Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

[Keratoconus detection and classification from parameters of the Corvis®ST : A study based on algorithms of machine learning].

In Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft

BACKGROUND AND OBJECTIVE : In the last decades increasingly more systems of artificial intelligence have been established in medicine, which identify diseases or pathologies or discriminate them from complimentary diseases. Up to now the Corvis®ST (Corneal Visualization Scheimpflug Technology, Corvis®ST, Oculus, Wetzlar, Germany) yielded a binary index for classifying keratoconus but did not enable staging. The purpose of this study was to develop a prediction model, which mimics the topographic keratoconus classification index (TKC) of the Pentacam high resolution (HR, Oculus) with measurement parameters extracted from the Corvis®ST.

PATIENTS AND METHODS : In this study 60 measurements from normal subjects (TKC 0) and 379 eyes with keratoconus (TKC 1-4) were recruited. After measurement with the Pentacam HR (target parameter TKC) a measurement with the Corvis®ST device was performed. From this device 6 dynamic response parameters were extracted, which were included in the Corvis biomechanical index (CBI) provided by the Corvis®ST (ARTh, SP-A1, DA ratio 1 mm, DA ratio 2 mm, A1 velocity, max. deformation amplitude). In addition to the TKC as the target, the binarized TKC (1: TKC 1-4, 0: TKC 0) was modelled. The performance of the model was validated with accuracy as an indicator for correct classification made by the algorithm. Misclassifications in the modelling were penalized by the number of stages of deviation between the modelled and measured TKC values.

RESULTS : A total of 24 different models of supervised machine learning from 6 different families were tested. For modelling of the TKC stages 0-4, the algorithm based on a support vector machine (SVM) with linear kernel showed the best performance with an accuracy of 65.1% correct classifications. For modelling of binarized TKC, a decision tree with a coarse resolution showed a superior performance with an accuracy of 95.2% correct classifications followed by the SVM with linear or quadratic kernel and a nearest neighborhood classifier with cubic kernel (94.5% each).

CONCLUSION : This study aimed to show the principle of supervised machine learning applied to a set-up for the modelled classification of keratoconus staging. Preprocessed measurement data extracted from the Corvis®ST device were used to mimic the TKC provided by the Pentacam device with a series of different algorithms of machine learning.

Langenbucher Achim, Häfner Larissa, Eppig Timo, Seitz Berthold, Szentmáry Nóra, Flockerzi Elias


Artificial intelligence, Corvis, Keratoconus, Scheimpflug corneal tomography, Supervised machine learning

Radiology Radiology

Validation of a Deep Learning Algorithm for the Detection of Malignant Pulmonary Nodules in Chest Radiographs.

In JAMA network open

Importance : The improvement of pulmonary nodule detection, which is a challenging task when using chest radiographs, may help to elevate the role of chest radiographs for the diagnosis of lung cancer.

Objective : To assess the performance of a deep learning-based nodule detection algorithm for the detection of lung cancer on chest radiographs from participants in the National Lung Screening Trial (NLST).

Design, Setting, and Participants : This diagnostic study used data from participants in the NLST ro assess the performance of a deep learning-based artificial intelligence (AI) algorithm for the detection of pulmonary nodules and lung cancer on chest radiographs using separate training (in-house) and validation (NLST) data sets. Baseline (T0) posteroanterior chest radiographs from 5485 participants (full T0 data set) were used to assess lung cancer detection performance, and a subset of 577 of these images (nodule data set) were used to assess nodule detection performance. Participants aged 55 to 74 years who currently or formerly (ie, quit within the past 15 years) smoked cigarettes for 30 pack-years or more were enrolled in the NLST at 23 US centers between August 2002 and April 2004. Information on lung cancer diagnoses was collected through December 31, 2009. Analyses were performed between August 20, 2019, and February 14, 2020.

Exposures : Abnormality scores produced by the AI algorithm.

Main Outcomes and Measures : The performance of an AI algorithm for the detection of lung nodules and lung cancer on radiographs, with lung cancer incidence and mortality as primary end points.

Results : A total of 5485 participants (mean [SD] age, 61.7 [5.0] years; 3030 men [55.2%]) were included, with a median follow-up duration of 6.5 years (interquartile range, 6.1-6.9 years). For the nodule data set, the sensitivity and specificity of the AI algorithm for the detection of pulmonary nodules were 86.2% (95% CI, 77.8%-94.6%) and 85.0% (95% CI, 81.9%-88.1%), respectively. For the detection of all cancers, the sensitivity was 75.0% (95% CI, 62.8%-87.2%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.8% (95% CI, 2.6%-5.0%), and the negative predictive value was 99.8% (95% CI, 99.6%-99.9%). For the detection of malignant pulmonary nodules in all images of the full T0 data set, the sensitivity was 94.1% (95% CI, 86.2%-100.0%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.4% (95% CI, 2.2%-4.5%), and the negative predictive value was 100.0% (95% CI, 99.9%-100.0%). In digital radiographs of the nodule data set, the AI algorithm had higher sensitivity (96.0% [95% CI, 88.3%-100.0%] vs 88.0% [95% CI, 75.3%-100.0%]; P = .32) and higher specificity (93.2% [95% CI, 89.9%-96.5%] vs 82.8% [95% CI, 77.8%-87.8%]; P = .001) for nodule detection compared with the NLST radiologists. For malignant pulmonary nodule detection on digital radiographs of the full T0 data set, the sensitivity of the AI algorithm was higher (100.0% [95% CI, 100.0%-100.0%] vs 94.1% [95% CI, 82.9%-100.0%]; P = .32) compared with the NLST radiologists, and the specificity (90.9% [95% CI, 89.6%-92.1%] vs 91.0% [95% CI, 89.7%-92.2%]; P = .91), positive predictive value (8.2% [95% CI, 4.4%-11.9%] vs 7.8% [95% CI, 4.1%-11.5%]; P = .65), and negative predictive value (100.0% [95% CI, 100.0%-100.0%] vs 99.9% [95% CI, 99.8%-100.0%]; P = .32) were similar to those of NLST radiologists.

Conclusions and Relevance : In this study, the AI algorithm performed better than NLST radiologists for the detection of pulmonary nodules on digital radiographs. When used as a second reader, the AI algorithm may help to detect lung cancer.

Yoo Hyunsuk, Kim Ki Hwan, Singh Ramandeep, Digumarthy Subba R, Kalra Mannudeep K


oncology Oncology

Validation of a Machine Learning Algorithm to Predict 180-Day Mortality for Outpatients With Cancer.

In JAMA oncology ; h5-index 85.0

Importance : Machine learning (ML) algorithms can identify patients with cancer at risk of short-term mortality to inform treatment and advance care planning. However, no ML mortality risk prediction algorithm has been prospectively validated in oncology or compared with routinely used prognostic indices.

Objective : To validate an electronic health record-embedded ML algorithm that generated real-time predictions of 180-day mortality risk in a general oncology cohort.

Design, Setting, and Participants : This prognostic study comprised a prospective cohort of patients with outpatient oncology encounters between March 1, 2019, and April 30, 2019. An ML algorithm, trained on retrospective data from a subset of practices, predicted 180-day mortality risk between 4 and 8 days before a patient's encounter. Patient encounters took place in 18 medical or gynecologic oncology practices, including 1 tertiary practice and 17 general oncology practices, within a large US academic health care system. Patients aged 18 years or older with outpatient oncology or hematology and oncology encounters were included in the analysis. Patients were excluded if their appointment was scheduled after weekly predictions were generated and if they were only evaluated in benign hematology, palliative care, or rehabilitation practices.

Exposures : Gradient-boosting ML binary classifier.

Main Outcomes and Measures : The primary outcome was the patients' 180-day mortality from the index encounter. The primary performance metric was the area under the receiver operating characteristic curve (AUC).

Results : Among 24 582 patients, 1022 (4.2%) died within 180 days of their index encounter. Their median (interquartile range) age was 64.6 (53.6-73.2) years, 15 319 (62.3%) were women, 18 015 (76.0%) were White, and 10 658 (43.4%) were seen in the tertiary practice. The AUC was 0.89 (95% CI, 0.88-0.90) for the full cohort. The AUC varied across disease-specific groups within the tertiary practice (AUC ranging from 0.74 to 0.96) but was similar between the tertiary and general oncology practices. At a prespecified 40% mortality risk threshold used to differentiate high- vs low-risk patients, observed 180-day mortality was 45.2% (95% CI, 41.3%-49.1%) in the high-risk group vs 3.1% (95% CI, 2.9%-3.3%) in the low-risk group. Integrating the algorithm into the Eastern Cooperative Oncology Group and Elixhauser comorbidity index-based classifiers resulted in favorable reclassification (net reclassification index, 0.09 [95% CI, 0.04-0.14] and 0.23 [95% CI, 0.20-0.27], respectively).

Conclusions and Relevance : In this prognostic study, an ML algorithm was feasibly integrated into the electronic health record to generate real-time, accurate predictions of short-term mortality for patients with cancer and outperformed routinely used prognostic indices. This algorithm may be used to inform behavioral interventions and prompt earlier conversations about goals of care and end-of-life preferences among patients with cancer.

Manz Christopher R, Chen Jinbo, Liu Manqing, Chivers Corey, Regli Susan Harkness, Braun Jennifer, Draugelis Michael, Hanson C William, Shulman Lawrence N, Schuchter Lynn M, O’Connor Nina, Bekelman Justin E, Patel Mitesh S, Parikh Ravi B


Surgery Surgery

Virtual Reality Anterior Cervical Discectomy and Fusion Simulation on the Novel Sim-Ortho Platform: Validation Studies.

In Operative neurosurgery (Hagerstown, Md.)

BACKGROUND : Virtual reality spine simulators are emerging as potential educational tools to assess and train surgical procedures in safe environments. Analysis of validity is important in determining the educational utility of these systems.

OBJECTIVE : To assess face, content, and construct validity of a C4-C5 anterior cervical discectomy and fusion simulation on the Sim-Ortho virtual reality platform, developed by OSSimTechTM (Montreal, Canada) and the AO Foundation (Davos, Switzerland).

METHODS : Spine surgeons, spine fellows, along with neurosurgical and orthopedic residents, performed a simulated C4-C5 anterior cervical discectomy and fusion on the Sim-Ortho system. Participants were separated into 3 categories: post-residents (spine surgeons and spine fellows), senior residents, and junior residents. A Likert scale was used to assess face and content validity. Construct validity was evaluated by investigating differences between the 3 groups on metrics derived from simulator data. The Kruskal-Wallis test was employed to compare groups and a post-hoc Dunn's test with a Bonferroni correction was utilized to investigate differences between groups on significant metrics.

RESULTS : A total of 21 individuals were included: 9 post-residents, 5 senior residents, and 7 junior residents. The post-resident group rated face and content validity, median ≥4, for the overall procedure and at least 1 tool in each of the 4 steps. Significant differences (P < .05) were found between the post-resident group and senior and/or junior residents on at least 1 metric for each component of the simulation.

CONCLUSION : The C4-C5 anterior cervical discectomy and fusion simulation on the Sim-Ortho platform demonstrated face, content, and construct validity suggesting its utility as a formative educational tool.

Ledwos Nicole, Mirchi Nykan, Bissonnette Vincent, Winkler-Schwartz Alexander, Yilmaz Recai, Del Maestro Rolando F


Anterior cervical discectomy and fusion, Neurosurgical simulation, Surgical education, Surgical simulation, Validation, Virtual reality

Radiology Radiology

Detection of COVID-19 Using Deep Learning Algorithms on Chest Radiographs.

In Journal of thoracic imaging

PURPOSE : To evaluate the performance of a deep learning (DL) algorithm for the detection of COVID-19 on chest radiographs (CXR).

MATERIALS AND METHODS : In this retrospective study, a DL model was trained on 112,120 CXR images with 14 labeled classifiers (ChestX-ray14) and fine-tuned using initial CXR on hospital admission of 509 patients, who had undergone COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR). The test set consisted of a CXR on presentation of 248 individuals suspected of COVID-19 pneumonia between February 16 and March 3, 2020 from 4 centers (72 RT-PCR positives and 176 RT-PCR negatives). The CXR were independently reviewed by 3 radiologists and using the DL algorithm. Diagnostic performance was compared with radiologists' performance and was assessed by area under the receiver operating characteristics (AUC).

RESULTS : The median age of the subjects in the test set was 61 (interquartile range: 39 to 79) years (51% male). The DL algorithm achieved an AUC of 0.81, sensitivity of 0.85, and specificity of 0.72 in detecting COVID-19 using RT-PCR as the reference standard. On subgroup analyses, the model achieved an AUC of 0.79, sensitivity of 0.80, and specificity of 0.74 in detecting COVID-19 in patients presented with fever or respiratory systems and an AUC of 0.87, sensitivity of 0.85, and specificity of 0.81 in distinguishing COVID-19 from other forms of pneumonia. The algorithm significantly outperforms human readers (P<0.001 using DeLong test) with higher sensitivity (P=0.01 using McNemar test).

CONCLUSIONS : A DL algorithm (COV19NET) for the detection of COVID-19 on chest radiographs can potentially be an effective tool in triaging patients, particularly in resource-stretched health-care systems.

Chiu Wan Hang Keith, Vardhanabhuti Varut, Poplavskiy Dmytro, Yu Philip Leung Ho, Du Richard, Yap Alistair Yun Hee, Zhang Sailong, Fong Ambrose Ho-Tung, Chin Thomas Wing-Yan, Lee Jonan Chun Yin, Leung Siu Ting, Lo Christine Shing Yen, Lui Macy Mei-Sze, Fang Benjamin Xin Hao, Ng Ming-Yen, Kuo Michael D


General General

Rapid health data repository allocation using predictive machine learning.

In Health informatics journal ; h5-index 25.0

Health-related data is stored in a number of repositories that are managed and controlled by different entities. For instance, Electronic Health Records are usually administered by governments. Electronic Medical Records are typically controlled by health care providers, whereas Personal Health Records are managed directly by patients. Recently, Blockchain-based health record systems largely regulated by technology have emerged as another type of repository. Repositories for storing health data differ from one another based on cost, level of security and quality of performance. Not only has the type of repositories increased in recent years, but the quantum of health data to be stored has increased. For instance, the advent of wearable sensors that capture physiological signs has resulted in an exponential growth in digital health data. The increase in the types of repository and amount of data has driven a need for intelligent processes to select appropriate repositories as data is collected. However, the storage allocation decision is complex and nuanced. The challenges are exacerbated when health data are continuously streamed, as is the case with wearable sensors. Although patients are not always solely responsible for determining which repository should be used, they typically have some input into this decision. Patients can be expected to have idiosyncratic preferences regarding storage decisions depending on their unique contexts. In this paper, we propose a predictive model for the storage of health data that can meet patient needs and make storage decisions rapidly, in real-time, even with data streaming from wearable sensors. The model is built with a machine learning classifier that learns the mapping between characteristics of health data and features of storage repositories from a training set generated synthetically from correlations evident from small samples of experts. Results from the evaluation demonstrate the viability of the machine learning technique used.

Uddin Md Ashraf, Stranieri Andrew, Gondal Iqbal, Balasubramanian Venki


Big Health data, Blockchain, classifier, deep learning, digital health record storage, electronic health record, machine learning, quality of performance, security and privacy, stream data