Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes

Undercounting diagnoses in Australian general practice: a data quality study with implications for population health reporting

BACKGROUND

Diagnosis can often be recorded in electronic medical records (EMRs) as free-text or using a term with a diagnosis code. Researchers, governments, and agencies, including organisations that deliver incentivised primary care quality improvement programs, frequently utilise coded data only and often ignore free-text entries. Diagnosis data are reported for population healthcare planning including resource allocation for patient care. This study sought to determine if diagnosis counts based on coded diagnosis data only, led to under-reporting of disease prevalence and if so, to what extent for six common or important chronic diseases.

METHODS

This cross-sectional data quality study used de-identified EMR data from 84 general practices in Victoria, Australia. Data represented 456,125 patients who attended one of the general practices three or more times in two years between January 2021 and December 2022. We reviewed the percentage and proportional difference between patient counts of coded diagnosis entries alone and patient counts of clinically validated free-text entries for asthma, chronic kidney disease, chronic obstructive pulmonary disease, dementia, type 1 diabetes and type 2 diabetes.

RESULTS

Undercounts were evident in all six diagnoses when using coded diagnoses alone (2.57-36.72% undercount), of these, five were statistically significant. Overall, 26.4% of all patient diagnoses had not been coded. There was high variation between practices in recording of coded diagnoses, but coding for type 2 diabetes was well captured by most practices.

CONCLUSION

In Australia clinical decision support and the reporting of aggregated patient diagnosis data to government that relies on coded diagnoses can lead to significant underreporting of diagnoses compared to counts that also incorporate clinically validated free-text diagnoses. Diagnosis underreporting can impact on population health, healthcare planning, resource allocation, and patient care. We propose the use of phenotypes derived from clinically validated text entries to enhance the accuracy of diagnosis and disease reporting. There are existing technologies and collaborations from which to build trusted mechanisms to provide greater reliability of general practice EMR data used for secondary purposes.

Impact of Medical-Pharmaceutical Separation Reform on Hospitalization Expenditure in Tertiary Public Hospitals: Difference-in-Difference Analysis Based on Panel Data from Beijing

Purpose

The medical-pharmaceutical separation (MPS) reform is a healthcare reform that focuses on reducing the proportion of drug expenditure. This study aims to analyze the impact of the MPS reform on hospitalization expenditure and its structure in tertiary public hospitals.

Methods

Using propensity score matching and multi-period difference-in-difference methods to analyze the impact of the MPS reform on hospitalization expenditure and its structure, a difference-in-difference-in-difference model was established to analyze the heterogeneity of whether the tertiary public hospital was a diagnosis-related-group (DRG) payment hospital. Of 22 municipal public hospitals offering tertiary care in Beijing, monthly panel data of 18 hospitals from July 2011 to March 2017, totaling 1242 items, were included in this study.

Results

After the MPS reform, the average drug expenditure, average Western drug expenditure, and average Chinese drug expenditures per hospitalization decreased by 24.5%, 24.6%, and 24.1%, respectively (P < 0.001). The proportions of drug expenditure decreased by 4.5% (P < 0.001), and the proportion of medical consumables expenditure increased significantly by 2.7% (P < 0.001).

Conclusion

The MPS reform may significantly optimize the hospitalization expenditure structure and control irrational increases in expenditure. DRG payment can control the tendency to increase the proportions of medical consumables expenditure after the reform and optimize the effect of the reform. There is a need to strengthen the management of medical consumables in the future, promote the MPS reform and DRG payment linkage, and improve supporting measures to ensure the long-term effect of the reform.

Evaluation of inpatient services of tertiary comprehensive hospitals based on DRG payment

Objective

This study aims to evaluate inpatient services in 49 tertiary comprehensive hospitals using indicators from the diagnosis related groups (DRG) payment system.

Method

DRG data from 49 tertiary comprehensive hospitals were obtained from the quality monitoring platform for provincial hospitals, and relevant indicators were identified. The analytic hierarchy process (AHP) was used to compute the weight of each indicator. The rank sum ratio method was used to calculate the weight rank sum ratio (WRSR) value and the corresponding probit value of each hospital. The hospitals were divided into four grades based on the threshold value: excellent, good, fair, and poor.

Results

Eight indicators of the 49 hospitals were scored, and the hospital rankings of indicators varied. The No. 1 hospital ranked first in the indicators of "total number of DRG", "number of groups", and "proportion of relative weights (RW) ≥ 2". The WRSR value of the No.1 hospital was the largest (0.574), and the WRSR value of the No. 44 hospital was the smallest (0.139). The linear regression equation was established: WRSRpredicted =-0.141+0.088*Probit, and the regression model was well-fitted (F = 2066.672, p < 0.001). The cut-off values of the three WRSRspredicted by the four levels were 0.167, 0.299, and 0.431, respectively. The 49 hospitals were divided into four groups: excellent (4), good (21), average (21), and poor (3). There were significant differences in the average WRSR values of four categories of hospitals (p < 0.05).

Conclusion

There were notable variances in the levels of inpatient services among 49 tertiary comprehensive hospitals, and hospitals of the same category also showed different service levels. The evaluation results contribute to the health administrative department and the hospital to optimize the allocation of resources, improve the DRG payment system, and enhance the quality and efficiency of inpatient services.

DRG-LLaMA : tuning LLaMA model to predict diagnosis-related group for hospitalized patients

In the U.S. inpatient payment system, the Diagnosis-Related Group (DRG) is pivotal, but its assignment process is inefficient. The study introduces DRG-LLaMA, an advanced large language model (LLM) fine-tuned on clinical notes to enhance DRGs assignment. Utilizing LLaMA as the foundational model and optimizing it through Low-Rank Adaptation (LoRA) on 236,192 MIMIC-IV discharge summaries, our DRG-LLaMA -7B model exhibited a noteworthy macro-averaged F1 score of 0.327, a top-1 prediction accuracy of 52.0%, and a macro-averaged Area Under the Curve (AUC) of 0.986, with a maximum input token length of 512. This model surpassed the performance of prior leading models in DRG prediction, showing a relative improvement of 40.3% and 35.7% in macro-averaged F1 score compared to ClinicalBERT and CAML, respectively. Applied to base DRG and complication or comorbidity (CC)/major complication or comorbidity (MCC) prediction, DRG-LLaMA achieved a top-1 prediction accuracy of 67.8% and 67.5%, respectively. Additionally, our findings indicate that DRG-LLaMA 's performance correlates with increased model parameters and input context lengths.

Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalities

OBJECTIVE

With the increasing amount and growing variety of healthcare data, multimodal machine learning supporting integrated modeling of structured and unstructured data is an increasingly important tool for clinical machine learning tasks. However, it is non-trivial to manage the differences in dimensionality, volume, and temporal characteristics of data modalities in the context of a shared target task. Furthermore, patients can have substantial variations in the availability of data, while existing multimodal modeling methods typically assume data completeness and lack a mechanism to handle missing modalities.

METHODS

We propose a Transformer-based fusion model with modality-specific tokens that summarize the corresponding modalities to achieve effective cross-modal interaction accommodating missing modalities in the clinical context. The model is further refined by inter-modal, inter-sample contrastive learning to improve the representations for better predictive performance. We denote the model as Attention-based cRoss-MOdal fUsion with contRast (ARMOUR). We evaluate ARMOUR using two input modalities (structured measurements and unstructured text), six clinical prediction tasks, and two evaluation regimes, either including or excluding samples with missing modalities.

RESULTS

Our model shows improved performances over unimodal or multimodal baselines in both evaluation regimes, including or excluding patients with missing modalities in the input. The contrastive learning improves the representation power and is shown to be essential for better results. The simple setup of modality-specific tokens enables ARMOUR to handle patients with missing modalities and allows comparison with existing unimodal benchmark results.

CONCLUSION

We propose a multimodal model for robust clinical prediction to achieve improved performance while accommodating patients with missing modalities. This work could inspire future research to study the effective incorporation of multiple, more complex modalities of clinical data into a single model.

Classification of neurologic outcomes from medical notes using natural language processing

Neurologic disability level at hospital discharge is an important outcome in many clinical research studies. Outside of clinical trials, neurologic outcomes must typically be extracted by labor intensive manual review of clinical notes in the electronic health record (EHR). To overcome this challenge, we set out to develop a natural language processing (NLP) approach that automatically reads clinical notes to determine neurologic outcomes, to make it possible to conduct larger scale neurologic outcomes studies. We obtained 7314 notes from 3632 patients hospitalized at two large Boston hospitals between January 2012 and June 2020, including discharge summaries (3485), occupational therapy (1472) and physical therapy (2357) notes. Fourteen clinical experts reviewed notes to assign scores on the Glasgow Outcome Scale (GOS) with 4 classes, namely 'good recovery', 'moderate disability', 'severe disability', and 'death' and on the Modified Rankin Scale (mRS), with 7 classes, namely 'no symptoms', 'no significant disability', 'slight disability', 'moderate disability', 'moderately severe disability', 'severe disability', and 'death'. For 428 patients' notes, 2 experts scored the cases generating interrater reliability estimates for GOS and mRS. After preprocessing and extracting features from the notes, we trained a multiclass logistic regression model using LASSO regularization and 5-fold cross validation for hyperparameter tuning. The model performed well on the test set, achieving a micro average area under the receiver operating characteristic and F-score of 0.94 (95% CI 0.93-0.95) and 0.77 (0.75-0.80) for GOS, and 0.90 (0.89-0.91) and 0.59 (0.57-0.62) for mRS, respectively. Our work demonstrates that an NLP algorithm can accurately assign neurologic outcomes based on free text clinical notes. This algorithm increases the scale of research on neurological outcomes that is possible with EHR data.

Challenges of implementing diagnostic-related groups and healthcare promotion in Iran: A strategic applied research

Background and Aim

Implementing the diagnostic-related groups (DRGs) promotes the efficiency of healthcare. Therefore, the present study aimed to identify the challenges facing implementing the DRGs in Iran.

Methods

The present study is a strategic applied research conducted in two phases. In the first phase, the challenges facing DRGs were extracted through a literature review. Then the collected data is entered into a checklist consisting of five sections including technological, cultural, organizational, strategic, and natural challenges. In the second phase, data were collected by purposive sampling and semistructured interviews with 10 managers of the Medical Services Organization of Tehran, Iran. Data analysis was performed by conventional content analysis using MAXQDA software and descriptive using SPSS software version 19.

Results

The challenges facing the implementing DGRs from the experts' perspective included technological, organizational, nature, strategic, and cultural in order of priority. The three main fundamental challenges were reported; lack of integrating the DGRs with health information system (70%), frequent changes of management (70%), reducing the quality of care following early patient discharge (60%).

Conclusion

The results of the present study showed that the DRG system faced with challenges and healthcare officials should apply policies and guidelines to reform the system before changing the reimbursement system in Iran. By considering the leading countries experiences in the nationalizing the DRG system field, the problems and solutions of the system can be identified and aid in the more successful implementation of these systems.

Optimizing the Implementation of Clinical Predictive Models to Minimize National Costs: Sepsis Case Study

BACKGROUND

Sepsis costs and incidence vary dramatically across diagnostic categories, warranting a customized approach for implementing predictive models.

OBJECTIVE

The aim of this study was to optimize the parameters of a sepsis prediction model within distinct patient groups to minimize the excess cost of sepsis care and analyze the potential effect of factors contributing to end-user response to sepsis alerts on overall model utility.

METHODS

We calculated the excess costs of sepsis to the Centers for Medicare and Medicaid Services (CMS) by comparing patients with and without a secondary sepsis diagnosis but with the same primary diagnosis and baseline comorbidities. We optimized the parameters of a sepsis prediction algorithm across different diagnostic categories to minimize these excess costs. At the optima, we evaluated diagnostic odds ratios and analyzed the impact of compliance factors such as noncompliance, treatment efficacy, and tolerance for false alarms on the net benefit of triggering sepsis alerts.

RESULTS

Compliance factors significantly contributed to the net benefit of triggering a sepsis alert. However, a customized deployment policy can achieve a significantly higher diagnostic odds ratio and reduced costs of sepsis care. Implementing our optimization routine with powerful predictive models could result in US $4.6 billion in excess cost savings for CMS.

CONCLUSIONS

We designed a framework for customizing sepsis alert protocols within different diagnostic categories to minimize excess costs and analyzed model performance as a function of false alarm tolerance and compliance with model recommendations. We provide a framework that CMS policymakers could use to recommend minimum adherence rates to the early recognition and appropriate care of sepsis that is sensitive to hospital department-level incidence rates and national excess costs. Customizing the implementation of clinical predictive models by accounting for various behavioral and economic factors may improve the practical benefit of predictive models.

Application of DRGs in hospital medical record management and its impact on service quality

BACKGROUND

To explore the application of diagnosis-related groups (DRGs) in hospital medical record management and the impact on service quality.

OBJECTIVE

This study introduced DGRs management into hospital medical record management in order to improve the quality of hospital medical record management.

METHOD

The medical record management of our hospital was analysed retrospectively between August 2020 and April 2021. A total of 7263 cases without DRG management before January 2021 were included in a control group, and 7922 cases with DRG management after January 2021 were included in a study group. The error rate of medical records, the specific error items and the scores of service capability, service efficiency and service quality were compared along with the comprehensive scores of the two groups.

RESULTS

The error rate of medical records in the study group was significantly lower than that in the control group (19.35% vs. 31.24%, P < 0.05). The error rates in terms of diagnosis on admission, surgical procedures, main diagnosis and other diagnoses in the study group were significantly lower than those in the control group. The scores for service ability, service efficiency and service quality were significantly higher in the study group than in the control group (P < 0.05). The comprehensive evaluation score of the study group was significantly higher than that of the control group (P < 0.01).

CONCLUSION

Applying DRGs in the hospital medical record management can effectively reduce the error rate of medical records and improve the quality of hospital services.

Enhancing Hospital-Wide Patient Flow to Reduce Emergency Department Crowding and Boarding

INTRODUCTION

ED overcrowding and boarding is a global phenomenon that negatively affects patients, hospital staff, and hospital-wide operations. Poor patient flow has been identified as a major contributing factor to ED overcrowding and boarding, which is directly linked to negative patient outcomes. This project implemented a multidisciplinary rounding team that addressed barriers to patient flow in real time. By reducing the inpatient length of stay bed capacity will improve, which in turn will help alleviate ED boarding and overcrowding.

METHODS

This before-and-after process improvement project took place on a 30-bed, inpatient medicine floor of a level-I trauma, tertiary, regional transfer center. Multidisciplinary rounding was used to improve care team communication and collaboration. Concepts from a Real-Time Demand Capacity model were used in this project to help develop a plan for capacity issues regarding bed supply and demand. Outcome variables included inpatient length of stay and ED boarding hours.

RESULTS

Implementation of multidisciplinary rounding resulted in a statistically significant reduction of 0.83 days in the length of stay for patients on this floor. By increasing inpatient bed capacity, ED boarding hours for patients targeted to the 3000-medicine floor was reduced by an average of 8.83 hours per month, a reduction > 50% from baseline.

DISCUSSION

Increasing inpatient bed capacity helps decrease ED access block, and contributes to reducing ED overcrowding. Implementing a daily multidisciplinary rounding structure on the inpatient floor helped hospital throughput by expediting discharges, which in turn created inpatient bed capacity.

A Machine Learning Approach for Predicting Readmission Charges Billed by Hospitals

Background

The Centers for Medicare and Medicaid Services projects that health care costs will continue to grow over the next few years. Rising readmission costs contribute significantly to increasing health care costs. Multiple areas of health care, including readmissions, have benefited from the application of various machine learning algorithms in several ways.

Objective

We aimed to identify suitable models for predicting readmission charges billed by hospitals. Our literature review revealed that this application of machine learning is underexplored. We used various predictive methods, ranging from glass-box models (such as regularization techniques) to black-box models (such as deep learning–based models).

Methods

We defined readmissions as readmission with the same major diagnostic category (RSDC) and all-cause readmission category (RADC). For these readmission categories, 576,701 and 1,091,580 individuals, respectively, were identified from the Nationwide Readmission Database of the Healthcare Cost and Utilization Project by the Agency for Healthcare Research and Quality for 2013. Linear regression, lasso regression, elastic net, ridge regression, eXtreme gradient boosting (XGBoost), and a deep learning model based on multilayer perceptron (MLP) were the 6 machine learning algorithms we tested for RSDC and RADC through 10-fold cross-validation.

Results

Our preliminary analysis using a data-driven approach revealed that within RADC, the subsequent readmission charge billed per patient was higher than the previous charge for 541,090 individuals, and this number was 319,233 for RSDC. The top 3 major diagnostic categories (MDCs) for such instances were the same for RADC and RSDC. The average readmission charge billed was higher than the previous charge for 21 of the MDCs in the case of RSDC, whereas it was only for 13 of the MDCs in RADC. We recommend XGBoost and the deep learning model based on MLP for predicting readmission charges. The following performance metrics were obtained for XGBoost: (1) RADC (mean absolute percentage error [MAPE]=3.121%; root mean squared error [RMSE]=0.414; mean absolute error [MAE]=0.317; root relative squared error [RRSE]=0.410; relative absolute error [RAE]=0.399; normalized RMSE [NRMSE]=0.040; mean absolute deviation [MAD]=0.031) and (2) RSDC (MAPE=3.171%; RMSE=0.421; MAE=0.321; RRSE=0.407; RAE=0.393; NRMSE=0.041; MAD=0.031). The performance obtained for MLP-based deep neural networks are as follows: (1) RADC (MAPE=3.103%; RMSE=0.413; MAE=0.316; RRSE=0.410; RAE=0.397; NRMSE=0.040; MAD=0.031) and (2) RSDC (MAPE=3.202%; RMSE=0.427; MAE=0.326; RRSE=0.413; RAE=0.399; NRMSE=0.041; MAD=0.032). Repeated measures ANOVA revealed that the mean RMSE differed significantly across models with P<.001. Post hoc tests using the Bonferroni correction method indicated that the mean RMSE of the deep learning/XGBoost models was statistically significantly (P<.001) lower than that of all other models, namely linear regression/elastic net/lasso/ridge regression.

Conclusions

Models built using XGBoost and MLP are suitable for predicting readmission charges billed by hospitals. The MDCs allow models to accurately predict hospital readmission charges.

"Note Bloat" impacts deep learning-based NLP models for clinical prediction tasks

One unintended consequence of the Electronic Health Records (EHR) implementation is the overuse of content-importing technology, such as copy-and-paste, that creates "bloated" notes containing large amounts of textual redundancy. Despite the rising interest in applying machine learning models to learn from real-patient data, it is unclear how the phenomenon of note bloat might affect the Natural Language Processing (NLP) models derived from these notes. Therefore, in this work we examine the impact of redundancy on deep learning-based NLP models, considering four clinical prediction tasks using a publicly available EHR database. We applied two deduplication methods to the hospital notes, identifying large quantities of redundancy, and found that removing the redundancy usually has little negative impact on downstream performances, and can in certain circumstances assist models to achieve significantly better results. We also showed it is possible to attack model predictions by simply adding note duplicates, causing changes of correct predictions made by trained models into wrong predictions. In conclusion, we demonstrated that EHR text redundancy substantively affects NLP models for clinical prediction tasks, showing that the awareness of clinical contexts and robust modeling methods are important to create effective and reliable NLP systems in healthcare contexts.

Tasks as needs: reframing the paradigm of clinical natural language processing research for real-world decision support

Electronic medical records are increasingly used to store patient information in hospitals and other clinical settings. There has been a corresponding proliferation of clinical natural language processing (cNLP) systems aimed at using text data in these records to improve clinical decision-making, in comparison to manual clinician search and clinical judgment alone. However, these systems have delivered marginal practical utility and are rarely deployed into healthcare settings, leading to proposals for technical and structural improvements. In this paper, we argue that this reflects a violation of Friedman's "Fundamental Theorem of Biomedical Informatics," and that a deeper epistemological change must occur in the cNLP field, as a parallel step alongside any technical or structural improvements. We propose that researchers shift away from designing cNLP systems independent of clinical needs, in which cNLP tasks are ends in themselves-"tasks as decisions"-and toward systems that are directly guided by the needs of clinicians in realistic decision-making contexts-"tasks as needs." A case study example illustrates the potential benefits of developing cNLP systems that are designed to more directly support clinical needs.

Clinical Coders' Perspectives on Pressure Injury Coding in Acute Care Services in Victoria, Australia

Pressure injuries (PIs) substantively impact quality of care during hospital stays, although only when they are severe or acquired as a result of the hospital stay are they reported as quality indicators. Globally, researchers have repeatedly highlighted the need to invest more in quality improvement, risk assessment, prevention, early detection, and care for PI to avoid the higher costs associated with treatment of PI. Coders' perspectives on quality assurance of the clinical coded PI data have never been investigated. This study aimed to explore challenges that hospital coders face in accurately coding and reporting PI data and subsequently, explore reasons why data sources may vary in their reporting of PI data. This article is based upon data collected as part of a multi-phase collaborative project to build capacity for optimizing PI prevention across Monash Partners health services. We have conducted 16 semi-structured phone interviews with clinical coders recruited from four participating health services located in Melbourne, Australia. One of the main findings was that hospital coders often lacked vital information in clinicians' records needed to code PI and report quality indicators accurately and highlighted the need for quality improvement processes for PI clinical documentation. Nursing documentation improvement is a vital component of the complex capacity building programs on PI prevention in acute care services and is relied on by coders. Coders reported the benefit of inter-professional collaborative workshops, where nurses and coders shared their perspectives. Collaborative workshops had the potential to improve coders' knowledge of PI classification and clinicians' understanding of what information should be included when documenting PI in the medical notes. Our findings identified three methods of quality assurance were important to coders to ensure accuracy of PI reporting: (1) training prior to initiation of coding activity and (2) continued education, and (3) audit and feedback communication about how to handle specific complex cases and complex documentation. From a behavioral perspective, most of the coders reported confidence in their own abilities and were open to changes in coding standards. Transitioning from paper-based to electronic records highlighted the need to improve training of both clinicians and coders.

Adjuvant osimertinib treatment in patients with early stage NSCLC (IB-IIIA): pathological pathway adaptations

Non-small cell lung cancer (NSCLC) is the most common type of lung cancer. Around 30% of patients are diagnosed with early disease and 60% after the tumour has spread to a different part of the body. The earlier NSCLC is diagnosed, the better the chances of prolonging survival. Recent years have seen striking improvements in cancer treatment outcomes through increased use of molecular diagnostics. Therapy decisions are now based on a combination of genetic testing and genetically matched targeted therapies. The positive results obtained with the use of tyrosine kinase inhibitors (TKIs), including osimertinib, in the metastatic disease, coupled with recent data in early stage disease support the importance of molecular testing in this setting. In this overview we discuss factors paramount in pathological pathways to ensure optimal management of early stage NSCLC and also provide an overview of requirements/recommendations. Critical issues in the pre-analytical phases regarding both cytology/biopsy samples and surgically resected tissues are highlighted and solutions are proposed to guarantee accuracy, adequacy and sustainability in the innovative approach to be introduced in clinical practice for NSCLC patients.

Estimation and Prediction of Hospitalization and Medical Care Costs Using Regression in Machine Learning

Medical costs are one of the most common recurring expenses in a person’s life. Based on different research studies, BMI, ageing, smoking, and other factors are all related to greater personal medical care costs. The estimates of the expenditures of health care related to obesity are needed to help create cost-effective obesity prevention strategies. Obesity prevention at a young age is a top concern in global health, clinical practice, and public health. To avoid these restrictions, genetic variants are employed as instrumental variables in this research. Using statistics from public huge datasets, the impact of body mass index (BMI) on overall healthcare expenses is predicted. A multiview learning architecture can be used to leverage BMI information in records, including diagnostic texts, diagnostic IDs, and patient traits. A hierarchy perception structure was suggested to choose significant words, health checks, and diagnoses for training phase informative data representations, because various words, diagnoses, and previous health care have varying significance for expense calculation. In this system model, linear regression analysis, naive Bayes classifier, and random forest algorithms were compared using a business analytic method that applied statistical and machine-learning approaches. According to the results of our forecasting method, linear regression has the maximum accuracy of 97.89 percent in forecasting overall healthcare costs. In terms of financial statistics, our methodology provides a predictive method.

Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods

BACKGROUND

Identifying patients at a high risk of psychosis relapse is crucial for early interventions. A relevant psychiatric clinical context is often recorded in clinical notes; however, the utilization of unstructured data remains limited. This study aimed to develop psychosis-relapse prediction models using various types of clinical notes and structured data.

METHODS

Clinical data were extracted from the electronic health records of the Ajou University Medical Center in South Korea. The study population included patients with psychotic disorders, and outcome was psychosis relapse within 1 year. Using only structured data, we developed an initial prediction model, then three natural language processing (NLP)-enriched models using three types of clinical notes (psychological tests, admission notes, and initial nursing assessment) and one complete model. Latent Dirichlet Allocation was used to cluster the clinical context into similar topics. All models applied the least absolute shrinkage and selection operator logistic regression algorithm. We also performed an external validation using another hospital database.

RESULTS

A total of 330 patients were included, and 62 (18.8%) experienced psychosis relapse. Six predictors were used in the initial model and 10 additional topics from Latent Dirichlet Allocation processing were added in the enriched models. The model derived from all notes showed the highest value of the area under the receiver operating characteristic (AUROC = 0.946) in the internal validation, followed by models based on the psychological test notes, admission notes, initial nursing assessments, and structured data only (0.902, 0.855, 0.798, and 0.784, respectively). The external validation was performed using only the initial nursing assessment note, and the AUROC was 0.616.

CONCLUSIONS

We developed prediction models for psychosis relapse using the NLP-enrichment method. Models using clinical notes were more effective than models using only structured data, suggesting the importance of unstructured data in psychosis prediction.

How Would Medicaid Expansion Affect Texas Hospitals? Evidence From a Retrospective Quasi-Experimental Study

This study aims to estimate the impact of a potential Medicaid expansion on Texas hospitals. The Affordable Care Act (ACA) Medicaid expansion increased access to health care and improved health outcomes. Still, several states, including Texas, have not adopted the expansion. This is a retrospective quasi-experimental study. We obtained inpatient data containing discharges from Texas hospitals between 2010 and 2017 from the Texas Department of State Health Services. Texas hospitals receive a significant number of patients from the adjacent states. We use a difference-in-differences methodology, where the patients from the neighboring states that expanded Medicaid in 2014 are the treatment group, and those that reside in Texas are the control group. The outcome variables are the payer mix and the cost of treatment, proxied by Diagnoses Related Group (DRG) weights assigned by the Centers for Medicare and Medicaid Services (CMS). The Medicaid expansion is associated with 4.15% lower costs of treatment among the patients from the expansion states (P < .01). Also, the uninsured rate decreased by 4.7 percentage points (from 11.3%, P < .01), while the share of Medicaid patients increased by 10.9 percentage points (from 30.7%, P < .01). There are no significant changes in the share of privately insured or Medicare patients. Texas hospitals can benefit significantly from Medicaid expansion due to reductions in average treatment costs and the share of the uninsured.

DeepDRG: Performance of Artificial Intelligence Model for Real-Time Prediction of Diagnosis-Related Groups

Nowadays, the use of diagnosis-related groups (DRGs) has been increased to claim reimbursement for inpatient care. The overall benefits of using DRGs depend upon the accuracy of clinical coding to obtain reasonable reimbursement. However, the selection of appropriate codes is always challenging and requires professional expertise. The rate of incorrect DRGs is always high due to the heavy workload, poor quality of documentation, and lack of computer assistance. We therefore developed deep learning (DL) models to predict the primary diagnosis for appropriate reimbursement and improving hospital performance. A dataset consisting of 81,486 patients with 128,105 episodes was used for model training and testing. Patients' age, sex, drugs, diseases, laboratory tests, procedures, and operation history were used as inputs to our multiclass prediction model. Gated recurrent unit (GRU) and artificial neural network (ANN) models were developed to predict 200 primary diagnoses. The performance of the DL models was measured by the area under the receiver operating curve, precision, recall, and F1 score. Of the two DL models, the GRU method, had the best performance in predicting the primary diagnosis (AUC: 0.99, precision: 83.2%, and recall: 66.0%). However, the performance of ANN model for DRGs prediction achieved AUC of 0.99 with a precision of 0.82 and recall of 0.57. The findings of our study show that DL algorithms, especially GRU, can be used to develop DRGs prediction models for identifying primary diagnosis accurately. DeepDRGs would help to claim appropriate financial incentives, enable proper utilization of medical resources, and improve hospital performance.