Performance of a Machine Learning Algorithm Using Electronic Health Record Data to Identify and Estimate Survival in a Longitudinal Cohort of Patients With Lung Cancer

A deep learning approach for overall survival prediction in lung cancer with missing values

BACKGROUND AND OBJECTIVE

In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges.

METHODS

We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time.

RESULTS

We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used.

CONCLUSIONS

The results show that our model not only outperforms the state-of-the-art's performance but also simplifies the analysis in the presence of missing data, by effectively eliminating the need to identify the most appropriate imputation strategy for predicting OS in NSCLC patients.

Prediction of prognosis in lung cancer using machine learning with inter-institutional generalizability: A multicenter cohort study (WJOG15121L: REAL-WIND)

OBJECTIVES

Predicting the prognosis of lung cancer is crucial for providing optimal medical care. However, a method to accurately predict the overall prognosis in patients with stage IV lung cancer, even with the use of machine learning, has not been established. Moreover, the inter-institutional generalizability of such algorithms remains unexplored. This study aimed to establish machine learning-based algorithms with inter-institutional generalizability to predict prognosis.

MATERIALS AND METHODS

This multicenter, retrospective, hospital-based cohort study included consecutive patients with stage IV lung cancer who were randomly categorized into the training and independent test cohorts with a 2:1 ratio, respectively. The primary metric to assess algorithm performance was the area under the receiver operating characteristic curve in the independent test cohort. To assess the inter-institutional generalizability of the algorithms, we investigated their ability to predict patient outcomes in the remaining facility after being trained using data from 15 other facilities.

RESULTS

Overall, 6,751 patients (median age, 70 years) were enrolled, and 1,515 (22 %) showed mutated epidermal growth factor receptor expression. The median overall survival was 16.6 (95 % confidence interval, 15.9-17.5) months. Algorithm performance metrics in the test cohort showed that the areas under the curves were 0.90 (95 % confidence interval, 0.88-0.91), 0.85 (0.84-0.87), 0.83 (0.81-0.85), and 0.85 (0.82-0.87) at 180, 360, 720, and 1,080 predicted survival days, respectively. The performance test of 16 algorithms for investigating inter-institutional generalizability showed median areas under the curves of 0.87 (range, 0.84-0.92), 0.84 (0.78-0.88), 0.84 (0.76-0.89), and 0.84 (0.75-0.90) at 180, 360, 720, and 1,080 days, respectively.

CONCLUSION

This study developed machine learning algorithms that could accurately predict the prognosis in patients with stage IV lung cancer with high inter-institutional generalizability. This can enhance the accuracy of prognosis prediction and support informed and shared decision-making in clinical settings.

MixEHR-SurG: A joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records

Survival models can help medical practitioners to evaluate the prognostic importance of clinical variables to patient outcomes such as mortality or hospital readmission and subsequently design personalized treatment regimes. Electronic Health Records (EHRs) hold the promise for large-scale survival analysis based on systematically recorded clinical features for each patient. However, existing survival models either do not scale to high dimensional and multi-modal EHR data or are difficult to interpret. In this study, we present a supervised topic model called MixEHR-SurG to simultaneously integrate heterogeneous EHR data and model survival hazard. Our contributions are three-folds: (1) integrating EHR topic inference with Cox proportional hazards likelihood; (2) integrating patient-specific topic hyperparameters using the PheCode concepts such that each topic can be identified with exactly one PheCode-associated phenotype; (3) multi-modal survival topic inference. This leads to a highly interpretable survival topic model that can infer PheCode-specific phenotype topics associated with patient mortality. We evaluated MixEHR-SurG using a simulated dataset and two real-world EHR datasets: the Quebec Congenital Heart Disease (CHD) data consisting of 8211 subjects with 75,187 outpatient claim records of 1767 unique ICD codes; the MIMIC-III consisting of 1458 subjects with multi-modal EHR records. Compared to the baselines, MixEHR-SurG achieved a superior dynamic AUROC for mortality prediction, with a mean AUROC score of 0.89 in the simulation dataset and a mean AUROC of 0.645 on the CHD dataset. Qualitatively, MixEHR-SurG associates severe cardiac conditions with high mortality risk among the CHD patients after the first heart failure hospitalization and critical brain injuries with increased mortality among the MIMIC-III patients after their ICU discharge. Together, the integration of the Cox proportional hazards model and EHR topic inference in MixEHR-SurG not only leads to competitive mortality prediction but also meaningful phenotype topics for in-depth survival analysis. The software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-SurG.

Current status of artificial intelligence methods for skin cancer survival analysis: a scoping review

Skin cancer mortality rates continue to rise, and survival analysis is increasingly needed to understand who is at risk and what interventions improve outcomes. However, current statistical methods are limited by inability to synthesize multiple data types, such as patient genetics, clinical history, demographics, and pathology and reveal significant multimodal relationships through predictive algorithms. Advances in computing power and data science enabled the rise of artificial intelligence (AI), which synthesizes vast amounts of data and applies algorithms that enable personalized diagnostic approaches. Here, we analyze AI methods used in skin cancer survival analysis, focusing on supervised learning, unsupervised learning, deep learning, and natural language processing. We illustrate strengths and weaknesses of these approaches with examples. Our PubMed search yielded 14 publications meeting inclusion criteria for this scoping review. Most publications focused on melanoma, particularly histopathologic interpretation with deep learning. Such concentration on a single type of skin cancer amid increasing focus on deep learning highlight growing areas for innovation; however, it also demonstrates opportunity for additional analysis that addresses other types of cutaneous malignancies and expands the scope of prognostication to combine both genetic, histopathologic, and clinical data. Moreover, researchers may leverage multiple AI methods for enhanced benefit in analyses. Expanding AI to this arena may enable improved survival analysis, targeted treatments, and outcomes.

A novel method leveraging time series data to improve subphenotyping and application in critically ill patients with COVID-19

Computational subphenotyping, a data-driven approach to understanding disease subtypes, is a prominent topic in medical research. Numerous ongoing studies are dedicated to developing advanced computational subphenotyping methods for cross-sectional data. However, the potential of time-series data has been underexplored until now. Here, we propose a Multivariate Levenshtein Distance (MLD) that can account for address correlation in multiple discrete features over time-series data. Our algorithm has two distinct components: it integrates an optimal threshold score to enhance the sensitivity in discriminating between pairs of instances, and the MLD itself. We have applied the proposed distance metrics on the k-means clustering algorithm to derive temporal subphenotypes from time-series data of biomarkers and treatment administrations from 1039 critically ill patients with COVID-19 and compare its effectiveness to standard methods. In conclusion, the Multivariate Levenshtein Distance metric is a novel method to quantify the distance from multiple discrete features over time-series data and demonstrates superior clustering performance among competing time-series distance metrics.

Quantitative patient graph analysis for transient ischemic attack risk factor distribution based on electronic medical records

A transient ischemic attack (TIA) affects millions of people worldwide. Although TIA risk factors have been identified individually, a systemic quantitative analysis of all health factors relevant to TIA using electronic medical records (EMR) remains lacking. This study employed a data-driven approach, leveraging hospital EMR data to create a TIA patient health factor graph. This graph consisted of 737 TIA and 737 control patient nodes, 740 health factor nodes, and over 33,000 relations between patients and factors. For all health factors in the graph, the connection delta ratios (CDRs) were determined and ranked, generating a quantitative distribution of TIA health factors. A literature review confirmed 56 risk factors in the distribution and unveiled a potential new risk factor "rhinosinusitis" for future validation. Moreover, the patient graph was visualized together with the TIA knowledge graph in the Unified Medical Language System. This integration enables clinicians to access and visualize patient data and international standard knowledge within a unified graph. In conclusion, graph CDR analysis can effectively quantify the distribution of TIA risk factors. The resulting TIA risk factor distribution might be instrumental in developing new risk prediction machine learning models for screening and early detection of TIA.

Predictors of acute incisional hernia incarceration at initial hernia diagnosis on computed tomography

BACKGROUND

Acute incisional hernia incarceration is associated with high morbidity and mortality yet there is little evidence to guide which patients will benefit most from prophylactic repair. We explored baseline computed tomography (CT) characteristics associated with incarceration.

METHODS

A case-control study design was utilized to explore adults (≥18 years) diagnosed with an incisional hernia between 2010 and 2017 at a single institution with a 1-year minimum follow-up. Computed tomography imaging at the time of initial hernia diagnosis was examined. Following propensity score matching for baseline characteristics, multivariable logistic regression was performed to identify independent predictors associated with acute incarceration.

RESULTS

A total of 532 patients (27.26% male, mean 61.55 years) were examined, of whom 238 experienced an acute incarceration. Between two well-matched cohorts with and without incarceration, the presence of small bowel in the hernia sac (odds ratio [OR], 7.50; 95% confidence interval [CI], 3.35-16.38), increasing sac height (OR, 1.34; 95% CI, 1.10-1.64), more acute hernia angle (OR, 0.98 per degree; 95% CI, 0.97-0.99), decreased fascial defect width (OR, 0.68; 95% CI, 0.58-0.81), and greater outer abdominal fat (OR, 1.28; 95% CI, 1.02-1.60) were associated with acute incarceration. Using threshold analysis, a hernia angle of <91 degrees and a sac height of >3.25 cm were associated with increased incarceration risk.

CONCLUSION

Computed tomography features present at the time of hernia diagnosis provide insight into later acute incarceration risk. Improved understanding of acute incisional hernia incarceration can guide selection for prophylactic repair and thereby may mitigate the excess morbidity associated with incarceration.

LEVEL OF EVIDENCE

Prognostic and Epidemiological; Level III.

AI/ML advances in non-small cell lung cancer biomarker discovery

Lung cancer is the leading cause of cancer deaths among both men and women, representing approximately 25% of cancer fatalities each year. The treatment landscape for non-small cell lung cancer (NSCLC) is rapidly evolving due to the progress made in biomarker-driven targeted therapies. While advancements in targeted treatments have improved survival rates for NSCLC patients with actionable biomarkers, long-term survival remains low, with an overall 5-year relative survival rate below 20%. Artificial intelligence/machine learning (AI/ML) algorithms have shown promise in biomarker discovery, yet NSCLC-specific studies capturing the clinical challenges targeted and emerging patterns identified using AI/ML approaches are lacking. Here, we employed a text-mining approach and identified 215 studies that reported potential biomarkers of NSCLC using AI/ML algorithms. We catalogued these studies with respect to BEST (Biomarkers, EndpointS, and other Tools) biomarker sub-types and summarized emerging patterns and trends in AI/ML-driven NSCLC biomarker discovery. We anticipate that our comprehensive review will contribute to the current understanding of AI/ML advances in NSCLC biomarker research and provide an important catalogue that may facilitate clinical adoption of AI/ML-derived biomarkers.

Temporal Generalizability of Machine Learning Models for Predicting Postoperative Delirium Using Electronic Health Record Data: Model Development and Validation Study

BACKGROUND

Although machine learning models demonstrate significant potential in predicting postoperative delirium, the advantages of their implementation in real-world settings remain unclear and require a comparison with conventional models in practical applications.

OBJECTIVE

The objective of this study was to validate the temporal generalizability of decision tree ensemble and sparse linear regression models for predicting delirium after surgery compared with that of the traditional logistic regression model.

METHODS

The health record data of patients hospitalized at an advanced emergency and critical care medical center in Kumamoto, Japan, were collected electronically. We developed a decision tree ensemble model using extreme gradient boosting (XGBoost) and a sparse linear regression model using least absolute shrinkage and selection operator (LASSO) regression. To evaluate the predictive performance of the model, we used the area under the receiver operating characteristic curve (AUROC) and the Matthews correlation coefficient (MCC) to measure discrimination and the slope and intercept of the regression between predicted and observed probabilities to measure calibration. The Brier score was evaluated as an overall performance metric. We included 11,863 consecutive patients who underwent surgery with general anesthesia between December 2017 and February 2022. The patients were divided into a derivation cohort before the COVID-19 pandemic and a validation cohort during the COVID-19 pandemic. Postoperative delirium was diagnosed according to the confusion assessment method.

RESULTS

A total of 6497 patients (68.5, SD 14.4 years, women n=2627, 40.4%) were included in the derivation cohort, and 5366 patients (67.8, SD 14.6 years, women n=2105, 39.2%) were included in the validation cohort. Regarding discrimination, the XGBoost model (AUROC 0.87-0.90 and MCC 0.34-0.44) did not significantly outperform the LASSO model (AUROC 0.86-0.89 and MCC 0.34-0.41). The logistic regression model (AUROC 0.84-0.88, MCC 0.33-0.40, slope 1.01-1.19, intercept -0.16 to 0.06, and Brier score 0.06-0.07), with 8 predictors (age, intensive care unit, neurosurgery, emergency admission, anesthesia time, BMI, blood loss during surgery, and use of an ambulance) achieved good predictive performance.

CONCLUSIONS

The XGBoost model did not significantly outperform the LASSO model in predicting postoperative delirium. Furthermore, a parsimonious logistic model with a few important predictors achieved comparable performance to machine learning models in predicting postoperative delirium.

Clicking Away to Capture Cancer Staging-The Benefits and Challenges of Completing Standardized Staging Modules

This article by Neelima Vidula and Jeffrey Peppercorn @MGHCancerCenter explores the benefits and challenges of completing standardized modules for cancer staging, and opportunities to improve module compliance while reducing burnout

Endovascular Aneurysm Repair Devices as a Use Case for Postmarketing Surveillance of Medical Devices

Importance

The US Food and Drug Administration (FDA) is building a national postmarketing surveillance system for medical devices, moving to a "total product life cycle" approach whereby more limited premarketing data are balanced with postmarketing surveillance to capture rare adverse events and long-term safety issues.

Objective

To assess the methodological requirements and feasibility of postmarketing device surveillance using endovascular aneurysm repair devices (EVARs), which have been the subject of safety concerns, using clinical data from a large health care system.

Design, Setting, and Participants

This retrospective cohort study included patients with electronic health record (EHR) data in the Veterans Affairs Corporate Data Warehouse.

Exposure

Implantation of an AFX Endovascular AAA System (AFX) device (any of 3 iterations) or a non-AFX comparator EVAR device from January 1, 2011, to December 21, 2021.

Main Outcomes and Measures

The primary outcomes were rates of type III endoleaks and all-cause mortality; and rates of these outcomes associated with AFX devices compared with non-AFX devices, assessed using Cox proportional hazards regression models and doubly robust causal modeling. Information on type III endoleaks was available only as free-text mentions in clinical notes, while all-cause mortality data could be extracted using structured data. Device-specific information required by the FDA is ascertained using unique device identifiers (UDIs), which include factors such as model numbers, catalog numbers, and manufacturer-specific product codes. The availability of UDIs in EHRs was assessed.

Results

In total, 13 941 patients (mean [SD] age, 71.8 [7.4] years) received 1 of the devices of interest (AFX with Strata [AFX-S]: 718 patients [5.2%]; AFX with Duraply [AFX-D]: 404 patients [2.9%]; or AFX2: 682 patients [4.9%]), and 12 137 (87.1%) received non-AFX devices. The UDIs were not recorded in the EHR for any patient with an AFX device, and partial UDIs were available for 19 patients (0.1%) with a non-AFX device. This necessitated the development of advanced natural language processing tools to define the cohort of patients for analysis. The study identified a significantly higher risk of type III endoleaks at 5 years among patients receiving any of the AFX device iterations, including the most recent version, AFX2 (11.6%; 95% CI, 8.1%-15.1%) compared with that among patients with non-AFX devices (5.7%; 95% CI, 2.2%-9.2%; absolute risk difference, 5.9%; 95% CI, 2.3%-9.4%). However, there was no significantly higher all-cause mortality for any of the AFX device iterations, including for AFX2 (19.0%; 95% CI, 16.0%-22.0%) compared with non-AFX devices (18.0%; 95% CI, 15.0%-21.0%; absolute risk difference, 1.0%; 95% CI, -2.1% to 4.1%).

Conclusions and Relevance

The findings of this cohort study suggest that clinical data can be used for the postmarketing device surveillance required by the FDA. The study also highlights ongoing challenges to performing larger-scale surveillance, including lack of consistent use of UDIs and insufficient relevant structured data to efficiently capture certain outcomes of interest.

Comprehensive analysis of clinical data for COVID-19 outcome estimation with machine learning models

COVID-19 is a global threat for the healthcare systems due to the rapid spread of the pathogen that causes it. In such situation, the clinicians must take important decisions, in an environment where medical resources can be insufficient. In this task, the computer-aided diagnosis systems can be very useful not only in the task of supporting the clinical decisions but also to perform relevant analyses, allowing them to understand better the disease and the factors that can identify the high risk patients. For those purposes, in this work, we use several machine learning algorithms to estimate the outcome of COVID-19 patients given their clinical information. Particularly, we perform 2 different studies: the first one estimates whether the patient is at low or at high risk of death whereas the second estimates if the patient needs hospitalization or not. The results of the analyses of this work show the most relevant features for each studied scenario, as well as the classification performance of the considered machine learning models. In particular, the XGBoost algorithm is able to estimate the need for hospitalization of a patient with an AUC-ROC of 0 . 8415 ± 0 . 0217 while it can also estimate the risk of death with an AUC-ROC of 0 . 7992 ± 0 . 0104 . Results have demonstrated the great potential of the proposal to determine those patients that need a greater amount of medical resources for being at a higher risk. This provides the healthcare services with a tool to better manage their resources.

Predictive Models for Health Deterioration: Understanding Disease Pathways for Personalized Medicine

Artificial intelligence (AI) and machine learning (ML) methods are currently widely employed in medicine and healthcare. A PubMed search returns more than 100,000 articles on these topics published between 2018 and 2022 alone. Notwithstanding several recent reviews in various subfields of AI and ML in medicine, we have yet to see a comprehensive review around the methods' use in longitudinal analysis and prediction of an individual patient's health status within a personalized disease pathway. This review seeks to fill that gap. After an overview of the AI and ML methods employed in this field and of specific medical applications of models of this type, the review discusses the strengths and limitations of current studies and looks ahead to future strands of research in this field. We aim to enable interested readers to gain a detailed impression of the research currently available and accordingly plan future work around predictive models for deterioration in health status.

Development of a Machine Learning Model to Predict Recurrence of Oral Tongue Squamous Cell Carcinoma

Despite diagnostic advancements, the development of reliable prognostic systems for assessing the risk of cancer recurrence still remains a challenge. In this study, we developed a novel framework to generate highly representative machine-learning prediction models for oral tongue squamous cell carcinoma (OTSCC) cancer recurrence. We identified cases of 5- and 10-year OTSCC recurrence from the SEER database. Four classification models were trained using the H₂O ai platform, whose performances were assessed according to their accuracy, recall, precision, and the area under the curve (AUC) of their receiver operating characteristic (ROC) curves. By evaluating Shapley additive explanation contribution plots, feature importance was studied. Of the 130,979 patients studied, 36,042 (27.5%) were female, and the mean (SD) age was 58.2 (13.7) years. The Gradient Boosting Machine model performed the best, achieving 81.8% accuracy and 97.7% precision for 5-year prediction. Moreover, 10-year predictions demonstrated 80.0% accuracy and 94.0% precision. The number of prior tumors, patient age, the site of cancer recurrence, and tumor histology were the most significant predictors. The implementation of our novel SEER framework enabled the successful identification of patients with OTSCC recurrence, with which highly accurate and sensitive prediction models were generated. Thus, we demonstrate our framework's potential for application in various cancers to build generalizable screening tools to predict tumor recurrence.

Postprediction Inference for Clinical Characteristics Extracted With Machine Learning on Electronic Health Records

PURPOSE

Real-world data (RWD) derived from electronic health records (EHRs) are often used to understand population-level relationships between patient characteristics and cancer outcomes. Machine learning (ML) methods enable researchers to extract characteristics from unstructured clinical notes, and represent a more cost-effective and scalable approach than manual expert abstraction. These extracted data are then used in epidemiologic or statistical models as if they were abstracted observations. Analytical results derived from extracted data in this way may differ from those given by abstracted data, and the magnitude of this difference is not directly informed by standard ML performance metrics.

METHODS

In this paper, we define the task of postprediction inference, which is to recover similar estimation and inference from an ML-extracted variable that would be obtained from abstracting the variable. We consider fitting a Cox proportional hazards model that uses a binary ML-extracted variable as a covariate and evaluate four approaches for postprediction inference in this setting. The first two approaches only require the ML-predicted probability, while the latter two additionally require a labeled (human abstracted) validation data set.

RESULTS

Our results for both simulated data and EHR-derived RWD from a national cohort demonstrate that we can improve inference from ML-extracted variables by leveraging a limited amount of labeled data.

CONCLUSION

We describe and evaluate methods for fitting statistical models using ML-extracted variables subject to model error. We show that estimation and inference is generally valid when using extracted data from high-performing ML models. More complex methods that incorporate auxiliary labeled data provide further improvements.

Profile of the multicenter cohort of the German Cancer Consortium's Clinical Communication Platform

Treatment concepts in oncology are becoming increasingly personalized and diverse. Successively, changes in standards of care mandate continuous monitoring of patient pathways and clinical outcomes based on large, representative real-world data. The German Cancer Consortium's (DKTK) Clinical Communication Platform (CCP) provides such opportunity. Connecting fourteen university hospital-based cancer centers, the CCP relies on a federated IT-infrastructure sourcing data from facility-based cancer registry units and biobanks. Federated analyses resulted in a cohort of 600,915 patients, out of which 232,991 were incident since 2013 and for which a comprehensive documentation is available. Next to demographic data (i.e., age at diagnosis: 2.0% 0-20 years, 8.3% 21-40 years, 30.9% 41-60 years, 50.1% 61-80 years, 8.8% 81+ years; and gender: 45.2% female, 54.7% male, 0.1% other) and diagnoses (five most frequent tumor origins: 22,523 prostate, 18,409 breast, 15,575 lung, 13,964 skin/malignant melanoma, 9005 brain), the cohort dataset contains information about therapeutic interventions and response assessments and is connected to 287,883 liquid and tissue biosamples. Focusing on diagnoses and therapy-sequences, showcase analyses of diagnosis-specific sub-cohorts (pancreas, larynx, kidney, thyroid gland) demonstrate the analytical opportunities offered by the cohort's data. Due to its data granularity and size, the cohort is a potential catalyst for translational cancer research. It provides rapid access to comprehensive patient groups and may improve the understanding of the clinical course of various (even rare) malignancies. Therefore, the cohort may serve as a decisions-making tool for clinical trial design and contributes to the evaluation of scientific findings under real-world conditions.

Artificial intelligence based personalized predictive survival among colorectal cancer patients

BACKGROUND AND OBJECTIVE

Colorectal cancer is a major health concern. It is now the third most common cancer and the fourth leading cause of cancer mortality worldwide. The aim of this study was to evaluate the performance of machine learning algorithms for predicting survival of colorectal cancer patients 1 to 5 years after diagnosis, and identify the most important variables.

METHODS

A sample of 1236 patients diagnosed with colorectal cancer and 118 predictor variables has been used. The outcome of interest was a binary variable indicating whether the patient survived the number of years in question or not. 20 predictor variables were selected using mutual information score with the outcome. We implemented 11 machine learning algorithms and evaluated their performance with a 5 by 2-fold cross-validation with stratified folds and with paired Student's t-tests. We compared the results with the Kaplan-Meier estimator and Cox's proportional hazard regression.

RESULTS

Using the 20 most important predictor variables for each of the survival years, the logistic regression algorithm achieved an area under the receiver operating characteristic curve of 0.850 (0.014 SD, 0.840-0.860 95 % CI) for the 1-year, and 0.872 (0.014 SD, 0.861-0.882 95% CI) for the 5-year survival prediction. Using only the 5 most important predictor variables, the corresponding values are 0.793 (0.020 SD, 0.778-0.807 95% CI) and 0.794 (0.011 SD, 0.785-0.802 95% CI). The most important variables for 1-year prediction were number of R residual, M distant metastasis, overall stage, probable recurrence within 5 years, and tumour length, whereas for 5-year prediction the most important were probable recurrence within 5 years, R residual, M distant metastasis, number of positive lymph nodes, and palliative chemotherapy. Biomarkers do not appear among the top 20 most important ones. For all survival intervals, the probability of the top model agrees with the Kaplan-Meier estimate, both in the interval of one standard deviation and in the 95% confidence interval.

CONCLUSIONS

The findings suggest that machine learning algorithms can predict the survival probability of colorectal cancer patients and can be used to inform the patients and assist decision-making in clinical care management. In addition, this study unveils the most essential variables for estimating survival short- and long-term among patients with Colorectal cancer.

Multimodal data fusion for cancer biomarker discovery with deep learning

Technological advances now make it possible to study a patient from multiple angles with high-dimensional, high-throughput multi-scale biomedical data. In oncology, massive amounts of data are being generated ranging from molecular, histopathology, radiology to clinical records. The introduction of deep learning has significantly advanced the analysis of biomedical data. However, most approaches focus on single data modalities leading to slow progress in methods to integrate complementary data types. Development of effective multimodal fusion approaches is becoming increasingly important as a single modality might not be consistent and sufficient to capture the heterogeneity of complex diseases to tailor medical care and improve personalised medicine. Many initiatives now focus on integrating these disparate modalities to unravel the biological processes involved in multifactorial diseases such as cancer. However, many obstacles remain, including lack of usable data as well as methods for clinical validation and interpretation. Here, we cover these current challenges and reflect on opportunities through deep learning to tackle data sparsity and scarcity, multimodal interpretability, and standardisation of datasets.

Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review

BACKGROUND

Natural Language Processing (NLP) is widely used to extract clinical insights from Electronic Health Records (EHRs). However, the lack of annotated data, automated tools, and other challenges hinder the full utilisation of NLP for EHRs. Various Machine Learning (ML), Deep Learning (DL) and NLP techniques are studied and compared to understand the limitations and opportunities in this space comprehensively.

METHODOLOGY

After screening 261 articles from 11 databases, we included 127 papers for full-text review covering seven categories of articles: (1) medical note classification, (2) clinical entity recognition, (3) text summarisation, (4) deep learning (DL) and transfer learning architecture, (5) information extraction, (6) Medical language translation and (7) other NLP applications. This study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

RESULT AND DISCUSSION

EHR was the most commonly used data type among the selected articles, and the datasets were primarily unstructured. Various ML and DL methods were used, with prediction or classification being the most common application of ML or DL. The most common use cases were: the International Classification of Diseases, Ninth Revision (ICD-9) classification, clinical note analysis, and named entity recognition (NER) for clinical descriptions and research on psychiatric disorders.

CONCLUSION

We find that the adopted ML models were not adequately assessed. In addition, the data imbalance problem is quite important, yet we must find techniques to address this underlining problem. Future studies should address key limitations in studies, primarily identifying Lupus Nephritis, Suicide Attempts, perinatal self-harmed and ICD-9 classification.

Developing Artificial Intelligence Models for Extracting Oncologic Outcomes from Japanese Electronic Health Records

INTRODUCTION

A framework that extracts oncological outcomes from large-scale databases using artificial intelligence (AI) is not well established. Thus, we aimed to develop AI models to extract outcomes in patients with lung cancer using unstructured text data from electronic health records of multiple hospitals.

METHODS

We constructed AI models (Bidirectional Encoder Representations from Transformers [BERT], Naïve Bayes, and Longformer) for tumor evaluation using the University of Miyazaki Hospital (UMH) database. This data included both structured and unstructured data from progress notes, radiology reports, and discharge summaries. The BERT model was applied to the Life Data Initiative (LDI) data set of six hospitals. Study outcomes included the performance of AI models and time to progression of disease (TTP) for each line of treatment based on the treatment response extracted by AI models.

RESULTS

For the UMH data set, the BERT model exhibited higher precision accuracy compared to the Naïve Bayes or the Longformer models, respectively (precision [0.42 vs. 0.47 or 0.22], recall [0.63 vs. 0.46 or 0.33] and F1 scores [0.50 vs. 0.46 or 0.27]). When this BERT model was applied to LDI data, prediction accuracy remained quite similar. The Kaplan-Meier plots of TTP (months) showed similar trends for the first (median 14.9 [95% confidence interval 11.5, 21.1] and 16.8 [12.6, 21.8]), the second (7.8 [6.7, 10.7] and 7.8 [6.7, 10.7]), and the later lines of treatment for the predicted data by the BERT model and the manually curated data.

CONCLUSION

We developed AI models to extract treatment responses in patients with lung cancer using a large EHR database; however, the model requires further improvement.

Predicting the Survival of Patients With Cancer From Their Initial Oncology Consultation Document Using Natural Language Processing

IMPORTANCE

Predicting short- and long-term survival of patients with cancer may improve their care. Prior predictive models either use data with limited availability or predict the outcome of only 1 type of cancer.

OBJECTIVE

To investigate whether natural language processing can predict survival of patients with general cancer from a patient's initial oncologist consultation document.

DESIGN, SETTING, AND PARTICIPANTS

This retrospective prognostic study used data from 47 625 of 59 800 patients who started cancer care at any of the 6 BC Cancer sites located in the province of British Columbia between April 1, 2011, and December 31, 2016. Mortality data were updated until April 6, 2022, and data were analyzed from update until September 30, 2022. All patients with a medical or radiation oncologist consultation document generated within 180 days of diagnosis were included; patients seen for multiple cancers were excluded.

EXPOSURES

Initial oncologist consultation documents were analyzed using traditional and neural language models.

MAIN OUTCOMES AND MEASURES

The primary outcome was the performance of the predictive models, including balanced accuracy and receiver operating characteristics area under the curve (AUC). The secondary outcome was investigating what words the models used.

RESULTS

Of the 47 625 patients in the sample, 25 428 (53.4%) were female and 22 197 (46.6%) were male, with a mean (SD) age of 64.9 (13.7) years. A total of 41 447 patients (87.0%) survived 6 months, 31 143 (65.4%) survived 36 months, and 27 880 (58.5%) survived 60 months, calculated from their initial oncologist consultation. The best models achieved a balanced accuracy of 0.856 (AUC, 0.928) for predicting 6-month survival, 0.842 (AUC, 0.918) for 36-month survival, and 0.837 (AUC, 0.918) for 60-month survival, on a holdout test set. Differences in what words were important for predicting 6- vs 60-month survival were found.

CONCLUSIONS AND RELEVANCE

These findings suggest that models performed comparably with or better than previous models predicting cancer survival and that they may be able to predict survival using readily available data without focusing on 1 cancer type.

Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts

BACKGROUND

Binary diagnosis of coronary artery disease does not preserve the complexity of disease or quantify its severity or its associated risk with death; hence, a quantitative marker of coronary artery disease is warranted. We evaluated a quantitative marker of coronary artery disease derived from probabilities of a machine learning model.

METHODS

In this cohort study, we developed and validated a coronary artery disease-predictive machine learning model using 95 935 electronic health records and assessed its probabilities as in-silico scores for coronary artery disease (ISCAD; range 0 [lowest probability] to 1 [highest probability]) in participants in two longitudinal biobank cohorts. We measured the association of ISCAD with clinical outcomes-namely, coronary artery stenosis, obstructive coronary artery disease, multivessel coronary artery disease, all-cause death, and coronary artery disease sequelae.

FINDINGS

Among 95 935 participants, 35 749 were from the BioMe Biobank (median age 61 years [IQR 18]; 14 599 [41%] were male and 21 150 [59%] were female; 5130 [14%] were with diagnosed coronary artery disease) and 60 186 were from the UK Biobank (median age 62 [15] years; 25 031 [42%] male and 35 155 [58%] female; 8128 [14%] with diagnosed coronary artery disease). The model predicted coronary artery disease with an area under the receiver operating characteristic curve of 0·95 (95% CI 0·94-0·95; sensitivity of 0·94 [0·94-0·95] and specificity of 0·82 [0·81-0·83]) and 0·93 (0·92-0·93; sensitivity of 0·90 [0·89-0·90] and specificity of 0·88 [0·87-0·88]) in the BioMe validation and holdout sets, respectively, and 0·91 (0·91-0·91; sensitivity of 0·84 [0·83-0·84] and specificity of 0·83 [0·82-0·83]) in the UK Biobank external test set. ISCAD captured coronary artery disease risk from known risk factors, pooled cohort equations, and polygenic risk scores. Coronary artery stenosis increased quantitatively with ascending ISCAD quartiles (increase per quartile of 12 percentage points), including risk of obstructive coronary artery disease, multivessel coronary artery disease, and stenosis of major coronary arteries. Hazard ratios (HRs) and prevalence of all-cause death increased stepwise over ISCAD deciles (decile 1: HR 1·0 [95% CI 1·0-1·0], 0·2% prevalence; decile 6: 11 [3·9-31], 3·1% prevalence; and decile 10: 56 [20-158], 11% prevalence). A similar trend was observed for recurrent myocardial infarction. 12 (46%) undiagnosed individuals with high ISCAD (≥0·9) had clinical evidence of coronary artery disease according to the 2014 American College of Cardiology/American Heart Association Task Force guidelines.

INTERPRETATION

Electronic health record-based machine learning was used to generate an in-silico marker for coronary artery disease that can non-invasively quantify atherosclerosis and risk of death on a continuous spectrum, and identify underdiagnosed individuals.

FUNDING

National Institutes of Health.

Symptoms timeline and outcomes in amyotrophic lateral sclerosis using artificial intelligence

Amyotrophic lateral sclerosis (ALS) is a fatal, neurodegenerative motor neuron disease. Although an early diagnosis is crucial to provide adequate care and improve survival, patients with ALS experience a significant diagnostic delay. This study aimed to use real-world data to describe the clinical profile and timing between symptom onset, diagnosis, and relevant outcomes in ALS. Retrospective and multicenter study in 5 representative hospitals and Primary Care services in the SESCAM Healthcare Network (Castilla-La Mancha, Spain). Using Natural Language Processing (NLP), the clinical information in electronic health records of all patients with ALS was extracted between January 2014 and December 2018. From a source population of all individuals attended in the participating hospitals, 250 ALS patients were identified (61.6% male, mean age 64.7 years). Of these, 64% had spinal and 36% bulbar ALS. For most defining symptoms, including dyspnea, dysarthria, dysphagia and fasciculations, the overall diagnostic delay from symptom onset was 11 (6-18) months. Prior to diagnosis, only 38.8% of patients had visited the neurologist. In a median post-diagnosis follow-up of 25 months, 52% underwent gastrostomy, 64% non-invasive ventilation, 16.4% tracheostomy, and 87.6% riluzole treatment; these were more commonly reported (all Ps < 0.05) and showed greater probability of occurrence (all Ps < 0.03) in bulbar ALS. Our results highlight the diagnostic delay in ALS and revealed differences in the clinical characteristics and occurrence of major disease-specific events across ALS subtypes. NLP holds great promise for its application in the wider context of rare neurological diseases.

Natural Language Processing Applications for Computer-Aided Diagnosis in Oncology

In the era of big data, text-based medical data, such as electronic health records (EHR) and electronic medical records (EMR), are growing rapidly. EHR and EMR are collected from patients to record their basic information, lab tests, vital signs, clinical notes, and reports. EHR and EMR contain the helpful information to assist oncologists in computer-aided diagnosis and decision making. However, it is time consuming for doctors to extract the valuable information they need and analyze the information from the EHR and EMR data. Recently, more and more research works have applied natural language processing (NLP) techniques, i.e., rule-based, machine learning-based, and deep learning-based techniques, on the EHR and EMR data for computer-aided diagnosis in oncology. The objective of this review is to narratively review the recent progress in the area of NLP applications for computer-aided diagnosis in oncology. Moreover, we intend to reduce the research gap between artificial intelligence (AI) experts and clinical specialists to design better NLP applications. We originally identified 295 articles from the three electronic databases: PubMed, Google Scholar, and ACL Anthology; then, we removed the duplicated papers and manually screened the irrelevant papers based on the content of the abstract; finally, we included a total of 23 articles after the screening process of the literature review. Furthermore, we provided an in-depth analysis and categorized these studies into seven cancer types: breast cancer, lung cancer, liver cancer, prostate cancer, pancreatic cancer, colorectal cancer, and brain tumors. Additionally, we identified the current limitations of NLP applications on supporting the clinical practices and we suggest some promising future research directions in this paper.

On the importance of interpretable machine learning predictions to inform clinical decision making in oncology

Machine learning-based tools are capable of guiding individualized clinical management and decision-making by providing predictions of a patient's future health state. Through their ability to model complex nonlinear relationships, ML algorithms can often outperform traditional statistical prediction approaches, but the use of nonlinear functions can mean that ML techniques may also be less interpretable than traditional statistical methodologies. While there are benefits of intrinsic interpretability, many model-agnostic approaches now exist and can provide insight into the way in which ML systems make decisions. In this paper, we describe how different algorithms can be interpreted and introduce some techniques for interpreting complex nonlinear algorithms.

Extracting patient-level data from the electronic health record: Expanding opportunities for health system research

BACKGROUND

Epidemiological studies of interstitial lung disease (ILD) are limited by small numbers and tertiary care bias. Investigators have leveraged the widespread use of electronic health records (EHRs) to overcome these limitations, but struggle to extract patient-level, longitudinal clinical data needed to address many important research questions. We hypothesized that we could automate longitudinal ILD cohort development using the EHR of a large, community-based healthcare system.

STUDY DESIGN AND METHODS

We applied a previously validated algorithm to the EHR of a community-based healthcare system to identify ILD cases between 2012-2020. We then extracted disease-specific characteristics and outcomes using fully automated data-extraction algorithms and natural language processing of selected free-text.

RESULTS

We identified a community cohort of 5,399 ILD patients (prevalence = 118 per 100,000). Pulmonary function tests (71%) and serologies (54%) were commonly used in the diagnostic evaluation, whereas lung biopsy was rare (5%). IPF was the most common ILD diagnosis (n = 972, 18%). Prednisone was the most commonly prescribed medication (911, 17%). Nintedanib and pirfenidone were rarely prescribed (n = 305, 5%). ILD patients were high-utilizers of inpatient (40%/year hospitalized) and outpatient care (80%/year with pulmonary visit), with sustained utilization throughout the post-diagnosis study period.

DISCUSSION

We demonstrated the feasibility of robustly characterizing a variety of patient-level utilization and health services outcomes in a community-based EHR cohort. This represents a substantial methodological improvement by alleviating traditional constraints on the accuracy and clinical resolution of such ILD cohorts; we believe this approach will make community-based ILD research more efficient, effective, and scalable.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.

Machine learning models for identifying predictors of clinical outcomes with first-line immune checkpoint inhibitor therapy in advanced non-small cell lung cancer

Immune checkpoint inhibitors (ICIs) are standard-of-care as first-line (1L) therapy for advanced non-small cell lung cancer (aNSCLC) without actionable oncogenic driver mutations. While clinical trials demonstrated benefits of ICIs over chemotherapy, variation in outcomes across patients has been observed and trial populations may not be representative of clinical practice. Predictive models can help understand heterogeneity of treatment effects, identify predictors of meaningful clinical outcomes, and may inform treatment decisions. We applied machine learning (ML)-based survival models to a real-world cohort of patients with aNSCLC who received 1L ICI therapy extracted from a US-based electronic health record database. Model performance was evaluated using metrics including concordance index (c-index), and we used explainability techniques to identify significant predictors of overall survival (OS) and progression-free survival (PFS). The ML model achieved c-indices of 0.672 and 0.612 for OS and PFS, respectively, and Kaplan-Meier survival curves showed significant differences between low- and high-risk groups for OS and PFS (both log-rank test p < 0.0001). Identified predictors were mostly consistent with the published literature and/or clinical expectations and largely overlapped for OS and PFS; Eastern Cooperative Oncology Group performance status, programmed cell death-ligand 1 expression levels, and serum albumin were among the top 5 predictors for both outcomes. Prospective and independent data set evaluation is required to confirm these results.

Temporal Trends in Clinical Evidence of 5-Year Survival Within Electronic Health Records Among Patients With Early-Stage Colon Cancer Managed With Laparoscopy-Assisted Colectomy vs Open Colectomy

IMPORTANCE

Temporal shifts in clinical knowledge and practice need to be adjusted for in treatment outcome assessment in clinical evidence.

OBJECTIVE

To use electronic health record (EHR) data to (1) assess the temporal trends in treatment decisions and patient outcomes and (2) emulate a randomized clinical trial (RCT) using EHR data with proper adjustment for temporal trends.

DESIGN, SETTING, AND PARTICIPANTS

The Clinical Outcomes of Surgical Therapy (COST) Study Group Trial assessing overall survival of patients with stages I to III early-stage colon cancer was chosen as the target trial. The RCT was emulated using EHR data of patients from a single health care system cohort who underwent colectomy for early-stage colon cancer from January 1, 2006, to December 31, 2017, and were followed up to January 1, 2020, from Mass General Brigham. Analyses were conducted from December 2, 2019, to January 24, 2022.

EXPOSURES

Laparoscopy-assisted colectomy (LAC) vs open colectomy (OC).

MAIN OUTCOMES AND MEASURES

The primary outcome was 5-year overall survival. To address confounding in the emulation, pretreatment variables were selected and adjusted. The temporal trends were adjusted by stratification of the calendar year when the colectomies were performed with cotraining across strata.

RESULTS

A total of 943 patients met key RCT eligibility criteria in the EHR emulation cohort, including 518 undergoing LAC (median age, 63 [range, 20-95] years; 268 [52%] women; 121 [23%] with stage I, 165 [32%] with stage II, and 232 [45%] with stage III cancer; 32 [6%] with colon adhesion; 278 [54%] with right-sided colon cancer; 18 [3%] with left-sided colon cancer; and 222 [43%] with sigmoid colon cancer) and 425 undergoing OC (median age, 65 [range, 28-99] years; 223 [52%] women; 61 [14%] with stage I, 153 [36%] with stage II, and 211 [50%] with stage III cancer; 39 [9%] with colon adhesion; 202 [47%] with right-sided colon cancer; 39 [9%] with left-sided colon cancer; and 201 [47%] with sigmoid colon cancer). Tests for temporal trends in treatment assignment (χ2 = 60.3; P < .001) and overall survival (χ2 = 137.2; P < .001) were significant. The adjusted EHR emulation reached the same conclusion as the RCT: LAC is not inferior to OC in overall survival rate with risk difference at 5 years of -0.007 (95% CI, -0.070 to 0.057). The results were consistent for stratified analysis within each temporal period.

CONCLUSIONS AND RELEVANCE

These findings suggest that confounding bias from temporal trends should be considered when conducting clinical evidence studies with long time spans. Stratification of calendar time and cotraining of models is one solution. With proper adjustment, clinical evidence may supplement RCTs in the assessment of treatment outcome over time.

Expanding Personalized, Data-Driven Dermatology: Leveraging Digital Health Technology and Machine Learning to Improve Patient Outcomes

The current revolution of digital health technology and machine learning offers enormous potential to improve patient care. Nevertheless, it is essential to recognize that dermatology requires an approach different from those of other specialties. For many dermatological conditions, there is a lack of standardized methodology for quantitatively tracking disease progression and treatment response (clinimetrics). Furthermore, dermatological diseases impact patients in complex ways, some of which can be measured only through patient reports (psychometrics). New tools using digital health technology (e.g., smartphone applications, wearable devices) can aid in capturing both clinimetric and psychometric variables over time. With these data, machine learning can inform efforts to improve health care by, for example, the identification of high-risk patient groups, optimization of treatment strategies, and prediction of disease outcomes. We use the term personalized, data-driven dermatology to refer to the use of comprehensive data to inform individual patient care and improve patient outcomes. In this paper, we provide a framework that includes data from multiple sources, leverages digital health technology, and uses machine learning. Although this framework is applicable broadly to dermatological conditions, we use the example of a serious inflammatory skin condition, chronic cutaneous graft-versus-host disease, to illustrate personalized, data-driven dermatology.

Using Natural Language Processing and Machine Learning to Preoperatively Predict Lymph Node Metastasis for Non-Small Cell Lung Cancer With Electronic Medical Records: Development and Validation Study

Background

Lymph node metastasis (LNM) is critical for treatment decision making of patients with resectable non–small cell lung cancer, but it is difficult to precisely diagnose preoperatively. Electronic medical records (EMRs) contain a large volume of valuable information about LNM, but some key information is recorded in free text, which hinders its secondary use.

Objective

This study aims to develop LNM prediction models based on EMRs using natural language processing (NLP) and machine learning algorithms.

Methods

We developed a multiturn question answering NLP model to extract features about the primary tumor and lymph nodes from computed tomography (CT) reports. We then combined these features with other structured clinical characteristics to develop LNM prediction models using machine learning algorithms. We conducted extensive experiments to explore the effectiveness of the predictive models and compared them with size criteria based on CT image findings (the maximum short axis diameter of lymph node >10 mm was regarded as a metastatic node) and clinician’s evaluation. Since the NLP model may extract features with mistakes, we also calculated the concordance correlation between the predicted probabilities of models using NLP-extracted features and gold standard features to explore the influence of NLP-driven automatic extraction.

Results

Experimental results show that the random forest models achieved the best performances with 0.792 area under the receiver operating characteristic curve (AUC) value and 0.456 average precision (AP) value for pN2 LNM prediction and 0.768 AUC value and 0.524 AP value for pN1&N2 LNM prediction. And all machine learning models outperformed the size criteria and clinician’s evaluation. The concordance correlation between the random forest models using NLP-extracted features and gold standard features is 0.950 and improved to 0.984 when the top 5 important NLP-extracted features were replaced with gold standard features.

Conclusions

The LNM models developed can achieve competitive performance using only limited EMR data such as CT reports and tumor markers in comparison with the clinician’s evaluation. The multiturn question answering NLP model can extract features effectively to support the development of LNM prediction models, which may facilitate the clinical application of predictive models.

Differentiation of lumbar disc herniation and lumbar spinal stenosis using natural language processing–based machine learning based on positive symptoms

OBJECTIVE

The purpose of this study was to develop natural language processing (NLP)–based machine learning algorithms to automatically differentiate lumbar disc herniation (LDH) and lumbar spinal stenosis (LSS) based on positive symptoms in free-text admission notes. The secondary purpose was to compare the performance of the deep learning algorithm with the ensemble model on the current task.

METHODS

In total, 1921 patients whose principal diagnosis was LDH or LSS between June 2013 and June 2020 at Zhongda Hospital, affiliated with Southeast University, were retrospectively analyzed. The data set was randomly divided into a training set and testing set at a 7:3 ratio. Long Short-Term Memory (LSTM) and extreme gradient boosting (XGBoost) models were developed in this study. NLP algorithms were assessed on the testing set by the following metrics: receiver operating characteristic (ROC) curve, area under the curve (AUC), accuracy score, recall score, F1 score, and precision score.

RESULTS

In the testing set, the LSTM model achieved an AUC of 0.8487, accuracy score of 0.7818, recall score of 0.9045, F1 score of 0.8108, and precision score of 0.7347. In comparison, the XGBoost model achieved an AUC of 0.7565, accuracy score of 0.6961, recall score of 0.7387, F1 score of 0.7153, and precision score of 0.6934.

CONCLUSIONS

NLP-based machine learning algorithms were a promising auxiliary to the electronic health record in spine disease diagnosis. LSTM, the deep learning model, showed better capacity compared with the widely used ensemble model, XGBoost, in differentiation of LDH and LSS using positive symptoms. This study presents a proof of concept for the application of NLP in prediagnosis of spine disease.

Machine learning methods to predict presence of residual cancer following hysterectomy

Surgical management for gynecologic malignancies often involves hysterectomy, often constituting the most common gynecologic surgery worldwide. Despite maximal surgical and medical care, gynecologic malignancies have a high rate of recurrence following surgery. Current machine learning models use advanced pathology data that is often inaccessible within low-resource settings and are specific to singular cancer types. There is currently a need for machine learning models to predict non-clinically evident residual disease using only clinically available health data. Here we developed and tested multiple machine learning models to assess the risk of residual disease post-hysterectomy based on clinical and operative parameters. Data from 3656 hysterectomy patients from the NSQIP dataset over 14 years were used to develop models with a training set of 2925 patients and a validation set of 731 patients. Our models revealed the top postoperative predictors of residual disease were the initial presence of gross abdominal disease on the diaphragm, disease located on the bowel mesentery, located on the bowel serosa, and disease located within the adjacent pelvis prior to resection. There were no statistically significant differences in performances of the top three models. Extreme gradient Boosting, Random Forest, and Logistic Regression models had comparable AUC ROC (0.90) and accuracy metrics (87–88%). Using these models, physicians can identify gynecologic cancer patients post-hysterectomy that may benefit from additional treatment. For patients at high risk for disease recurrence despite adequate surgical intervention, machine learning models may lay the basis for potential prospective trials with prophylactic/adjuvant therapy for non-clinically evident residual disease, particularly in under-resourced settings.

Postdiagnosis BMI Change Is Associated with Non-Small Cell Lung Cancer Survival

BACKGROUND

Body mass index (BMI) change after a lung cancer diagnosis has been associated with non-small cell lung cancer (NSCLC) survival. This study aimed to quantify the association based on a large-scale observational study.

METHODS

Included in the study were 7,547 patients with NSCLC with prospectively collected BMI data from Massachusetts General Hospital and Brigham and Women's Hospital/Dana-Farber Cancer Institute. Cox proportional hazards regression with time-dependent covariates was used to estimate effect of time-varying postdiagnosis BMI change rate (% per month) on overall survival (OS), stratified by clinical subgroups. Spline analysis was conducted to quantify the nonlinear association. A Mendelian Randomization (MR) analysis with a total of 3,495 patients further validated the association.

RESULTS

There was a J-shape association between postdiagnosis BMI change and OS among patients with NSCLC. Specifically, a moderate BMI decrease [0.5-2.0; HR = 2.45; 95% confidence interval (CI), 2.25-2.67] and large BMI decrease (≥2.0; HR = 4.65; 95% CI, 4.15-5.20) were strongly associated with worse OS, whereas moderate weight gain (0.5-2.0) reduced the risk for mortality (HR = 0.78; 95% CI, 0.68-0.89) and large weight gain (≥2.0) slightly increased the risk of mortality without reaching statistical significance (HR = 1.10; 95% CI, 0.86-1.42). MR analyses supported the potential causal roles of postdiagnosis BMI change in survival.

CONCLUSIONS

This study indicates that BMI change after diagnosis was associated with mortality risk.

IMPACT

Our findings, which reinforce the importance of postdiagnosis BMI surveillance, suggest that weight loss or large weight gain may be unwarranted.

Electronic tools in clinical laboratory diagnostics: key examples, limitations, and value in laboratory medicine

Electronic tools in clinical laboratory diagnostics can assist laboratory professionals, clinicians, and patients in medical diagnostic management and laboratory test interpretation. With increasing implementation of electronic health records (EHRs) and laboratory information systems worldwide, there is increasing demand for well-designed and evidence-based electronic resources. Both complex data-driven and simple interpretative electronic healthcare tools are currently available to improve the integration of clinical and laboratory information towards a more patient-centered approach to medicine. Several studies have reported positive clinical impact of electronic healthcare tool implementation in clinical laboratory diagnostics, including in the management of neonatal bilirubinemia, cardiac disease, and nutritional status. As patients have increasing access to their medical laboratory data, it is essential that accessible electronic healthcare tools are evidence-based and user-friendly for individuals of varying digital and medical literacy. Indeed, studies suggest electronic healthcare tool development processes significantly lack the involvement of relevant healthcare professionals and often present misinformation, including erroneous calculation algorithms or inappropriate interpretative recommendations. The current review provides an overview of the utility of available electronic healthcare tools in clinical laboratory diagnostics and critically reviews potential limitations and benefits of their clinical implementation. The Canadian Laboratory Initiative on Pediatric Reference Intervals (CALIPER) online database is also detailed as an example of a pediatric diagnostic tool with widespread global impact.