BMC Medical Informatics and Decision Making最新文献

Background: Machine Learning (ML) plays a crucial role in biomedical research. Nevertheless, it still has limitations in data integration and irreproducibility. To address these challenges, robust methods are needed. Pancreatic ductal adenocarcinoma (PDAC), a highly aggressive cancer with low early detection rates and survival rates, is used as a case study. PDAC lacks reliable diagnostic biomarkers, especially metastatic biomarkers, which remains an unmet need. In this study, we propose an ML-based approach for discovering disease biomarkers, apply it to the identification of a PDAC metastatic composite biomarker candidate, and demonstrate the advantages of harnessing data resources.

Methods: We utilised primary tumour RNAseq data from five public repositories, pooling samples to maximise statistical power and integrating data by correcting for technical variance. Data were split into train and validation sets. The train dataset underwent variable selection via a 10-fold cross-validation process that combined three algorithms in 100 models per fold. Genes found in at least 80% of models and five folds were considered robust to build a consensus multivariate model. A random forest model was constructed using selected genes from the train dataset and tested in the validation set. We also assessed the goodness of prediction by recalibrating a model using only the validation data. The biological context and relevance of signals was explored through enrichment and pathway analyses using QIAGEN Ingenuity Pathway Analysis and GeneMANIA.

Results: We developed a pipeline that can detect robust signatures to build composite biomarkers. We tested the pipeline in PDAC, exploiting transcriptomics data from different sources, proposing a composite biomarker candidate comprised of fifteen genes consistently selected that showed very promising predictive capability. Biological contextualisation revealed links with cancer progression and metastasis, underscoring their potential relevance. All code is available in GitHub.

Conclusion: This study establishes a robust framework for identifying composite biomarkers across various disease contexts. We demonstrate its potential by proposing a plausible composite biomarker candidate for PDAC metastasis. By reusing data from public repositories, we highlight the sustainability of our research and the wider applications of our pipeline. The preliminary findings shed light on a promising validation and application path.

Background: Because spontaneous remission is common in IMN, and there are adverse effects of immunosuppressive therapy, it is important to assess the risk of progressive loss of renal function before deciding whether and when to initiate immunosuppressive therapy. Therefore, this study aimed to establish a risk prediction model to predict patient prognosis and treatment response to help clinicians evaluate patient prognosis and decide on the best treatment regimen.

Methods: From September 2019 to December 2020, a total of 232 newly diagnosed IMN patients from three hospitals in Liaoning Province were enrolled. Logistic regression analysis selected the risk factors affecting the prognosis, and a dynamic online nomogram prognostic model was constructed based on extreme gradient boost, random forest, logistic regression machine learning algorithms. Receiver operating characteristic and calibration curves and decision curve analysis were utilized to assess the performance and clinical utility of the developed model.

Results: A total of 130 patients were in the training cohort and 102 patients in the validation cohort. Logistic regression analysis identified four risk factors: course ≥ 6 months, UTP, D-dimer and sPLA2R-Ab. The random forest algorithm showed the best performance with the highest AUROC (0.869). The nomogram had excellent discrimination ability, calibration ability and clinical practicability in both the training cohort and the validation cohort.

Conclusions: The dynamic online nomogram model can effectively assess the prognosis and treatment response of IMN patients. This will help clinicians assess the patient's prognosis more accurately, communicate with the patient in advance, and jointly select the most appropriate treatment plan.

Background: Digital health is being used as an accelerator to improve the traditional healthcare system, aiding countries in achieving their sustainable development goals. Burkina Faso aims to harmonize its digital health interventions to guide its digital health strategy for the coming years. The current assessment represents upstream work to steer the development of this strategic plan.

Methods: This was a quantitative, descriptive study conducted between September 2022 and April 2023. It involved a two-part survey: a self-administered questionnaire distributed to healthcare information managers in facilities, and direct interviews conducted with software developers. This was complemented by a documentary review of the country's strategic and standards documents on digital transformation.

Results: Burkina Faso possesses a relatively comprehensive collection of governance documents pertaining to digital transformation. The study identified a total of 35 digital health interventions. Analysis showed that 89% of funding originated from technical and financial partners as well as the private sector. While the use of open-source technologies for the development of the applications, software, or platforms used to implement these digital health interventions is well established (77%), there remains a deficiency in the integration of data from different platforms. Furthermore, the classification of digital health interventions revealed an uneven distribution between the different elements across domains: the health system, the classification of digital health interventions (DHI), and the subsystems of the National Health Information System (NHIS). Most digital health intervention projects are still in the pilot phase (66%), with isolated electronic patient record initiatives remaining incomplete. Within the public sector, these records typically take the form of electronic registers or isolated specialty records in a hospital. Within the private sector, tool implementation varies based on expressed needs. Challenges persist in adhering to interoperability norms and standards during tool design, with minimal utilization of the data generated by the implemented tools.

Conclusion: This study provides an insightful overview of the digital health environment in Burkina Faso and highlights significant challenges regarding intervention strategies. The findings serve as a foundational resource for developing the digital health strategic plan. By addressing the identified shortcomings, this plan will provide a framework for guiding future digital health initiatives effectively.

Hematoma expansion (HE) is a high risky symptom with high rate of occurrence for patients who have undergone spontaneous intracerebral hemorrhage (ICH) after a major accident or illness. Correct prediction of the occurrence of HE in advance is critical to help the doctors to determine the next step medical treatment. Most existing studies focus only on the occurrence of HE within 6 h after the occurrence of ICH, while in reality a considerable number of patients have HE after the first 6 h but within 24 h. In this study, based on the medical doctors recommendation, we focus on prediction of the occurrence of HE within 24 h, as well as the occurrence of HE every 6 h within 24 h. Based on the demographics and computer tomography (CT) image extraction information, we used the XGBoost method to predict the occurrence of HE within 24 h. In this study, to solve the issue of highly imbalanced data set, which is a frequent case in medical data analysis, we used the SMOTE algorithm for data augmentation. To evaluate our method, we used a data set consisting of 582 patients records, and compared the results of proposed method as well as few machine learning methods. Our experiments show that XGBoost achieved the best prediction performance on the balanced dataset processed by the SMOTE algorithm with an accuracy of 0.82 and F1-score of 0.82. Moreover, our proposed method predicts the occurrence of HE within 6, 12, 18 and 24 h at the accuracy of 0.89, 0.82, 0.87 and 0.94, indicating that the HE occurrence within 24 h can be predicted accurately by the proposed method.

Background: Artificial intelligence (AI) has become a pivotal tool in advancing contemporary personalised medicine, with the goal of tailoring treatments to individual patient conditions. This has heightened the demand for access to diverse data from clinical practice and daily life for research, posing challenges due to the sensitive nature of medical information, including genetics and health conditions. Regulations like the Health Insurance Portability and Accountability Act (HIPAA) in the U.S. and the General Data Protection Regulation (GDPR) in Europe aim to strike a balance between data security, privacy, and the imperative for access.

Results: We present the Gemelli Generator - Real World Data (GEN-RWD) Sandbox, a modular multi-agent platform designed for distributed analytics in healthcare. Its primary objective is to empower external researchers to leverage hospital data while upholding privacy and ownership, obviating the need for direct data sharing. Docker compatibility adds an extra layer of flexibility, and scalability is assured through modular design, facilitating combinations of Proxy and Processor modules with various graphical interfaces. Security and reliability are reinforced through components like Identity and Access Management (IAM) agent, and a Blockchain-based notarisation module. Certification processes verify the identities of information senders and receivers.

Conclusions: The GEN-RWD Sandbox architecture achieves a good level of usability while ensuring a blend of flexibility, scalability, and security. Featuring a user-friendly graphical interface catering to diverse technical expertise, its external accessibility enables personnel outside the hospital to use the platform. Overall, the GEN-RWD Sandbox emerges as a comprehensive solution for healthcare distributed analytics, maintaining a delicate equilibrium between accessibility, scalability, and security.

Purpose: Symptom assessment is central to appropriate adenomyosis management. Using a WeChat mini-program-based portal, we aimed to establish a valid symptom assessment scale of adenomyosis (AM-SAS) to precisely and timely identify needs of symptom management and ultimately, to alert disease recurrence.

Methods: A combination of intensive interviews of patients with adenomyosis and natural language processing on WeChat clinician-patient group communication was used to generate a pool of symptom items-related to adenomyosis. An expert panel shortened the list to form the provisional AM-SAS. The AM-SAS was built in a Wechat mini-programmer and sent to patients to exam the psychotically validity and clinical applicability through classic test theory and item response theory.

Results: Total 338 patients with adenomyosis (29 for interview, 179 for development, and 130 for external validation) and 86 gynecologists were included. The over 90% compliance to the WeChat-based symptom evaluate. The AM-SAS demonstrated the uni-dimensionality through Rasch analysis, good internal consistency (all Cronbach's alphas above 0.8), and test-retest reliability (intraclass correlation coefficients ranging from 0.65 to 0.84). Differences symptom severity score between patients in the anemic and normal hemoglobin groups (3.04 ± 3.17 vs. 5.68 ± 3.41, P < 0.001). In external validation, AM-SAS successfully detected differences in symptom burden and physical status between those with or without relapse.

Conclusion: Electronic PRO-based AM-SAS is a valuable instrument for monitoring AM-related symptoms. As an outcome measure of multiple symptoms in clinical trials, the AM-SAS may identify patients who need extensive care after discharge and capture significant beneficial changes of patients may have been overlooked.

Trial registration: This trial was approved by the institutional review board of the Chongqing Medical University and three participating hospitals (Medical Ethics Committee of Nanchong Central Hospital, Medical Ethics Committee of Affiliated Hospital of Southwest Medical University, and Medical Ethics Committee of Haifu Hospital) and registered in the Chinese Clinical Trial Registry (registration number ChiCTR2000038590), date of registration was 26/10/2020.

Background: Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible due to privacy concerns and parties are unable to engage in centrally coordinated joint computation. We study the feasibility of combining privacy preserving synthetic data sets in place of the original data for collaborative learning on real-world health data from the UK Biobank.

Methods: We perform an empirical evaluation based on an existing prospective cohort study from the literature. Multiple parties were simulated by splitting the UK Biobank cohort along assessment centers, for which we generate synthetic data using differentially private generative modelling techniques. We then apply the original study's Poisson regression analysis on the combined synthetic data sets and evaluate the effects of 1) the size of local data set, 2) the number of participating parties, and 3) local shifts in distributions, on the obtained likelihood scores.

Results: We discover that parties engaging in the collaborative learning via shared synthetic data obtain more accurate estimates of the regression parameters compared to using only their local data. This finding extends to the difficult case of small heterogeneous data sets. Furthermore, the more parties participate, the larger and more consistent the improvements become up to a certain limit. Finally, we find that data sharing can especially help parties whose data contain underrepresented groups to perform better-adjusted analysis for said groups.

Conclusions: Based on our results we conclude that sharing of synthetic data is a viable method for enabling learning from sensitive data without violating privacy constraints even if individual data sets are small or do not represent the overall population well. Lack of access to distributed sensitive data is often a bottleneck in biomedical research, which our study shows can be alleviated with privacy-preserving collaborative learning methods.

Background: Pattern mining techniques are helpful tools when extracting new knowledge in real practice, but the overwhelming number of patterns is still a limiting factor in the health-care domain. Current efforts concerning the definition of measures of interest for patterns are focused on reducing the number of patterns and quantifying their relevance (utility/usefulness). However, although the temporal dimension plays a key role in medical records, few efforts have been made to extract temporal knowledge about the patient's evolution from multivariate sequential patterns.

Methods: In this paper, we propose a method to extract a new type of patterns in the clinical domain called Jumping Diagnostic Odds Ratio Sequential Patterns (JDORSP). The aim of this method is to employ the odds ratio to identify a concise set of sequential patterns that represent a patient's state with a statistically significant protection factor (i.e., a pattern associated with patients that survive) and those extensions whose evolution suddenly changes the patient's clinical state, thus making the sequential patterns a statistically significant risk factor (i.e., a pattern associated with patients that do not survive), or vice versa.

Results: The results of our experiments highlight that our method reduces the number of sequential patterns obtained with state-of-the-art pattern reduction methods by over 95%. Only by achieving this drastic reduction can medical experts carry out a comprehensive clinical evaluation of the patterns that might be considered medical knowledge regarding the temporal evolution of the patients. We have evaluated the surprisingness and relevance of the sequential patterns with clinicians, and the most interesting fact is the high surprisingness of the extensions of the patterns that become a protection factor, that is, the patients that recover after several days of being at high risk of dying.

Conclusions: Our proposed method with which to extract JDORSP generates a set of interpretable multivariate sequential patterns with new knowledge regarding the temporal evolution of the patients. The number of patterns is greatly reduced when compared to those generated by other methods and measures of interest. An additional advantage of this method is that it does not require any parameters or thresholds, and that the reduced number of patterns allows a manual evaluation.

Background: Cesarean section-induced postpartum hemorrhage (PPH) potentially causes anemia and hypovolemic shock in pregnant women. Hence, it is helpful for obstetricians and anesthesiologists to prepare pre-emptive prevention when predicting PPH occurrence in advance. However, current works on PPH prediction focus on whether PPH occurs rather than assessing PPH amount. To this end, this work studies quantitative PPH prediction with machine learning (ML).

Methods: The study cohort in this paper was selected from individuals with PPH who were hospitalized at Shijiazhuang Obstetrics and Gynecology Hospital from 2020 to 2022. In this study cohort, we built a dataset with 6,144 subjects covering clinical parameters, anesthesia operation records, laboratory examination results, and other information in the electronic medical record system. Based on our built dataset, we exploit six different ML models, including logistic regression, linear regression, gradient boosting, XGBoost, multilayer perceptron, and random forest, to automatically predict the amount of bleeding during cesarean section. Eighty percent of the dataset was used as model training, and 20 $\%$ was used for verification. Those ML models are constantly verified and improved by root mean squared error(RMSE) and mean absolute error(MAE). Moreover, we also leverage the importance of permutation and partial dependence plot (PDP) to discuss their feasibility.

Result: The experiment results show that random forest obtains the highest accuracy for PPH amount prediction compared to other ML methods. Random forest reaches the mean absolute error of 21.7, less than 5.4 $\%$ prediction error. It also gains the root mean squared error of 33.75, less than 9.3 $\%$ prediction error. On the other hand, the experimental results also disclose indicators that contributed most to PPH prediction, including Ca, hemoglobin, white blood cells, platelets, Na, and K.

Conclusion: It effectively predicts the amount of PPH during a cesarean section by ML methods, especially random forest. With the above insight, ML predicting PPH amounts provides early warning for clinicians, thus reducing complications and improving cesarean sections' safety. Furthermore, the importance of ML and permutation, complemented by incorporating PDP, promises to provide clinicians with a transparent indication of individual risk prediction.