CD8+ T-cell differentiation and dysfunction inform treatment response in acute myeloid leukemia.

The interplay between T-cell states of differentiation, dysfunction, and treatment response in acute myeloid leukemia (AML) remains unclear. Here, we leveraged a multimodal approach encompassing high-dimensional flow cytometry and single-cell transcriptomics and found that early memory CD8+ T cells are associated with therapy response and exhibit a bifurcation into 2 distinct terminal end states. One state is enriched for markers of activation, whereas the other expresses natural killer (NK)-like and senescence markers.

Learning Predictive and Interpretable Timeseries Summaries from ICU Data.

Machine learning models that utilize patient data across time (rather than just the most recent measurements) have increased performance for many risk stratification tasks in the intensive care unit. However, many of these models and their learned representations are complex and therefore difficult for clinicians to interpret, creating challenges for validation. Our work proposes a new procedure to learn summaries of clinical timeseries that are both predictive and easily understood by humans.

Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise As Much As Possible.

We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance. Our model exhibits an interpretable gating function that provides information on when human rules should be followed or avoided. The gating function is maximized for using human-based rules, and classification errors are minimized.

Real-time prediction of COVID-19 related mortality using electronic health records.

Coronavirus disease 2019 (COVID-19) is a respiratory disease with rapid human-to-human transmission caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to the exponential growth of infections, identifying patients with the highest mortality risk early is critical to enable effective intervention and prioritisation of care. Here, we present the COVID-19 early warning system (CovEWS), a risk scoring system for assessing COVID-19 related mortality risk that we developed using data amounting to a total of over 2863 years of observation time from a cohort of 66 430 patients seen at over 69 healthcare institutions.

Information Bottleneck for Estimating Treatment Effects with Systematically Missing Covariates.

Estimating the effects of an intervention from high-dimensional observational data is a challenging problem due to the existence of confounding. The task is often further complicated in healthcare applications where a set of observations may be entirely missing for certain patients at test time, thereby prohibiting accurate inference. In this paper, we address this issue using an approach based on the information bottleneck to reason about the effects of interventions.

Host Genomics of the HIV-1 Reservoir Size and Its Decay Rate During Suppressive Antiretroviral Treatment.

Background: The primary hurdle for the eradication of HIV-1 is the establishment of a latent viral reservoir early after primary infection. Here, we investigated the potential influence of human genetic variation on the HIV-1 reservoir size and its decay rate during suppressive antiretroviral treatment.

Setting: Genome-wide association study and exome sequencing study to look for host genetic determinants of HIV-1 reservoir measurements in patients enrolled in the Swiss HIV Cohort Study, a nation-wide prospective observational study.

Determinants of HIV-1 reservoir size and long-term dynamics during suppressive ART.

The HIV-1 reservoir is the major hurdle to a cure. We here evaluate viral and host characteristics associated with reservoir size and long-term dynamics in 1,057 individuals on suppressive antiretroviral therapy for a median of 5.4 years.

Improving counterfactual reasoning with kernelised dynamic mixing models.

Simulation-based approaches to disease progression allow us to make counterfactual predictions about the effects of an untried series of treatment choices. However, building accurate simulators of disease progression is challenging, limiting the utility of these approaches for real world treatment planning. In this work, we present a novel simulation-based reinforcement learning approach that mixes between models and kernel-based approaches to make its forward predictions.

Combining Kernel and Model Based Learning for HIV Therapy Selection.

We present a mixture-of-experts approach for HIV therapy selection. The heterogeneity in patient data makes it difficult for one particular model to succeed at providing suitable therapy predictions for all patients. An appropriate means for addressing this heterogeneity is through combining kernel and model-based techniques.

Lymphoedema in young patients with breast cancer.

Gross lymphoedema is a devastating complication in patients with breast cancer and more so in young women. These patients present with more advanced disease and suffer a higher incidence of loco-regional recurrence. Young women are also subject to more traumas to the lymphatics by virtue of their being more active.

Hyperglycemia in the critically ill patient.

Hyperglycemia and insulin resistance are common among critically ill patients and occur in patients with or without a history of diabetes mellitus. All patients undergoing critical illness are at risk for stress-induced hyperglycemia. Some patients may be at greater risk for hyperglycemia than others when considering underlying disease states and iatrogenic factors.

A registration framework for the comparison of mammogram sequences.

In this paper, we present a two-stage algorithm for mammogram registration, the geometrical alignment of mammogram sequences. The rationale behind this paper stems from the intrinsic difficulties in comparing mammogram sequences. Mammogram comparison is a valuable tool in national breast screening programs as well as in frequent monitoring and hormone replacement therapy (HRT).

A mammographic image analysis method to detect and measure changes in breast density.

We present an image analysis method that can detect and measure breast density from digitised mammograms. We present initial results on applying our method to characterise breast changes, in particular, changes due to Hormone Replacement Therapy (HRT). It has been established that long-term use of certain hormone replacement therapies can increase the risk of breast cancer, a fact that encourages the notion that objective measures of tissue density can be an important development in breast cancer image analysis.

Diagnostic accuracy of mammography and scintimammography in detection of primary breast cancer related size of the tumour.

Background: The detection of breast cancer relies on physical examination and mammography (XMM). The sensitivity of conventional imaging is lesions-size dependent. However, mammography has good sensitivity in small tumours when microcalcification is present, but the sensitivity is relatively low in other small tumours.

The role of scintimammography and mammography in recurrent breast cancer. Evaluation of their accuracy using ROC curves.

Background: With the increasing demand for breast conservation surgery, the probability of recurrent tumour within the breast increases. Traditionally x-ray mammography (XMM) was used to assess the post-surgical breast, but post-surgery and radiotherapy changes have reduced the accuracy of this method. Scintimammography (SMM) has also been proposed and appears to be more accurate than XMM.

Can scintimammography with (99m)Tc-MIBI identify multifocal and multicentric primary breast cancer?

Scintimammography with (99m)Tc-MIBI has been shown to be an effective adjunct to imaging of the breast with mammography. Uptake of (99m)Tc-MIBI is particularly high in sites of non-calcified cancer and ductal carcinoma in situ (DCIS), and as a consequence it may be possible to use this method of imaging in identifying multifocal or multicentric disease. The aim of this study was to evaluate the efficacy of preoperative scintimammography in the detection of multifocal and multicentric breast cancer and compare these results with mammography.

Correlation between uptake of Tc-99m sestaMIBI and prognostic factors of breast cancer.

Unlabelled: The purpose of this retrospective study was assessment of correlation between Tc-99m sestaMIBI uptake and some prognostic factors of breast cancer. The following prognostic factors have been included in this study: size of the tumour, age of the patients, axilla node involvement, oestrogen and progesterone receptor (ER, PR) status, grading system of Bloom-Richardson and Ki-67 antigen expression.

Methods: 79 patients were enrolled in this study, with 85 lesions confirmed as primary breast cancers.

Prone SPET scintimammography.

Prone single photon emission tomography (SPET) was performed in 24 patients with suspected primary or recurrent breast cancer to determine if this technique offers more accurate imaging than that obtained from planar scintimammography. All patients were imaged on a specially designed couch with two cushion inserts. The first insert was lined with lead and was used to perform prone lateral planar scintimammography 5 min after the injection of 740 MBq 99Tcm-MIBI.

Use of 99Tcm-MIBI in the assessment of patients with suspected recurrent breast cancer.

A prospective trial was performed to assess the accuracy of 99Tcm-methoxyisobutyl isonitrile (99Tcm-MIBI) scintimammography and X-ray mammography in 18 patients (mean age 58 years, range 46-79 years) with suspected recurrent breast cancer in the breast and/or loco-regional tissues. All patients had been diagnosed to have breast cancer 1-23 years before scintimammography. Two patients had undergone mastectomy, so that a total of 34 breasts were studied with X-ray mammography and with prone-lateral and anterior scintimammography.

Comparison of accuracy of scintimammography and X-ray mammography in the diagnosis of primary breast cancer in patients selected for surgical biopsy.

Mammography, whilst remaining the first line imaging investigation of suspected primary breast cancer, can be difficult to interpret in patients with fibrous or dense breasts. Radionuclide imaging of the breast (scintimammography) has been suggested as an additional test. The aim of this study was to perform prospectively a comparison of the two techniques in a population with suspected breast cancer.

The effect of chemotherapy on the uptake of technetium-99m sestamibi in breast cancer.

Technetium-99m sestamibi scintimammography has been used primarily in the diagnosis of breast cancer. It has also been suggested that this technique could be used to monitor response to chemotherapy and possibly to predict those patients in whom no response can be expected. An initial study was performed in nine patients with primary breast cancer.

Response of women aged 65-74 to invitation for screening for breast cancer by mammography: a pilot study in London, UK.

Objective: To investigate the response and benefits to be gained from mammographic screening for breast cancer in women aged 65-74, who are not normally invited for screening.

Design: This was a pilot study comprising women aged 65-74 who are not currently invited for routine screening under the NHS breast screening programme. The results from this study were compared with the results of routinely screened women (aged 50-64) from the same health district.

Laser Doppler perfusion imaging--a new technique for measuring breast skin blood flow.

Future detection of breast cancer will probably be based on tissue function such as altered vascularity and blood flow. Assessment of tumour blood flow and its pattern may be significant for prognostic prediction, and early evaluation of treatment response. An ideal method of assessment of perfusion would therefore measure a wide area of the breast without the necessity for surface contact.