Cited by 269Machine Learning in HealthcareNursing Diagnosis and DocumentationElectronic Health Records Systems

The DOI matches its Crossref record; 34 of the 35 references it cites were found in a registry or an index.

Combining structured and unstructured data for predictive models: a deep learning approach

Open access

Zhang, Dongdong, Yin, Changchang, Zeng, Jucheng, Yuan, Xiaohui, Zhang, Ping·2020·BMC Medical Informatics and Decision Making

DOI 10.1186/s12911-020-01297-6PMC PMC7596962

Published version of a preprint

Open this paper in CoChat — free account Open PDF

Abstract

BACKGROUND: The broad adoption of electronic health records (EHRs) provides great opportunities to conduct health care research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. However, while many research studies utilize temporal structured data on predictive modeling, they typically neglect potentially valuable information in unstructured clinical notes. Integrating heterogeneous data types across EHRs through deep learning techniques may help improve the performance of prediction models. METHODS: In this research, we proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data. The proposed fusion models leverage document embeddings for the representation of long clinical note documents and either convolutional neural network or long short-term memory networks to model the sequential clinical notes and temporal signals, and one-hot encoding for static information representation. The concatenated representation is the final patient representation which is used to make predictions. RESULTS: We evaluate the performance of proposed models on 3 risk prediction tasks (i.e. in-hospital mortality, 30-day hospital readmission, and long length of stay prediction) using derived data from the publicly available Medical Information Mart for Intensive Care III dataset. Our results show that by combining unstructured clinical notes with structured data, the proposed models outperform other models that utilize either unstructured notes or structured data only. CONCLUSIONS: The proposed fusion models learn better patient representation by combining structured and unstructured data. Integrating heterogeneous data types across EHRs helps improve the performance of prediction models and reduce errors.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Integrity signals

Registry

Crossref · 10.1186/s12911-020-01297-6

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Fig. 1 Architecture of CNN-based fusion-CNN. Fusion-CNN uses document embeddings, 2-layer CNN and max-pooling to model sequential clinical notes. Similarly, 2-layer CNN and max-pooling are used to model temporal signals. The final patient representation is the concatenation of the latent representation of sequential clinical notes, temporal signals, and the static information vector. Then the final patient representation is passed to output layers to make predictionsCC BY · PubMed Central

Fig. 2 Architecture of LSTM-based Fusion-LSTM. Fusion-LSTM uses document embeddings, a BiLSTM layer, and a max-pooling layer to model sequential clinical notes. 2-layer LSTMs are used to model temporal signals. The concatenated patient representation is passed to output layers to make predictionsCC BY · PubMed Central

Fig. 3 Comparison of model running time with different inputsCC BY · PubMed Central

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Deep learning
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“, logistic regression and random forest) with scikit-learn [32].”
Background
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“Deep learning models are implemented using PyTorch [33].”
Method
Occurrence of the potent mutagens 2- nitrobenzanthrone and 3-nitrobenzanthrone in fine airborne particles
Santos, A. G., da Rocha, G. O., & de Andrade, J. B. (2019) · Scientific Reports · doi:10.1038/s41598-018-37186-2 · Cited by 8,495
MIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141
Distributed Representations of Sentences and DocumentsPreprint
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 7,905 · cited 1×
“Doc2Vec) [30] to learn the embedding of each clinical note.”
Background
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058
Software Framework for Topic Modelling with Large Corpora
Rek, R. R. U., & Sojka, P. (2010) · doi:10.13140/2.1.2393.1847 · Cited by 3,789
Scalable and accurate deep learning with electronic health records
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0029-1 · Cited by 2,648
Scalable and accurate deep learning with electronic health records.
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · eScholarship (California Digital Library) · Cited by 2,242

Show all 35 references

Research works printed but not linked: 3

Henry J, Pylypchuk Y, Searcy T, Patel V. Adoption of electronic health record systems among US non-federal acute care hospitals: 2008–2015. ONC Data Brief. 2016;35:1–9.
Ghassemi M, Naumann T, Joshi R, Rumshisky A. Topic models for mortality modeling in intensive care units. In: ICML machine learning for clinical data analysis workshop; 2012. p. 1–4.
Hackbarth G, Reischauer R, Miller M. Report to the congress: promoting greater efficiency in medicare. Washington, DC: MedPAC; 2007.

Sorted by citations

Items 101–200 of 268

Statistics in enabling 2D materials: Optimization, predictive modelling, and data-driven discovery
Abifarin, J. K., & Lu, Y. (2025) · Materials Today Physics · doi:10.1016/j.mtphys.2025.101814 · Cited by 10
From Web to RheumaLpack: Creating a Linguistic Corpus for Exploitation and Knowledge Discovery in Rheumatology
Madrid-García, A., Barbancho, B. M., Freites, D., Rodríguez‐Rodríguez, L., Menasalvas, E., Rodríguez‐González, A., & Peñas, A. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108920 · Cited by 8
Length of stay prediction for hospital management using domain adaptation
Momo, L. N. W., Moorosi, N., Nsoesie, E. O., Rademakers, F. E., & Moor, B. D. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108088 · Cited by 10
Disambiguating Clinical Abbreviations by One-to-All Classification: Algorithm Development and Validation Study
Sung, S., Hu, Y., & Chen, C.-Y. (2024) · JMIR Medical Informatics · doi:10.2196/56955 · Cited by 10
Towards Interpretable Multimodal Predictive Models for Early Mortality Prediction of Hemorrhagic Stroke Patients.
Emdad, F. B., Tian, S., Nandy, E., Hanna, K., & He, Z. (2023) · PubMed Central · Cited by 9
Machine learning models in clinical practice for the prediction of postoperative complications after major abdominal surgery
Stam, W. T., Ingwersen, E. W., Ali, M., Spijkerman, J. T., Geert Kazemier, M., Bruns, E. R. J., & Daams, F. D. (2023) · Surgery Today · doi:10.1007/s00595-023-02662-4 · Cited by 14
“With unstructured data in particular, such as data from electronic health records and computed tomography or magnetic resonance imaging, ML models show their superiority [50].”
Method
Enhancing heart failure diagnosis through multi-modal data integration and deep learning
Liu, Y., Li, D., Zhao, J., & Liang, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17716-5 · Cited by 8
“In [25], a deep learning-based multimodal neural network is introduced for risk prediction tasks.”
Innovation through Artificial Intelligence in Triage Systems for Resource Optimization in Future Pandemics
Garrido, N. J., González-Martínez, F., Losada, S., Plaza, A., Carrillo, E. D. O., & Mateo, J. (2024) · Biomimetics · doi:10.3390/biomimetics9070440 · Cited by 8
“…[46,47], Gaussian Naive Bayes (GNB) [48–50], K-Nearest Neighbors (KNNs) [51–53], Support Vector Machines (SVMs) [54–56], Neural Networks (NNs) [57,58], Random forest (RF) [59–61], the Convolutional Neural Network (CNN) [62,63], AdaBoost [64,65], and the novel method proposed in this study [66–69].”
Method
Predicting 30-day hospital readmissions using ClinicalT5 with structured and unstructured electronic health records
Pandey, S. R., Tile, J. D., & Oghaz, M. M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0328848 · Cited by 14
“Notably, the performance of our model exceeds that of the study by [45].”
Empowering text classification with NLP and explainable AI for enhanced interpretability
Mustafa, S. K., & Saeed, M. H. (2025) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-025-00273-2 · Cited by 8
“For the research in 2020 and onward, a multi-model of CNN LSTM and Bio-BERT were proposed for biomedical text mining and [18, 19].”
Automated algorithm for medical data structuring, and segmentation using artificial intelligence within secured environment for dataset creation
Nainamalai, V., Qair, H. A., Pelanis, E., Jenssen, H. B., Fretland, Å. A., Edwin, B., Elle, O. J., & Balasingham, I. (2024) · European Journal of Radiology Open · doi:10.1016/j.ejro.2024.100582 · Cited by 8
Hospital Readmission Prediction Using Clinical Admission Notes
Thapa, N. B., Seifollahi, S., & Taheri, S. (2022) · Australasian Computer Science Week Multiconference (ACSW) · doi:10.1145/3511616.3513115 · Cited by 9
“The BoW model is considered as a strong baseline representation used in downstream clinical tasks such as predicting early mortality risk, length of stay, and hospital readmission[19, 32].”
BackgroundMethod
Predicting Student Performance Through Classroom Concentration: A Review on Machine Learning and Computer Vision Approaches
Umar, U. S., Rana, M. E., & Hameed, V. A. (2023) · IEEE Student Conference on Research and Development (SCOReD) · doi:10.1109/scored60679.2023.10563245 · Cited by 7
“On the other hand, neural networks, particularly deep learning models, excel at processing unstructured data, including images and sequences, allowing them to extract intricate patterns and representations [31].”
BackgroundMethod
DR-Z2AN: dual-recurrent neural network with a tri-channel attention mechanism for financial management prediction
Knifo, S., & Alzubi, A. B. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01613-x · Cited by 7
“Zhang et al. [29] implemented a fusion-based model that combined the beneﬁts of a fused LSTM and CNN model and provided accurate prediction.”
The multifactorial nature of Alzheimer’s disease: A review of diverse determinants and the essential role of multimodal machine learning
Mostaghimi, H., Cohen, D. A., Okhravi, H. R., Niknejad, B., & Audette, M. A. (2025) · Archives of Gerontology and Geriatrics Plus · doi:10.1016/j.aggp.2025.100207 · Cited by 7
Multimodal Clinical Prediction with Unified Prompts and Pretrained Large-Language Models
Winston, C., Winston, C., Winston, C., Winston, C., & Winston, C. (2024) · 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi61247.2024.00108 · Cited by 6
“…monitoring, and the electronic health record (EHR) - to assist in tasks ranging from determining patient acuity in the emergency department to predicting patient outcomes, such as length of stay, probability of hospital readmission, and risk of speciﬁc diseases like asthma exacerbations [1]– [4].”
Background
Artificial Intelligence in Cardiovascular Medicine: Focus on Hypertension
Varzideh, F., Mone, P., Kansakar, U., Pande, S., Jankauskas, S. S., & Santulli, G. (2026) · Hypertension · doi:10.1161/hypertensionaha.126.26094 · Cited by 6
Machine Learning Model to Predict Postmastectomy Breast Reconstruction Complications
Shaheen, M. S., McManus, B. T., Cullen, C. M., Chen, J., Momeni, A., Kuo, C., Tsai, P.-H., & Chung, K. C. (2026) · JAMA Network Open · doi:10.1001/jamanetworkopen.2026.7232 · Cited by 6
Deep learning for multisource medical information processing
Gezimati, M., & Singh, G. K. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-313233-9.00009-6 · Cited by 6
Heart failure prognosis prediction: Let’s start with the MDL-HFP model
Ma, H., Li, D., Fu, J., Zhao, G., & Zhao, J. (2024) · Information Systems · doi:10.1016/j.is.2024.102408 · Cited by 6
Integrating Structured and Unstructured Data with BERTopic and Machine Learning: A Comprehensive Predictive Model for Mortality in ICU Heart Failure Patients
Wu, S., Li, C., Chien, T.-N., & Chu, C.-M. (2024) · Applied Sciences · doi:10.3390/app14177546 · Cited by 8
Hospital Length of Stay Prediction Based on Multi-modal Data Towards Trustworthy Human-AI Collaboration in Radiomics
Baniecki, H., Sobieski, B., Bombiński, P., Szatkowski, P., & Biecek, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-34344-5_9 · Cited by 6
Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study
Huang, Y., Zheng, Z., Ma, M., Xin, X., Liu, H., Fei, X., Wei, L., & Chen, H. (2022) · Journal of Medical Internet Research · doi:10.2196/37486 · Cited by 6
“Our finding is similar to the results of other studies [39,40].”
Result
Characterizing the clinical profile and prevalence of people with diabetes attended in the hospital setting by using unstructured healthcare data and natural language processing: the Diabetic@ study
Blanco-Carrasco, A. J., Merino-Torres, J. F., Rubio-Almanza, M., Molina, G. C., Brito-Sanfiel, M. Á., Galindo, D. E. B., Olmedo, L. A. C., Mauricio, D., Tofé, S., Barro, J. A. B., et al. (2025) · Diabetes Research and Clinical Practice · doi:10.1016/j.diabres.2025.112214 · Cited by 5
Heterogeneous graph neural network-based prediction of immune-related adverse events
He, X., Ni, Q., Cui, C., Li, H., Ni, L., Zhou, J., Tang, L., & Peng, B. (2025) · Scientific Reports · doi:10.1038/s41598-025-30266-0 · Cited by 7
Towards Accurate and Reliable ICU Outcome Prediction: A Multimodal Learning Framework Based on Belief Function Theory using Structured EHRs and Free-Text Notes
Ruan, Y., Tan, D. J., Ng, S. K., Huang, L., & Feng, M. (2025) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-025-00219-3 · Cited by 11
“In this study, we focus on Nursing , Nursing/Other , Physician , and Radiology notes, as these comprise the majority of clinical documentation and are frequently recorded in the MIMIC-III database [12].”
AI-Powered Predictive Modeling to Optimize Pharmaceutical Formulation and Precise Drug Delivery in Modified Release Tablets
Singh, P. K., Kumar, V., Parihar, A., Shah, K., & Dewangan, H. K. (2025) · Journal of Pharmaceutical Innovation · doi:10.1007/s12247-025-10283-2 · Cited by 5
SimSUM – simulated benchmark with structured and unstructured medical records
Rabaey, P., Heytens, S., & Demeester, T. (2025) · Journal of Biomedical Semantics · doi:10.1186/s13326-025-00341-6 · Cited by 11
“Electronic health records (EHRs) are a gold mine of information, containing a mix of structured tabular variables 1 (medication, diagnosis codes, lab results. . . ) and free unstructured text (detailed clinical notes from physicians, nurses. . . ) (Ford et al. 2016).”
Influential
SGIR: Star Graph-Based Interaction for Efficient and Robust Multimodal Representation
Ding, Z., Lan, G., Song, Y., & Yang, Z. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3321404 · Cited by 5
“Following the previous works [24], [26], [41], we apply the preprocessing and unimodal encoding of raw features for different datasets.”
BackgroundMethodInfluential
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
Molaei, S., Bousejin, N. G., Ghosheh, G. O., Thakur, A., Chauhan, V. K., Zhu, T., & Clifton, D. A. (2024) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-024-00169-2 · Cited by 5
AI-aided dynamic prediction of bleeding and ischemic risk after coronary stenting and subsequent DAPTPreprint
Li, F., Rasmy, L., Yang, X., Feng, J., Du, J., Aguilar, D. A., Dhoble, A., Wang, Q., Niu, S., Hu, X., et al. (2022) · medRxiv · doi:10.1101/2022.02.05.22270508 · Cited by 6
“Further, we will integrate multi-modal data (such as unstructured clinical notes) as complementary information to enhance patient representation learning (48).”
Transforming primary healthcare through natural language processing and big data analytics
Uddin, Y., Nair, A., Shariq, S., & Hannan, S. H. (2023) · BMJ · doi:10.1136/bmj.p948 · Cited by 5
Leveraging BERT for embedding ICD codes from large scale cardiovascular EMR data to understand patient diagnostic patterns
Kim, M. K., Kim, Y., Kang, H. J., Seo, H., Choi, H., Han, J., Kee, G., Ko, S., Jung, H., Kim, B., et al. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03145-x · Cited by 4
“Future research should focus on incorporating broader datasets, exploring alternative coding systems, and including additional patient data types to develop more comprehensive and accurate prediction models [55].”
Machine Learning Approaches for Segmentation of Cardiovascular Neurocristopathy Related Images
Iqbal, T., Soliman, O. I. I., Sultan, S., & Ullah, I. (2023) · IEEE Access · doi:10.1109/access.2023.3325960 · Cited by 7
TransformerFusionNet: A Real-Time Multimodal Framework for ICU Heart Failure Mortality Prediction Using Big Data Streaming
Saleh, H., McCann, M., El–Sappagh, S., & Breslin, J. G. (2024) · International Conference on Computer and Applications (ICCA) · doi:10.1109/icca62237.2024.10927742 · Cited by 5
Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
Rasheed, N., Khaliq, U., Ahmed, A., & Bermak, A. (2025) · IEEE Access · doi:10.1109/access.2025.3601117 · Cited by 4
“Zhang et al. [35] have performed three prediction tasks: in-hospital mortality, 30-day hospital readmission, and length of stay from the MIMIC-III dataset.”
Mortality prediction for ICU patients with mental disorders using large language models ensemble and unstructured medical notes
Nazih, W., Abuhmed, T., Alharbi, M., & El–Sappagh, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0332134 · Cited by 5
“However, integrating structured and unstructured electronic health record (EHR) data has proven critical for predicting ICU patient mortality [48].”
A comparison of attentional neural network architectures for modeling with electronic medical records
Finch, A., Crowell, A., Chang, Y.-C., Parameshwarappa, P., Martinez, J., & Horberg, M. A. (2021) · JAMIA Open · doi:10.1093/jamiaopen/ooab064 · Cited by 7
“Some studies have also examined provider notes and demonstrated significant utility from this data, although it is often much less structured and may contain similar content to the semistructured diagnostic information provided by medical entities.(10) Beginning with techniques such as Med2Vec, it has become standard…”
Method
Enabling Timely Medical Intervention by Exploring Health-Related Multivariate Time Series with a Hybrid Attentive Model
Xie, J., Wang, Z., Yu, Z., & Guo, B. (2022) · Sensors · doi:10.3390/s22166104 · Cited by 4
“Recently, a set of models had been proposed to combine vital physiological time series with demographic information (including age, gender, lab test results and so on) to provide clinical predictions [30,61].”
Background
A Cloudy Crystal Ball: Critically Assessing and Rethinking the Antibiogram
MacDougall, C. (2023) · Clinical Infectious Diseases · doi:10.1093/cid/ciad468 · Cited by 4
Integration of text-mining and telemedicine appointment optimization
Ji, M., Mosaffa, M., Ardestani-Jaafari, A., Li, J., & Peng, C. L. (2023) · Annals of Operations Research · doi:10.1007/s10479-023-05660-4 · Cited by 4
“For instance, Baechle et al. (2020) and Zhang et al. (2020) utilize unstructured data as the primary data source to provide a much richer understanding of healthcare decision-making problems.”
Enhancing Suicide Attempt Risk Prediction Models with Temporal Clinical Note Features
Krause, K. J., Davis, S. E., Yin, Z., Schafer, K. M., Rosenbloom, S. T., & Walsh, C. G. (2024) · Applied Clinical Informatics · doi:10.1055/a-2411-5796 · Cited by 4
“18, 19,”
Deep learning-based mortality surveillance: implications for healthcare policy and practice
Rakhmawan, S. A., Mahmood, T. A., & Abbas, N. (2024) · Journal of Population Research · doi:10.1007/s12546-024-09358-7 · Cited by 4
“Segmentation of other groups, such as patients in the ICU, is also an issue raised in modeling mortality using deep learning methods (Zeng et al., 2023; Zhang et al., 2020).”
Artificial intelligence platform to predict children's hospital care for respiratory disease using clinical, pollution, and climatic factors
Cabral‐Miranda, W., Beloni, C., Lora, F. M., Afonso, R., Araújo, T., & Fernandes, F. R. (2025) · Journal of Global Health · doi:10.7189/jogh.15.04207 · Cited by 4
“Recent advances in ML have shown great promise in health care, particularly in predicting clinical outcomes such as morbidity, hospital readmission, and mortality [ 5 , 6 ].”
Harvesting social media with artificial intelligence for medical threats mapping and analytics
David, W., King‐Okoye, M., Capone, A., Sensidoni, G., & Piovan, S. (2021) · Proceedings of the ICA · doi:10.5194/ica-proc-4-24-2021 · Cited by 4
“This helps with the development of predictive and reasoning models that can be run against all the relevant features (Zhang et al., 2020).”
Background
Multi-modal fusion model for Time-Varying medical Data: Addressing Long-Term dependencies and memory challenges in sequence fusion
Ma, M., Wang, M., Wei, L., Fei, X., & Chen, H. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104823 · Cited by 3
Predicting Extracorporeal Shock Wave Lithotripsy Outcomes Using Machine Learning and the Triple-/Quadruple-D Scores
Gelmiş, M., Kardaş, S., Ayten, A., Cura, O., Gönültaş, S., & Köse, M. G. (2025) · Journal of College of Physicians And Surgeons Pakistan · doi:10.29271/jcpsp.2025.08.1007 · Cited by 3
Explainable multimodal deep learning models for variable-length sequences in critically ill patients
Martin, J., Afshar, M., Afshar, A. S., Caskey, J., Dligach, D., Gao, Y., Gao, J., Chen, G., Mayampurath, A. M., & Churpek, M. M. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105001 · Cited by 4
Artificial Intelligence Support to the Paradigm Shift from Reactive to Anticipatory Action in Humanitarian Responses
David, W., Garmendia-Doval, B., & King‐Okoye, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-31268-7_9 · Cited by 3
TGRA-P: Task-driven model predicts 90-day mortality from ICU clinical notes on mechanical ventilation
Zou, B., Ding, Y., Li, J., Yu, B., & Kui, X. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107783 · Cited by 3
Artificial Intelligence (AI) and Machine Learning (ML): An Innovative Cross-Talk Perspective and Their Role in the Healthcare Industry
Sharma, R., Gulati, A., & Chopra, K. (2023) · Springer eBooks · doi:10.1007/978-981-99-6472-7_2 · Cited by 4
Deep Learning Based Satellite Image Segmentation Analyzes for Coastal Flood Disaster
Hayatunnufus, H., Candra, A., Slamet, B., Jaya, I., Wilson, & Syadzwana, H. (2024) · International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM) · doi:10.1109/elticom64085.2024.10864384 · Cited by 3
Data Imputation Based on Retrieval-Augmented Generation
Shi, X., Wang, J., Chung, G., Julian, D., & Qiao, L. (2025) · Applied Sciences · doi:10.3390/app15137371 · Cited by 4
Development and implementation of centralised, cloud-based, employee health contact tracing database and predictive modelling framework in the COVID-19 pandemic
Rabii, K. B., Javaid, W., & Nabeel, I. (2022) · The Lancet Digital Health · doi:10.1016/s2589-7500(22)00171-6 · Cited by 3
Optimization of Dynamic Pricing Models for Consumer Segmentation Markets and Analysis of Big Data-Driven Marketing Strategies
Zhang, Q., Qiang, S., Alataş, B., & Yuan, Y.-H. (2025) · Journal of Organizational and End User Computing · doi:10.4018/joeuc.368840 · Cited by 2
Machine learning models for predicting survival in lung cancer patients undergoing microwave ablation
Liu, Y., Wang, Z., Cao, X., Liu, M., & Zhong, L. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1561083 · Cited by 2
Automated Risk Prediction of Post-Stroke Adverse Mental Outcomes Using Deep Learning Methods and Sequential Data
Oei, C. W., Ng, E. Y. K., Ng, M. H. S., Chan, Y. M., Subbhuraam, V., Chan, L. G., & Acharya, U. R. (2025) · Bioengineering · doi:10.3390/bioengineering12050517 · Cited by 2
“…such as longitudinal clinical variables such as daily lab results (e.g., white blood count, C-reactive protein, etc.), which are modeled using DL algorithms to capture temporal trends and interactions, hypothesising that including data from various data types leads to better model performance [33].”
Towards Privacy-Preserving Big Data Analysis With Decentralized Learning for ROP Imaging
Mahrous, F. M., Abu-Leif, H. A., Modyiq, T. A., AlGhamdi, H. M., AlSaedi, K. S., & Algamdi, A. M. (2025) · International Conference on Innovation in Artificial Intelligence and Internet of Things (AIIT) · doi:10.1109/aiit63112.2025.11082911 · Cited by 2
“In parallel, the role of big data analytics in health-care has been extensively examined and analyzed [22]–[24], emphasizing its potential in processing vast volumes of structured and unstructured data [25].”
Heat syndrome types prediction of traditional Chinese medicine in acute ischemic stroke through deep learning: a pilot study
Yu, X., He, L., Wang, Q., Zhang, Z., Zhu, H., & Song, J. (2025) · Frontiers in Pharmacology · doi:10.3389/fphar.2025.1601601 · Cited by 2
“Previous studies have employed CNN to predict clinical outcomes such as in-hospital mortality using structured data (Zhang et al., 2020).”
The challenges of using electronic medical records (EMR) to facilitate guideline-directed medical therapy (GDMT) for patients with heart failure (HF) and chronic kidney disease (CKD)
Desai, N. R., Ahmad, T., & Wilson, F. P. (2025) · Heart Failure Reviews · doi:10.1007/s10741-025-10564-5 · Cited by 4
A New Paradigm of Large-model Collaborative Digital-intelligent Decision-making：Key Mechanisms and Future Prospects
Kou, G., Tang, X., Chen, X., Wang, X., & Chang, J. (2025) · 中国科学基金 · doi:10.3724/bnsfc-2025.07.14.0001 · Cited by 2
A survey of the use of EHR as real-world evidence for discovering and validating new drug indications
Talukdar, N., Zhang, X., Paithankar, S., Wang, H., & Chen, B. (2025) · Drug Discovery Today · doi:10.1016/j.drudis.2025.104552 · Cited by 2
Developing a Suicide Risk Prediction Algorithm Using Electronic Health Record Data in Mental Health Care: Real-World Case Study
Hummel, L., Lorenz-Artz, K. C. A. G., Bierbooms, J. J. P. A., & Bongers, I. M. B. (2025) · JMIR Medical Informatics · doi:10.2196/74240 · Cited by 4
The Role of Artificial Intelligence in Reducing Dispensing Errors for Patient Safety and Quality: A Systems Approach
Ouda, E., Chaabi, I. M., Abualola, H., Ramadan, M. A., Patro, P. K., Kaya, G. K., & Simsekler, M. C. E. (2026) · Risk Management and Healthcare Policy · doi:10.2147/rmhp.s573762 · Cited by 2
“38,44 In parallel, transparency, ethics, and governance must be embedded throughout the model lifecycle: explainability, auditability, and systematic bias assessment should accompany data protection, access control, and incident-response mechanisms, with clearly delineated accountability for…”
An Artificial Intelligence and Simulation Approach to Climate-Conflict-Migration Driven Security Issues
David, W., King‐Okoye, M., Mugambwa, I., & Garmendia-Doval, B. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-26754-3_13 · Cited by 2
Clinical Reasoning over Tabular Data and Text with Bayesian Networks
Rabaey, P., Deleu, J., Heytens, S., & Demeester, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66538-7_24 · Cited by 3
Disease Phenotype Classification Model Based on Multi-channel Deep Supervised Bi-LSTM
Wang, D., Zou, C. R., Wei, Z., & Zhong, Z. (2024) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea62105.2024.10603967 · Cited by 2
“The dataset was divided into training and testing sets following a ratio of 85% to 15%, like previous studies [19] .”
Method
NLP Based Prediction of Hospital Readmission using ClinicalBERT and Clinician Notes
Matondora, L., Mutandavari, M., & Mupini, B. (2024) · International Journal of Innovative Science and Research Technology (IJISRT) · doi:10.38124/ijisrt/ijisrt24jul1191 · Cited by 2
“[17]”
Remaining Life Prediction of Automatic Fare Collection Systems from the Perspective of Sustainable Development: A Sparse and Weak Feature Fault Data-Based Approach
Xiong, J., Sun, Y., Xu, Z., Wan, Y., & Yu, G. (2024) · Sustainability · doi:10.3390/su17010230 · Cited by 2
Predicting Robotic Hysterectomy Incision Time: Optimizing Surgical Scheduling with Machine Learning
Shah, V., Yung, H. C., Yang, J. C., Zaslavsky, J. M., Algarroba, G. N., Pullano, A., Karpel, H. C., Munoz, N. E., Aphinyanaphongs, Y., Saraceni, M., et al. (2024) · JSLS Journal of the Society of Laparoscopic & Robotic Surgeons · doi:10.4293/jsls.2024.00040 · Cited by 2
Data-Driven Decision Management: Multi-Modal Analytics in a Health Case Study
Agomuo, O. C., Khan, Z., Otuomasirichi, A. I., Uzoma, A. K., & Muzamal, J. H. (2025) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom64595.2025.10857526 · Cited by 2
Enhancing futures price forecasting with large-scale text feature extraction and compressed hybrid data-driven modeling
Zhu, L., Liu, H., Zhao, J., Liang, K., Zhou, L., & Yang, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127357 · Cited by 4
Healing with hierarchy: Hierarchical attention empowered graph neural networks for predictive analysis in medical data
Gupta, S., Sharma, S., Sharma, R. K., & Chandra, J. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103134 · Cited by 3
Operationalizing a Medical Intelligence Platform for Humanitarian Security in Protracted Crises
David, W., King‐Okoye, M., Sensidoni, G., Capone, A., Mugambwa, I., Kraynova, S., & Garmendia-Doval, B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98260-7_25 · Cited by 2
Video-based AI Decision Support System for Lifting Risk Assessment
Zhou, G., Aggarwal, V., Yin, M., & Yu, D. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9659025 · Cited by 2
“Since structured data with domain-speciﬁed features can still be widely observed in various healthcare settings [20], both LIME and SHAP have been widely used in healthcare AI applications, such as risk detection and disease diagnoses (e.g., [21], [22]).”
Method
Improving information fusion on multimodal clinical data in classification settings
Jha, S., Mayer, E. K., & Barahona, M. (2022) · International Workshop on Health Text Mining and Information Analysis (LOUHI) · doi:10.18653/v1/2022.louhi-1.18 · Cited by 2
“There are also available comparisons against baseline logistic regression and random forest models in (Zhang et al., 2020).”
Result
Convolutional Neural Network Based Predictive Framework for Intensive Care Unit Readmission
Rasheed, N., Akram, M. U., & Zeb, J. (2024) · International Conference on Advancements in Computational Sciences (ICACS) · doi:10.1109/icacs60934.2024.10473298 · Cited by 2
“Zhang, D., et al. [34] have performed three prediction tasks including in-hospital mortality, 30-day hospital readmission, and long length of stay using MIMIC-III dataset.”
Method
Knowledge Guided Multi-filter Residual Convolutional Neural Network for ICD Coding from Clinical TextPreprint
Boukhers, Z., Goswami, P., & Jürjens, J. (2022) · Research Square · doi:10.21203/rs.3.rs-1873701/v1 · Cited by 2
MuST: Multimodal Spatiotemporal Graph-Transformer for Hospital Readmission Prediction
Miao, Y., & Yu, L. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-47425-5_25 · Cited by 1
Personalized insights into liver disease management: a text mining analysis of online consultation data
Xiang, K., & Shi, D. (2025) · Frontiers in Public Health · doi:10.3389/fpubh.2025.1467117 · Cited by 1
The incremental value of unstructured data via natural language processing in machine learning-based COVID-19 mortality prediction: a comparative study
da Silva, R. P., & Pazin‐Filho, A. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03178-2 · Cited by 1
“…unstructured data led to improved model metrics, particularly in terms of sensitivity for four of the six models tested, the head-to-head comparison revealed that none of these performance gains were statistically significant, a finding that contradicts results presented by other authors [19, 44].”
Influential
Multimodal Prediction of Renal Tumor Malignancy From Radiology Reports and Structured Electronic Health Records: Retrospective Cohort Study
Fan, Z., Liang, R., Sun, C., Pan, J., Terry, R. S., & Xu, J. (2026) · JMIR Medical Informatics · doi:10.2196/84396 · Cited by 1
Deep Learning in the Design of Nanoparticle-based Drug Formulations
Pawar, M. K., Joshi, S., Bhandari, R. B., Jagadish, S., M, V. T. R. P. K., & Karthikayen, A. (2025) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc65114.2025.11212406 · Cited by 1
“[24] Deep Learning (CNN + NLP for text mining) Improved predictive accuracy by integrating chemical structures with literature text; enabled better decision-making in drug formulation.”
ICU-Length of Stay Prediction on Electronic Health Records using Graph Neural Networks and Homogeneous Similarity Graphs
Musawi, A. F. A., Rana, P., Raha, S., Braunstein, J. A., Sleeman, W. C., Kapoor, R., & Ghosh, P. (2025) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3765612.3767211 · Cited by 1
“Zhang et al. [23] further incorporated clinical notes using CNNs, LSTMs, and Doc2Vec embeddings.”
The evolution of accountancy research: A systematic literature review of trends from 1995 to 2025
Dunakhir, S., & Idrus, M. (2025) · Multidisciplinary Reviews · doi:10.31893/multirev.2026329 · Cited by 2
“(Zhang et al., 2020; Landers & Behrend, 2023) How can unstructured data be reliably incorporated into forecasting models?”
IoT based athlete physical training improves metabolic obesity symptoms: Muscle thermal energy consumption
Zhe, J. (2026) · Archives of Physiology and Biochemistry · doi:10.1080/13813455.2025.2610477 · Cited by 1
A fusion model of multimodal data based on cooperative attention for diagnosing occupational pneumoconiosis
Zhao, Q., Guo, Y., Gong, D., & Jin, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109850 · Cited by 1
Predicting Mortality and Readmission in Obstructive Sleep Apnea via LLM-Expanded Clinical Concepts
Ahmed, A., Rispoli, A., Wasieloski, C., Khurram, I., Zamora‐Resendiz, R., Morrow, D., Dong, A., & Crivelli, S. N. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10030097 · Cited by 1
“Recent studies have shown that unstructured clinical notes improve the prediction of mortality and hospital readmission [12,13].”
A Theoretical and Methodological Review of the Data Fusion Process: Architectures, Algorithms, and Challenges
KACAR, A., & Türkoğlu, İ. (2026) · Türk doğa ve fen dergisi :/Türk doğa ve fen dergisi · doi:10.46810/tdfd.1783115 · Cited by 1
Predicting Laboratory Test Ordering in Emergency Departments Using Integrated Structured and Unstructured Electronic Health Records: Machine Learning Study
Zhang, X., Ling, H., Zhang, X., & Zhang, A. (2026) · JMIR Medical Informatics · doi:10.2196/85255 · Cited by 1
“Notably, such a finding builds on and further affirms the existing methodological literature suggesting the potential of combining structured and unstructured data [28,29].”
The expanding role of artificial intelligence in medical diagnosis: from molecular diagnostics and multi-omics to digital health and medical imaging
Ramezani, A., Bagheri, M., Mahmoudian, F., Fattahi, F., ghahroodi, F. N., Nasirmoghadas, P., Pourzardosht, N., Khalesi, B., Hashemi, Z. S., & Khalili, S. (2026) · Expert Review of Molecular Diagnostics · doi:10.1080/14737159.2026.2706000 · Cited by 1
“Also, most of the information in EHRs is recorded as unstructured data, like narrative reports and clinical notes, whereas a smaller fraction is structured data, such as vital signs, patient demographics, and lab test results [111].”
An Introduction to Quantitative Portfolio Management and Risk Management
Zhang, Q. T., Li, B., & Xie, D. (2022) · Palgrave studies in risk and insurance · doi:10.1007/978-3-031-11612-4_1 · Cited by 1
Automatic retrieval of health case reports for public needs using deep learning techniques
Liu, Y.-H., Chen, S.-F., & Wen, D.-W. (2023) · Aslib Journal of Information Management · doi:10.1108/ajim-01-2023-0002 · Cited by 2
SAFE : Unsupervised image feature extraction using self‐attention based feature extraction network
Choi, Y. J., Lee, G. T., & Kim, C. O. (2024) · Expert Systems · doi:10.1111/exsy.13583 · Cited by 1
Research on Key Technologies of Deep Learning Techniques in Unstructured Data Processing
Zhang, G., Cheng-li, F., & Zhou, H. (2024) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns-2024-3175 · Cited by 1
Data Flow-Based Strategies to Improve the Interpretation and Understanding of Machine Learning Models
Brimacombe, M. B. (2024) · Bioengineering · doi:10.3390/bioengineering11121189 · Cited by 3
“These procedures and related tagging/keyword search procedures have been applied to a wide variety of data [7].”
Understanding deep learning models for Length of Stay prediction on critically ill patients through latent space visualization
Momo, L. N. W., Scheltjens, V., Verbeke, W., Rademakers, F. E., & Moor, B. D. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108832 · Cited by 1
Personalized insights into urinary tract infection management: A text mining analysis of online consultation data
Tang, R., Zhu, P., Yan, R., Zhou, Y., Tang, Z., & He, W. (2025) · Digital Health · doi:10.1177/20552076251393289 · Cited by 1
“Extracting meaningful, clinically relevant insights necessitates sophisticated computational methods for knowledge extraction and interpretation, 24 which have historically been lacking.”
MiPy: A Framework for Benchmarking Machine Learning Prediction of Unplanned Hospital and ICU Readmission in the MIMIC-IV DatabasePreprint
Partovi, A., Lukose, D., & Webb, G. I. (2022) · Research Square · doi:10.21203/rs.3.rs-2100869/v1 · Cited by 1
Integrative Analysis of Neuroimaging and Microbiome Data Predicts Cognitive Decline in Parkinson’s DiseasePreprint
Delice, B., Nalbantoğlu, Ö. U., & Yıldırım, S. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.03.28.645180 · Cited by 1

Authors: Zhang, D., Yin, C., Zeng, J., Yuan, X., & Zhang, P.
Affiliations: Wuhan University of Technology (CN)
The Ohio State University (US)
Corresponding author: Zhang, Ping
ORCID: Zhang, Dongdong
Yin, Changchang
Yuan, Xiaohui
Zhang, Ping
Venue: BMC Medical Informatics and Decision Making
Publisher: Springer Science and Business Media LLC
Published: 2020-10-29
Volume: 20
Issue: 1
Pages: 280-280
ISSN: 1472-6947 (ISSN-L)
DOI: 10.1186/s12911-020-01297-6
PMC: PMC7596962
OpenAlex: W3095791468
Cited by: 269
References: 35
Citations by year: 2026: 41 · 2025: 72 · 2024: 52 · 2023: 52 · 2022: 34 · 2021: 18
FWCI: 10.13
Type: journal article
Language: en
Open access: gold
doi.org
Licence: cc-by
creativecommons.org/licenses/by/4.0/ (tdm)
creativecommons.org/licenses/by/4.0/ (vor)
Locations: BMC Medical Informatics and Decision Making (publishedVersion, cc-by)
medRxiv (acceptedVersion, cc-by-nc-nd)
PubMed Central (publishedVersion, cc-by)
PubMed (publishedVersion)
DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Health Sciences › Nursing › Research and Theory › Nursing Diagnosis and Documentation
Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
Keywords: electronic health records, unstructured clinical notes, multimodal neural networks, patient representation learning, in-hospital mortality prediction, hospital readmission prediction, length of stay prediction, MIMIC-III, clinical risk prediction
MeSH terms: Machine Learning, Deep Learning, Humans, Patient Readmission, Neural Networks, Computer, Electronic Health Records

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Combining structured and unstructured data for predictive models: a deep learning approach

Abstract

Overview

Integrity signals

Figures

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks