Dataset Information

The Subarachnoid Hemorrhage-Weather Myth: A Long-Term Big Data and Deep Learning Analysis.

ABSTRACT: Objective: The frequency of aneurysmal subarachnoid hemorrhage (aSAH) presents complex fluctuations that have been attributed to weather and climate changes in the past. In the present long-term big data and deep learning analysis, we have addressed this long-held myth. Methods: Bleeding dates and basic demographic data for all consecutive patients (n = 1,271) admitted to our vascular center for treatment of aSAH between January 2003 and May 2020 (6,334 days) were collected from our continuously maintained database. The meteorological data of the local weather station, including 13 different weather and climate parameters, were retrieved from Germany's National Meteorological Service for the same period. Six different deep learning models were programmed using the Keras framework and were trained for aSAH event prediction with meteorological data from January 2003 to June 2017, with 10% of this dataset applied for data validation and model improvement. The dataset from July 2017 to May 2020 was tested for aSAH event prediction accuracy for all six models using the area under the receiver operating characteristic curve (AUROC) as the metric. Results: The study group comprised of 422 (33.2%) male and 849 (66.8%) female patients with an average age of 55 ± 14 years. None of the models showed an AUROC larger than 60.2. From the presented data, the influence of weather and climate on the occurrence of aSAH events is extremely unlikely. Conclusion: The myth of special weather conditions influencing the frequency of aSAH is disenchanted by this long-term big data and deep learning analysis.

SUBMITTER: Helsper M

PROVIDER: S-EPMC8131675 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:In about 25% of patients with spontaneous subarachnoid hemorrhage (SAH), a bleeding source cannot be identified during radiological diagnostics. Generally, the outcome of perimesencephalic or prepontine (PM) SAH is known to be significantly better than after non-PM SAH. Data about long-term follow-up concerning physical and mental health are scarce, so this study is reports on long-term results. We measured the influence of PM SAH on a quality-of-life modified Rankin (mRs) scale after six months. For long-term follow-up, a SF-36 questionnaire was used. Questionnaires were sent out between 18 and 168 months after ictus. In 37 patients, a long-term follow-up was available (up to 14 years after SAH). Data detected with the SF-36 questionnaire are compared to reference applicability to the standard population. In total, 37 patients were included for further analysis and divided in 2 subgroups; 13 patients (35%) received subsequent rehabilitation after clinical stay and 24 (65%) did not. In the short-term outcome, a significant improvement from discharge until follow-up was identified in patients with subsequent rehabilitation, but not in the matched pair group without rehabilitation. When PM SAH was compared to the standard population, a reduction in quality of life was identified in physical items (role limitations because of physical health problems, physical functioning) as well as in psychological items (role limitations because of emotional problems). Subsequent rehabilitation on PM SAH patients probably leads to an increase in independence and better mRs. While better mRs was shown at discharge in patients without subsequent rehabilitation, the mRs of rehabilitants was nearly identical after rehabilitation. Patients with good mRs also reached high levels of health-related quality of life (HRQoL) without rehabilitation. Thus, subsequent rehabilitation needs to be encouraged on an individual basis. Indication criteria for subsequent rehabilitation should be defined in further studies to improve patient treatment and efficiency in health care.

Project description:BackgroundDespite improvements in the critical care management of subarachnoid hemorrhage (SAH), a substantial number of patients still suffer from disabilities. In most areas of the world, longitudinal follow-up is not routinely performed, and the patient's trajectory remains unknown.MethodsWe prospectively collected data of 298 consecutive patients with spontaneous SAH and evaluated clinical trajectories at discharge, 3 months, and 1 year after SAH. In a subgroup of patients transferred to a local neurorehabilitation center (Rehab-Hochzirl), we studied the effects of rehabilitation intensity on clinical trajectories. Any decrease in the modified Rankin Scale (mRS) was defined as an improvement, with mRS ≤ 2 indicating good outcome. We used multivariate generalized linear models to investigate associations with clinical trajectories.ResultsOut of the 250 surviving patients, 35% were transferred directly to Rehab-Hochzirl (n = 87 of 250; mRS at discharge = 4), 11% were transferred to another rehabilitation center (n = 27 of 250; mRS = 1), 1% were transferred to a nursing home (n = 3 of 250; mRS = 5), 21% were transferred to their country of origin (n = 52 of 250; mRS = 4), and 32% (n = 79 of 250; mRS = 1) were discharged home. Functional outcome improved in 57% (n = 122 of 215) of patients during the first 3 months, with an additional 16% (35 of 215) improving between 3 and 12 months, resulting in an overall improvement in 73% (n = 157 of 215) of survivors. After 1 year, 60% (n = 179 of 250) of patients were functionally independent. A lower Hunt and Hess scale score at intensive care unit admission, younger age, a lower mRS at intensive care unit discharge, fewer days on mechanical ventilation, and male sex were independently associated with better functional recovery. Although the subgroup of patients transferred to Rehab-Hochzirl were more severely affected, 60% (52 of 87) improved during inpatient neurorehabilitation.ConclusionsOur results indicate ongoing functional improvement in a substantial number of patients with SAH throughout a follow-up period of 12 months. This effect was also observed in patients with severe disability receiving inpatient neurorehabilitation.

Dataset Information

The Subarachnoid Hemorrhage-Weather Myth: A Long-Term Big Data and Deep Learning Analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets