under the ROC curve of 0.920 (95% CI 0.902-0.939). Decision curve analysis (DCA) suggested that the model had greater net clinical benefit. Conclusively, genetic variants can alter women\'s susceptibility to GDM by affecting the transcription of target genes. The predictive nomogram model constructed based on genetic and clinical variables can effectively distinguish individuals with different GDM risk factors.

BACKGROUND: Sarcomatoid urothelial carcinoma (SUC) is a rare and highly malignant form of bladder cancer with a poor prognosis. Currently, there is limited information on the imaging features of bladder SUC and reliable indicators for distinguishing it from conventional urothelial carcinoma (CUC). The objective of our study was to identify the unique imaging characteristics of bladder SUC and determine factors that aid in its differential diagnosis.
METHODS: This retrospective study enrolled 22 participants with bladder SUC and 61 participants with CUC. The clinical, pathologic, and CT/MRI data from both groups were recorded, and a comparison was conducted using univariate analysis and multinomial logistic regression for distinguishing SUC from CUC.
RESULTS: The majority of SUCs were located in the trigone of the bladder and exhibited large tumor size, irregular shape, low ADC values, Vesical Imaging-Reporting and Data System (VI-RADS) score ≥ 4, the presence of necrosis, and an invasive nature. Univariate analysis revealed significant differences in terms of tumor location, shape, the maximum long-axis diameter (LAD), the short-axis diameter (SAD), ADC-value, VI-RADS scores, necrosis, extravesical extension (EVE), pelvic peritoneal spread (PPS), and hydronephrosis/ureteral effusion (p < .001 ~ p = .037) between SUCs and CUCs. Multinomial logistic regression found that only SAD (p = .014) and necrosis (p = .003) emerged as independent predictors for differentiating between SUC and CUC. The model based on these two factors achieved an area under curve (AUC) of 0.849 in ROC curve analysis.
CONCLUSIONS: Bladder SUC demonstrates several distinct imaging features, including a high incidence of trigone involvement, large tumor size, and obvious invasiveness accompanied by necrosis. A bladder tumor with a large SAD and evidence of necrosis is more likely to be SUC rather than CUC.

BACKGROUND: The role that preoperative Satisfaction with Breast plays in a patient\'s postoperative course after postmastectomy breast reconstruction (PMBR) is not understood. The aim of this study is to understand the impact of the preoperative score on postoperative outcome as an independent variable.
METHODS: We examined patients who underwent PMBR between 2017 and 2021 and who completed the BREAST-Q Satisfaction with Breasts at 1 year postoperatively. Two multiple linear regression models (Model 1 with the preoperative Satisfaction with Breasts score and Model 2 without the preoperative score), likelihood ratio tests, simple t-statistics, and sample patient dataset to predict the 1 year score were performed. Multiple imputation was used to account for missing preoperative scores.
RESULTS: Overall, 2324 patients were included. Model 1 showed that the preoperative score is significantly associated with the postoperative score (β = 0.09, 95% confidence interval 0.04-0.14; p < 0.001). Comparing Model 1 and Model 2 demonstrated that including preoperative Satisfaction with Breasts in a regression significantly improves model fit (test statistic = 10.04; p = 0.0021). Using the absolute value of the t-statistics as a measure of variable importance in linear regression, the importance of the preoperative score was quantified as 3.39-more important than neoadjuvant radiation, mastectomy weight, body mass index, bilateral prophylactic mastectomy, and race, but less than adjuvant radiation, reconstruction type, and psychiatric diagnoses.
CONCLUSIONS: Preoperative Satisfaction with Breasts scores are an important independent predictor of postoperative satisfaction after PMBR. Just as vital sign and work-up are carefully documented before surgery, preoperative scores should be collected to pre-emptively gauge patients\' satisfaction and optimize postoperative outcomes.