Benchmarking deep learning models on large healthcare datasets.

Introduction Several methods have been developed to electronically monitor patients for severe sepsis, but few provide predictive capabilities to enable early intervention; furthermore, no severe sepsis prediction systems have been previously validated in a randomised study. We tested the use of a machine learning-based severe sepsis prediction system for reductions in average length of stay and in-hospital mortality rate. Methods We conducted a randomised controlled clinical trial at two medical-surgical intensive care units at the University of California, San Francisco Medical Center, evaluating the primary outcome of average length of stay, and secondary outcome of in-hospital mortality rate from December 2016 to February 2017. Adult patients (18+) admitted to participating units were eligible for this factorial, open-label study. Enrolled patients were assigned to a trial arm by a random allocation sequence. In the control group, only the current severe sepsis detector was used; in the experimental group, the machine learning algorithm (MLA) was also used. On receiving an alert, the care team evaluated the patient and initiated the severe sepsis bundle, if appropriate. Although participants were randomly assigned to a trial arm, group assignments were automatically revealed for any patients who received MLA alerts. Results Outcomes from 75 patients in the control and 67 patients in the experimental group were analysed. Average length of stay decreased from 13.0 days in the control to 10.3 days in the experimental group (p=0.042). In-hospital mortality decreased by 12.4 percentage points when using the MLA (p=0.018), a relative reduction of 58.0%. No adverse events were reported during this trial. Conclusion The MLA was associated with improved patient outcomes. This is the first randomised controlled trial of a sepsis surveillance system to demonstrate statistically significant differences in length of stay and in-hospital mortality. Trial registration NCT03015454.

/pdf/effect-of-a-machine-learning-based-severe-sepsis-prediction-h4emcbpoal.pdf

Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial.

Objectives We validate a machine learning-based sepsis-prediction algorithm (InSight) for the detection and prediction of three sepsis-related gold standards, using only six vital signs We evaluate robustness to missing data, customisation to site-specific data using transfer learning and generalisability to new settings Design A machine-learning algorithm with gradient tree boosting Features for prediction were created from combinations of six vital sign measurements and their changes over time Setting A mixed-ward retrospective dataset from the University of California, San Francisco (UCSF) Medical Center (San Francisco, California, USA) as the primary source, an intensive care unit dataset from the Beth Israel Deaconess Medical Center (Boston, Massachusetts, USA) as a transfer-learning source and four additional institutions’ datasets to evaluate generalisability Participants 684 443 total encounters, with 90 353 encounters from June 2011 to March 2016 at UCSF Interventions None Primary and secondary outcome measures Area under the receiver operating characteristic (AUROC) curve for detection and prediction of sepsis, severe sepsis and septic shock Results For detection of sepsis and severe sepsis, InSight achieves an AUROC curve of 092 (95% CI 090 to 093) and 087 (95% CI 086 to 088), respectively Four hours before onset, InSight predicts septic shock with an AUROC of 096 (95% CI 094 to 098) and severe sepsis with an AUROC of 085 (95% CI 079 to 091) Conclusions InSight outperforms existing sepsis scoring systems in identifying and predicting sepsis, severe sepsis and septic shock This is the first sepsis screening system to exceed an AUROC of 090 using only vital sign inputs InSight is robust to missing data, can be customised to novel hospital data using a small fraction of site data and retains strong discrimination across all institutions

https://bmjopen.bmj.com/content/bmjopen/8/1/e017833.full.pdf

Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU

Mortality prediction of intensive care unit (ICU) patients facilitates hospital benchmarking and has the opportunity to provide caregivers with useful summaries of patient health at the bedside. The development of novel models for mortality prediction is a popular task in machine learning, with researchers typically seeking to maximize measures such as the area under the receiver operator characteristic curve (AUROC). The number of ’researcher degrees of freedom’ that contribute to the performance of a model, however, presents a challenge when seeking to compare reported performance of such models. In this study, we review publications that have reported performance of mortality prediction models based on the Medical Information Mart for Intensive Care (MIMIC) database and attempt to reproduce the cohorts used in their studies. We then compare the performance reported in the studies against gradient boosting and logistic regression models using a simple set of features extracted from MIMIC. We demonstrate the large heterogeneity in studies that purport to conduct the single task of ’mortality prediction’, highlighting the need for improvements in the way that prediction tasks are reported to enable fairer comparison between models. We reproduced datasets for 38 experiments corresponding to 28 published studies using MIMIC. In half of the experiments, the sample size we acquired was 25% greater or smaller than the sample size reported. The highest discrepancy was 11,767 patients. While accurate reproduction of each study cannot be guaranteed, we believe that these results highlight the need for more consistent reporting of model design and methodology to allow performance improvements to be compared. We discuss the challenges in reproducing the cohorts used in the studies, highlighting the importance of clearly reported methods (e.g. data cleansing, variable selection, cohort selection) and the need for open code and publicly available benchmarks.

/pdf/reproducibility-in-critical-care-a-mortality-prediction-case-42r433m7gc.pdf

Reproducibility in critical care: a mortality prediction case study

The development an artificial intelligence algorithm for early sepsis diagnosis in the intensive care unit

Stretchable strain sensors with well-controlled sensitivity and stretchability are crucial for applications ranging from large deformation monitoring to subtle vibration detection. Here, based on single-metal material on the elastomer and one-pot evaporation fabrication method, we realize controlled strain sensor performance via a novel programable cracking technology. Specifically, through elastomeric substrate surface chemistry modification, the microcrack generation and morphology evolution of the strain sensing layer is controlled. This process allows for fine tunability of the cracked film morphology, resulting in strain sensing devices with a sensitivity gauge factor of over 10 000 and stretchability up to 100%. Devices with a frequency response up to 5.2 Hz and stability higher than 1000 cycles are reported. The reported strain sensors, tracking both subtle and drastic mechanical deformations, are demonstrated in healthcare devices, human-machine interaction, and smart-home applications.

Tuning Strain Sensor Performance via Programmed Thin-Film Crack Evolution.

A computational approach to mortality prediction of alcohol use disorder inpatients

Functional composites by programming entropy-driven nanosheet growth.

Advances in printing techniques have enabled a new generation of low‐cost and large‐area flexible electronics. However, in applications where a combination of printed components is required, multiple fabrication processes and subsequent integration can be complex and time consuming. Additionally, these applications require devices to be stacked atop each other, reducing overall mechanical flexibility. In this work, surface‐energy‐patterning (SEP) is used to enable simultaneous blade coating of organic photodiode (OPD) and organic light‐emitting diode (OLED) films side‐by‐side. The result is dual functionality on a single flexible substrate. Various active layer solution concentrations are investigated to optimize active layer thicknesses and consequently optimize the performance of each device. A peak spectral responsivity of 0.33 A W−1 at 800 nm is achieved for optimized OPDs and a maximum luminance of 7000 cd m−2 is achieved for optimized OLEDs at an applied bias of 8 V. Overall, this technique enables the printing of two functionally distinct devices in a single step without compromising the performance of either device.

https://rss.onlinelibrary.wiley.com/doi/am-pdf/10.1002/adfm.202112343

Flexible Blade‐Coated Optoelectronic Devices: Dual Functionality via Simultaneous Deposition

Low arterial blood oxygenation (SpO2) is a measure of hypoxemia and a sign of problems relating to breathing and circulation. Progressive drop in arterial SpO2 can be an early indicator of severe disease in COVID-19 patients [1]. A hypoxic state can occur rapidly and without a patient's knowledge; therefore, early detection of SpO2 decline can be lifesaving. In other respiratory system diseases such as COPD and sleep apnea, continuously monitoring of SpO2 with a pulse oximeter can enable timely diagnosis of oxygen desaturation. SpO2 is measured with Photoplethysmography (PPG) that uses a photodetector (PD) to detect either the transmission or reflection of light from the surface of the skin at two different light wavelengths. Commercial fingertip SpO2 sensors are not designed for chronic wear and require user intervention to trigger measurements. Alternatively, wearable SpO2 recording devices in the form of watches and rings can operate in the background with minimal user intervention. However, continuous acquisition of SpO2 can present a significant power burden to a wearable device since high-power LEDs must be powered on for each sample, dominating the power dissipation of the sensor. We present a low-power pulse oximeter sensor IC that utilizes sparse sampling to reduce the overall power by 70%.

An SpO2 Sensor Using Reconstruction-Free Sparse Sampling for 70% System Power Reduction

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Jasmine Jan

Author Tools

Chat about Author