Breast cancer is the most common cancer and second leading cause of cancer-related death worldwide. The mainstay of breast cancer workup is histopathological diagnosis - which guides therapy and ...prognosis. However, emerging knowledge about the complex nature of cancer and the availability of tailored therapies have exposed opportunities for improvements in diagnostic precision. In parallel, advances in artificial intelligence (AI) along with the growing digitization of pathology slides for the primary diagnosis are a promising approach to meet the demand for more accurate detection, classification and prediction of behaviour of breast tumours. In this article, we cover the current and prospective uses of AI in digital pathology for breast cancer, review the basics of digital pathology and AI, and outline outstanding challenges in the field.
•Limited-channel EEG is a widely used method for EEG monitoring in neonates.•Existing tools for analysis and review are outdated or proprietary.•We have developed an open source toolbox of the most ...commonly used analytic methods.•These tools have been validated by experienced reviewers indicating that they are comparable to closed-source commercial tools.
Limited-channel EEG research in neonates is hindered by lack of open, accessible analytic tools. To overcome this limitation, we have created the Washington University-Neonatal EEG Analysis Toolbox (WU-NEAT), containing two of the most commonly used tools, provided in an open-source, clinically-validated package running within MATLAB.
The first algorithm is the amplitude-integrated EEG (aEEG), which is generated by filtering, rectifying and time-compressing the original EEG recording, with subsequent semi-logarithmic display. The second algorithm is the spectral edge frequency (SEF), calculated as the critical frequency below which a user-defined proportion of the EEG spectral power is located. The aEEG algorithm was validated by three experienced reviewers. Reviewers evaluated aEEG recordings of fourteen preterm/term infants, displayed twice in random order, once using a reference algorithm and again using the WU-NEAT aEEG algorithm. Using standard methodology, reviewers assigned a background pattern classification. Inter/intra-rater reliability was assessed. For the SEF, calculations were made using the same fourteen recordings, first with the reference and then with the WU-NEAT algorithm. Results were compared using Pearson's correlation coefficient.
For the aEEG algorithm, intra- and inter-rater reliability was 100% and 98%, respectively. For the SEF, the mean±SD Pearson correlation coefficient between algorithms was 0.96±0.04.
We have demonstrated a clinically-validated toolbox for generating the aEEG as well as calculating the SEF from EEG data. Open-source access will enable widespread use of common analytic algorithms which are device-independent and unlikely to become outdated as technology changes, thereby facilitating future collaborative research in neonatal EEG.
A prospective cohort study.
In this study, we employed diffusion basis spectrum imaging (DBSI) to quantitatively assess axon/myelin injury, cellular inflammation, and axonal loss of cervical ...spondylotic myelopathy (CSM) spinal cords.
A major shortcoming in the management of CSM is the lack of an effective diagnostic approach to stratify treatments and to predict outcomes. No current clinical diagnostic imaging approach is capable of accurately reflecting underlying spinal cord pathologies.
Seven patients with mild (mJOA ≥15), five patients with moderate (14≥mJOA ≥11), and two patients with severe (mJOA <11) CSM were prospectively enrolled. Given the low number of severe patients, moderate and severe patients were combined for comparison with seven age-matched controls and statistical analysis. We employed the newly developed DBSI to quantitatively measure axon and myelin injury, cellular inflammation, and axonal loss.
Median DBSI-inflammation volume is similar in control (266 μL) and mild CSM (171 μL) subjects, with a significant overlap of the middle 50% of observations (quartile 3 - quartile 1). This was in contrast to moderate CSM subjects that had higher DBSI-inflammation volumes (382 μL; P = 0.033). DBSI-axon volume shows a strong correlation with clinical measures (r = 0.79 and 0.87, P = 1.9 x 10-5 and 2 x 10-4 for mJOA and MDI, respectively). In addition to axon and myelin injury, our findings suggest that both inflammation and axon loss contribute to neurological impairment. Most strikingly, DBSI-derived axon volume declines as severity of impairment increases.
DBSI-quantified axonal loss may be an imaging biomarker to predict functional recovery following decompression in CSM. Our results demonstrate an increase of about 60% in the odds of impairment relative to the control for each decrease of 100 μL in axon volume.
3.
Genomic data are becoming increasingly valuable as we develop methods to utilize the information at scale and gain a greater understanding of how genetic information relates to biological function. ...Advances in synthetic biology and the decreased cost of sequencing are increasing the amount of privately held genomic data. As the quantity and value of private genomic data grows, so does the incentive to acquire and protect such data, which creates a need to store and process these data securely. We present an algorithm for the Secure Interrogation of Genomic DataBases (SIG-DB). The SIG-DB algorithm enables databases of genomic sequences to be searched with an encrypted query sequence without revealing the query sequence to the Database Owner or any of the database sequences to the Querier. SIG-DB is the first application of its kind to take advantage of locality-sensitive hashing and homomorphic encryption to allow generalized sequence-to-sequence comparisons of genomic data.
Recent studies in other fields have suggested that healthcare on the weekend may have worse outcomes. In particular, patients with stroke and acute cardiovascular events have shown worse outcomes ...with weekend treatment. It is unclear whether this extends to patients with spinal cord injury. This study was designed to evaluate factors for readmission after index hospitalization for spinal cord injury.
A total of 795 consecutive patients over an 11-year period were analyzed. After excluding patients with chronic spinal cord injury and surgical care at an outside hospital, 745 patients remained. The primary outcome measure evaluated was 30-day readmission. Secondary measures include perioperative complications, readmission rate when discharged on the weekend, and the effect of race and insurance status on readmission rate. Univariate and multivariate analysis were utilized to evaluate the covariates collected. The χ2 test, Fisher's exact test, and linear and logistic regression methods were utilized for statistical analysis.
A total of 745 patients were analyzed after exclusions. Payer status did not affect length of stay, ICU length of stay, or perioperative complications. Neither weekend admission nor weekend operation affected length of stay, ICU length of stay, or readmission by 30 days. Patients undergoing weekend surgical treatment had lower perioperative complication rates (2.2% vs. 6.5% on weekday, P<0.01). Discharge on the weekend was associated with a significantly lower rate of readmission by 30 days (OR=0.07, 95% CI: 0.009-0.525, P<0.005). Payer status was associated with 30-day readmission (P<0.005). Patients with Medicare (20.8%) and Medicaid (20.1%) showed higher rates of readmission than patients with other payers. 21.1% of African-American patients were readmitted, versus 10.2% of other patients (Odds ratio: 2.2, 95% confidence interval 1.36-3.27, P<0.001). Correcting for payer status lessened but did not eliminate the effect of race on readmission.
Weekend admission did not increase perioperative complications or hospital length of stay. After discharge, patients with Medicaid and Medicare show higher rates of 30-day readmission, as do African-American patients. The effect of race on readmission is multifactorial, and may partially explained by the increased rate of Medicaid coverage in African-Americans in our institutions catchment area.
ObjectivesFew machine learning (ML) models are successfully deployed in clinical practice. One of the common pitfalls across the field is inappropriate problem formulation: designing ML to fit the ...data rather than to address a real-world clinical pain point.MethodsWe introduce a practical toolkit for user-centred design consisting of four questions covering: (1) solvable pain points, (2) the unique value of ML (eg, automation and augmentation), (3) the actionability pathway and (4) the model’s reward function. This toolkit was implemented in a series of six participatory design workshops with care managers in an academic medical centre.ResultsPain points amenable to ML solutions included outpatient risk stratification and risk factor identification. The endpoint definitions, triggering frequency and evaluation metrics of the proposed risk scoring model were directly influenced by care manager workflows and real-world constraints.ConclusionsIntegrating user-centred design early in the ML life cycle is key for configuring models in a clinically actionable way. This toolkit can guide problem selection and influence choices about the technical setup of the ML problem.
This study investigated the effects of eccentric phase-emphasis strength training (EPE) on unilateral strength and performance in 180- and 45-degree change of direction (COD) tasks in rugby union ...players. A 12-week cross-over design was used to compare the efficacy of resistance training executed with 3 s eccentric duration (EPE,
= 12) against conventional strength training, with no constraints on tempo (CON,
= 6). Players in each condition were categorised as 'fast' (FAST) or 'slow' (SLOW) using median trial times from baseline testing. Players recorded greater isometric strength improvements following EPE (ES = -0.54 to 1.80). Whilst these changes were not immediate, players improved in strength following cessation. Improvements in 180-degree COD performance was recorded at all test-points following EPE (ES = -1.32 to -0.15). Improvements in 45-degree COD performance were apparent for FAST following CON (ES = -0.96 to 0.10), but CON was deleterious for SLOW (ES = -0.60 to 1.53). Eccentric phase-emphasis strength training shows potential for sustained strength enhancement. Positive performance changes in COD tasks were category- and condition-specific. The data indicate the greatest improvement occurred at nine weeks following resistance training in these players. Performance benefits may also be specific to COD task, player category, and relative to emphasis on eccentric phase activity.