1
|
Marcinkevičs R, Reis Wolfertstetter P, Klimiene U, Chin-Cheong K, Paschke A, Zerres J, Denzinger M, Niederberger D, Wellmann S, Ozkan E, Knorr C, Vogt JE. Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitis. Med Image Anal 2024; 91:103042. [PMID: 38000257 DOI: 10.1016/j.media.2023.103042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2023] [Revised: 11/10/2023] [Accepted: 11/20/2023] [Indexed: 11/26/2023]
Abstract
Appendicitis is among the most frequent reasons for pediatric abdominal surgeries. Previous decision support systems for appendicitis have focused on clinical, laboratory, scoring, and computed tomography data and have ignored abdominal ultrasound, despite its noninvasive nature and widespread availability. In this work, we present interpretable machine learning models for predicting the diagnosis, management and severity of suspected appendicitis using ultrasound images. Our approach utilizes concept bottleneck models (CBM) that facilitate interpretation and interaction with high-level concepts understandable to clinicians. Furthermore, we extend CBMs to prediction problems with multiple views and incomplete concept sets. Our models were trained on a dataset comprising 579 pediatric patients with 1709 ultrasound images accompanied by clinical and laboratory data. Results show that our proposed method enables clinicians to utilize a human-understandable and intervenable predictive model without compromising performance or requiring time-consuming image annotation when deployed. For predicting the diagnosis, the extended multiview CBM attained an AUROC of 0.80 and an AUPR of 0.92, performing comparably to similar black-box neural networks trained and tested on the same dataset.
Collapse
Affiliation(s)
- Ričards Marcinkevičs
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zürich, 8092, Switzerland.
| | - Patricia Reis Wolfertstetter
- Department of Pediatric Surgery and Pediatric Orthopedics, Hospital St. Hedwig of the Order of St. John of God, University Children's Hospital Regensburg (KUNO), Steinmetzstrasse 1-3, Regensburg, 93049, Germany; Faculty of Medicine, University of Regensburg, Franz-Josef-Strauss-Allee 11, Regensburg, 93053, Germany.
| | - Ugne Klimiene
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zürich, 8092, Switzerland
| | - Kieran Chin-Cheong
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zürich, 8092, Switzerland
| | - Alyssia Paschke
- Faculty of Medicine, University of Regensburg, Franz-Josef-Strauss-Allee 11, Regensburg, 93053, Germany
| | - Julia Zerres
- Faculty of Medicine, University of Regensburg, Franz-Josef-Strauss-Allee 11, Regensburg, 93053, Germany
| | - Markus Denzinger
- Department of Pediatric Surgery and Pediatric Orthopedics, Hospital St. Hedwig of the Order of St. John of God, University Children's Hospital Regensburg (KUNO), Steinmetzstrasse 1-3, Regensburg, 93049, Germany; Faculty of Medicine, University of Regensburg, Franz-Josef-Strauss-Allee 11, Regensburg, 93053, Germany
| | - David Niederberger
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zürich, 8092, Switzerland
| | - Sven Wellmann
- Faculty of Medicine, University of Regensburg, Franz-Josef-Strauss-Allee 11, Regensburg, 93053, Germany; Division of Neonatology, Hospital St. Hedwig of the Order of St. John of God, University Children's Hospital Regensburg (KUNO), Steinmetzstrasse 1-3, Regensburg, 93049, Germany
| | - Ece Ozkan
- Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, 43 Vassar Street, Cambridge, 02139, USA
| | - Christian Knorr
- Department of Pediatric Surgery and Pediatric Orthopedics, Hospital St. Hedwig of the Order of St. John of God, University Children's Hospital Regensburg (KUNO), Steinmetzstrasse 1-3, Regensburg, 93049, Germany
| | - Julia E Vogt
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zürich, 8092, Switzerland.
| |
Collapse
|
2
|
Marx A, Di Stefano F, Leutheuser H, Chin-Cheong K, Pfister M, Burckhardt MA, Bachmann S, Vogt JE. Blood glucose forecasting from temporal and static information in children with T1D. Front Pediatr 2023; 11:1296904. [PMID: 38155742 PMCID: PMC10752933 DOI: 10.3389/fped.2023.1296904] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/21/2023] [Accepted: 11/27/2023] [Indexed: 12/30/2023] Open
Abstract
Background The overarching goal of blood glucose forecasting is to assist individuals with type 1 diabetes (T1D) in avoiding hyper- or hypoglycemic conditions. While deep learning approaches have shown promising results for blood glucose forecasting in adults with T1D, it is not known if these results generalize to children. Possible reasons are physical activity (PA), which is often unplanned in children, as well as age and development of a child, which both have an effect on the blood glucose level. Materials and Methods In this study, we collected time series measurements of glucose levels, carbohydrate intake, insulin-dosing and physical activity from children with T1D for one week in an ethics approved prospective observational study, which included daily physical activities. We investigate the performance of state-of-the-art deep learning methods for adult data-(dilated) recurrent neural networks and a transformer-on our dataset for short-term (30 min) and long-term (2 h) prediction. We propose to integrate static patient characteristics, such as age, gender, BMI, and percentage of basal insulin, to account for the heterogeneity of our study group. Results Integrating static patient characteristics (SPC) proves beneficial, especially for short-term prediction. LSTMs and GRUs with SPC perform best for a prediction horizon of 30 min (RMSE of 1.66 mmol/l), a vanilla RNN with SPC performs best across different prediction horizons, while the performance significantly decays for long-term prediction. For prediction during the night, the best method improves to an RMSE of 1.50 mmol/l. Overall, the results for our baselines and RNN models indicate that blood glucose forecasting for children conducting regular physical activity is more challenging than for previously studied adult data. Conclusion We find that integrating static data improves the performance of deep-learning architectures for blood glucose forecasting of children with T1D and achieves promising results for short-term prediction. Despite these improvements, additional clinical studies are warranted to extend forecasting to longer-term prediction horizons.
Collapse
Affiliation(s)
- Alexander Marx
- Department of Computer Science, ETH Zurich, Zurich, Switzerland
| | | | | | | | - Marc Pfister
- Pediatric Pharmacology and Pharmacometrics, University Children’s Hospital Basel, Basel, Switzerland
- Department of Clinical Research, University Hospital Basel, Basel, Switzerland
| | - Marie-Anne Burckhardt
- Department of Clinical Research, University Hospital Basel, Basel, Switzerland
- Pediatric Endocrinolgy and Diabetology, University Children’s Hospital Basel, Basel, Switzerland
| | - Sara Bachmann
- Department of Clinical Research, University Hospital Basel, Basel, Switzerland
- Pediatric Endocrinolgy and Diabetology, University Children’s Hospital Basel, Basel, Switzerland
| | - Julia E. Vogt
- Department of Computer Science, ETH Zurich, Zurich, Switzerland
| |
Collapse
|
3
|
Sutter T, Roth JA, Chin-Cheong K, Hug BL, Vogt JE. A comparison of general and disease-specific machine learning models for the prediction of unplanned hospital readmissions. J Am Med Inform Assoc 2021; 28:868-873. [PMID: 33338231 DOI: 10.1093/jamia/ocaa299] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2020] [Accepted: 11/17/2020] [Indexed: 11/14/2022] Open
Abstract
Unplanned hospital readmissions are a burden to patients and increase healthcare costs. A wide variety of machine learning (ML) models have been suggested to predict unplanned hospital readmissions. These ML models were often specifically trained on patient populations with certain diseases. However, it is unclear whether these specialized ML models-trained on patient subpopulations with certain diseases or defined by other clinical characteristics-are more accurate than a general ML model trained on an unrestricted hospital cohort. In this study based on an electronic health record cohort of consecutive inpatient cases of a single tertiary care center, we demonstrate that accurate prediction of hospital readmissions may be obtained by general, disease-independent, ML models. This general approach may substantially decrease the cost of development and deployment of respective ML models in daily clinical routine, as all predictions are obtained by the use of a single model.
Collapse
Affiliation(s)
- Thomas Sutter
- Medical Data Science, Department of Computer Science, ETH Zurich, Zurich, Switzerland.,Swiss Institute of Bioinformatics, Lausanne, Switzerland
| | - Jan A Roth
- University of Basel, Basel, Switzerland.,Division of Infectious Diseases and Hospital Epidemiology, University Hospital Basel, Basel, Switzerland.,Basel Institute for Clinical Epidemiology and Biostatistics, University Hospital Basel, Switzerland, Basel
| | - Kieran Chin-Cheong
- Medical Data Science, Department of Computer Science, ETH Zurich, Zurich, Switzerland.,Swiss Institute of Bioinformatics, Lausanne, Switzerland
| | - Balthasar L Hug
- University of Basel, Basel, Switzerland.,Department of Internal Medicine, Kantonsspital Luzern, Lucerne, Switzerland
| | - Julia E Vogt
- Medical Data Science, Department of Computer Science, ETH Zurich, Zurich, Switzerland.,Swiss Institute of Bioinformatics, Lausanne, Switzerland
| |
Collapse
|