Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies
Abstract Serious clinical complications (SCC; CTCAE grade ≥ 3) occur frequently in patients treated for hematological malignancies. Early diagnosis and treatment of SCC are essential to improve outcomes. Here we report a deep learning model-derived SCC-Score to detect and predict SCC from time-serie...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-06-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-023-00847-2 |
| _version_ | 1797426560577306624 |
|---|---|
| author | Malte Jacobsen Rahil Gholamipoor Till A. Dembek Pauline Rottmann Marlo Verket Julia Brandts Paul Jäger Ben-Niklas Baermann Mustafa Kondakci Lutz Heinemann Anna L. Gerke Nikolaus Marx Dirk Müller-Wieland Kathrin Möllenhoff Melchior Seyfarth Markus Kollmann Guido Kobbe |
| author_facet | Malte Jacobsen Rahil Gholamipoor Till A. Dembek Pauline Rottmann Marlo Verket Julia Brandts Paul Jäger Ben-Niklas Baermann Mustafa Kondakci Lutz Heinemann Anna L. Gerke Nikolaus Marx Dirk Müller-Wieland Kathrin Möllenhoff Melchior Seyfarth Markus Kollmann Guido Kobbe |
| author_sort | Malte Jacobsen |
| collection | DOAJ |
| description | Abstract Serious clinical complications (SCC; CTCAE grade ≥ 3) occur frequently in patients treated for hematological malignancies. Early diagnosis and treatment of SCC are essential to improve outcomes. Here we report a deep learning model-derived SCC-Score to detect and predict SCC from time-series data recorded continuously by a medical wearable. In this single-arm, single-center, observational cohort study, vital signs and physical activity were recorded with a wearable for 31,234 h in 79 patients (54 Inpatient Cohort (IC)/25 Outpatient Cohort (OC)). Hours with normal physical functioning without evidence of SCC (regular hours) were presented to a deep neural network that was trained by a self-supervised contrastive learning objective to extract features from the time series that are typical in regular periods. The model was used to calculate a SCC-Score that measures the dissimilarity to regular features. Detection and prediction performance of the SCC-Score was compared to clinical documentation of SCC (AUROC ± SD). In total 124 clinically documented SCC occurred in the IC, 16 in the OC. Detection of SCC was achieved in the IC with a sensitivity of 79.7% and specificity of 87.9%, with AUROC of 0.91 ± 0.01 (OC sensitivity 77.4%, specificity 81.8%, AUROC 0.87 ± 0.02). Prediction of infectious SCC was possible up to 2 days before clinical diagnosis (AUROC 0.90 at −24 h and 0.88 at −48 h). We provide proof of principle for the detection and prediction of SCC in patients treated for hematological malignancies using wearable data and a deep learning model. As a consequence, remote patient monitoring may enable pre-emptive complication management. |
| first_indexed | 2024-03-09T08:31:59Z |
| format | Article |
| id | doaj.art-a34c547877334fbd9c99cb0731a5f2a3 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T08:31:59Z |
| publishDate | 2023-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-a34c547877334fbd9c99cb0731a5f2a32023-12-02T19:44:41ZengNature Portfolionpj Digital Medicine2398-63522023-06-01611910.1038/s41746-023-00847-2Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignanciesMalte Jacobsen0Rahil Gholamipoor1Till A. Dembek2Pauline Rottmann3Marlo Verket4Julia Brandts5Paul Jäger6Ben-Niklas Baermann7Mustafa Kondakci8Lutz Heinemann9Anna L. Gerke10Nikolaus Marx11Dirk Müller-Wieland12Kathrin Möllenhoff13Melchior Seyfarth14Markus Kollmann15Guido Kobbe16Faculty of Health, University Witten/HerdeckeDepartment of Computer Science, Heinrich Heine University DüsseldorfDepartment of Neurology, Faculty of Medicine, University of CologneDepartment of Hematology, Oncology, and Clinical Immunology, University Hospital Düsseldorf, Medical Faculty, Heinrich Heine University DüsseldorfDepartment of Internal Medicine I, University Hospital Aachen, RWTH Aachen UniversityDepartment of Internal Medicine I, University Hospital Aachen, RWTH Aachen UniversityDepartment of Hematology, Oncology, and Clinical Immunology, University Hospital Düsseldorf, Medical Faculty, Heinrich Heine University DüsseldorfDepartment of Hematology, Oncology, and Clinical Immunology, University Hospital Düsseldorf, Medical Faculty, Heinrich Heine University DüsseldorfDepartment of Oncology and Hematology, St. Lukas Hospital SolingenScience-Consulting in DiabetesDepartment of Hematology, Oncology, and Clinical Immunology, University Hospital Düsseldorf, Medical Faculty, Heinrich Heine University DüsseldorfDepartment of Internal Medicine I, University Hospital Aachen, RWTH Aachen UniversityDepartment of Internal Medicine I, University Hospital Aachen, RWTH Aachen UniversityMathematical Institute, Heinrich Heine University DüsseldorfFaculty of Health, University Witten/HerdeckeDepartment of Biology, Heinrich Heine University DüsseldorfDepartment of Hematology, Oncology, and Clinical Immunology, University Hospital Düsseldorf, Medical Faculty, Heinrich Heine University DüsseldorfAbstract Serious clinical complications (SCC; CTCAE grade ≥ 3) occur frequently in patients treated for hematological malignancies. Early diagnosis and treatment of SCC are essential to improve outcomes. Here we report a deep learning model-derived SCC-Score to detect and predict SCC from time-series data recorded continuously by a medical wearable. In this single-arm, single-center, observational cohort study, vital signs and physical activity were recorded with a wearable for 31,234 h in 79 patients (54 Inpatient Cohort (IC)/25 Outpatient Cohort (OC)). Hours with normal physical functioning without evidence of SCC (regular hours) were presented to a deep neural network that was trained by a self-supervised contrastive learning objective to extract features from the time series that are typical in regular periods. The model was used to calculate a SCC-Score that measures the dissimilarity to regular features. Detection and prediction performance of the SCC-Score was compared to clinical documentation of SCC (AUROC ± SD). In total 124 clinically documented SCC occurred in the IC, 16 in the OC. Detection of SCC was achieved in the IC with a sensitivity of 79.7% and specificity of 87.9%, with AUROC of 0.91 ± 0.01 (OC sensitivity 77.4%, specificity 81.8%, AUROC 0.87 ± 0.02). Prediction of infectious SCC was possible up to 2 days before clinical diagnosis (AUROC 0.90 at −24 h and 0.88 at −48 h). We provide proof of principle for the detection and prediction of SCC in patients treated for hematological malignancies using wearable data and a deep learning model. As a consequence, remote patient monitoring may enable pre-emptive complication management.https://doi.org/10.1038/s41746-023-00847-2 |
| spellingShingle | Malte Jacobsen Rahil Gholamipoor Till A. Dembek Pauline Rottmann Marlo Verket Julia Brandts Paul Jäger Ben-Niklas Baermann Mustafa Kondakci Lutz Heinemann Anna L. Gerke Nikolaus Marx Dirk Müller-Wieland Kathrin Möllenhoff Melchior Seyfarth Markus Kollmann Guido Kobbe Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies npj Digital Medicine |
| title | Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies |
| title_full | Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies |
| title_fullStr | Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies |
| title_full_unstemmed | Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies |
| title_short | Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies |
| title_sort | wearable based monitoring and self supervised contrastive learning detect clinical complications during treatment of hematologic malignancies |
| url | https://doi.org/10.1038/s41746-023-00847-2 |
| work_keys_str_mv | AT maltejacobsen wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT rahilgholamipoor wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT tilladembek wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT paulinerottmann wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT marloverket wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT juliabrandts wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT pauljager wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT benniklasbaermann wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT mustafakondakci wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT lutzheinemann wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT annalgerke wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT nikolausmarx wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT dirkmullerwieland wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT kathrinmollenhoff wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT melchiorseyfarth wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT markuskollmann wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies AT guidokobbe wearablebasedmonitoringandselfsupervisedcontrastivelearningdetectclinicalcomplicationsduringtreatmentofhematologicmalignancies |