Clinical Application of AMH Measurement in Assisted Reproduction

Anti-Müllerian hormone reflects the continuum of the functional ovarian reserve, and as such can predict ovarian response to gonadotropin stimulation and be used to individualize treatment pathways to improve efficacy and safety. However, consistent with other biomarkers and age-based prediction models it has limited ability to predict live birth and should not be used to refuse treatment, but rather to inform counselling and shared decision making. The use of absolute clinical thresholds to stratify patient phenotypes, assess discordance and individualize treatment protocols in non-validated algorithms combined with the lack of standardization of assays may result in inappropriate classification and sub-optimal clinical decision making. We propose that holistic baseline phenotyping, incorporating antral follicle count and other patient characteristics is critical. Treatment decisions driven by validated algorithms that use ovarian reserve biomarkers as continuous measures, reducing the risk of misclassification, are likely to improve overall outcomes for our patients.

Download Full-text

APhA Drug Treatment Protocols Support Clinical Decision-Making and Patient Care

Journal of the American Pharmaceutical Association (1996) ◽

10.1016/s1086-5802(16)30260-1 ◽

1997 ◽

Vol 37 (5) ◽

pp. 503-509

Author(s):

Patti Gasdek Manolakis

Keyword(s):

Decision Making ◽

Drug Treatment ◽

Patient Care ◽

Clinical Decision Making ◽

Clinical Decision ◽

Treatment Protocols

Download Full-text

Artificial Intelligence in Lung Cancer: Bridging the Gap Between Computational Power and Clinical Decision-Making

Canadian Association of Radiologists Journal ◽

10.1177/0846537120941434 ◽

2020 ◽

pp. 084653712094143

Author(s):

Jaryd R. Christie ◽

Pencilla Lang ◽

Lauren M. Zelko ◽

David A. Palma ◽

Mohamed Abdelrazek ◽

...

Keyword(s):

Artificial Intelligence ◽

Lung Cancer ◽

Decision Making ◽

Clinical Decision Making ◽

Prediction Models ◽

Biomarker Discovery ◽

Surgical Techniques ◽

Clinical Decision ◽

Clinical Implementation ◽

Cancer Management

Lung cancer remains the most common cause of cancer death worldwide. Recent advances in lung cancer screening, radiotherapy, surgical techniques, and systemic therapy have led to increasing complexity in diagnosis, treatment decision-making, and assessment of recurrence. Artificial intelligence (AI)–based prediction models are being developed to address these issues and may have a future role in screening, diagnosis, treatment selection, and decision-making around salvage therapy. Imaging plays an essential role in all components of lung cancer management and has the potential to play a key role in AI applications. Artificial intelligence has demonstrated value in prognostic biomarker discovery in lung cancer diagnosis, treatment, and response assessment, putting it at the forefront of the next phase of personalized medicine. However, although exploratory studies demonstrate potential utility, there is a need for rigorous validation and standardization before AI can be utilized in clinical decision-making. In this review, we will provide a summary of the current literature implementing AI for outcome prediction in lung cancer. We will describe the anticipated impact of AI on the management of patients with lung cancer and discuss the challenges of clinical implementation of these techniques.

Download Full-text

P05.82 Clinical decision making. The route from an ontology to a prediction model for stereotactic radiotherapy: PRE.M.I.S.E. (PREdiction Models in Stereotactic External Radiotherapy)

Neuro-Oncology ◽

10.1093/neuonc/noy139.408 ◽

2018 ◽

Vol 20 (suppl_3) ◽

pp. iii322-iii322

Author(s):

F Bianciardi ◽

S Chiesa ◽

B Tolu ◽

S Longo ◽

G Minniti ◽

...

Keyword(s):

Decision Making ◽

Prediction Model ◽

Stereotactic Radiotherapy ◽

Clinical Decision Making ◽

Prediction Models ◽

Clinical Decision ◽

External Radiotherapy

Download Full-text

Calibration: the Achilles heel of predictive analytics

BMC Medicine ◽

10.1186/s12916-019-1466-7 ◽

2019 ◽

Vol 17 (1) ◽

Cited By ~ 40

Author(s):

Ben Van Calster ◽

◽

David J. McLernon ◽

Maarten van Smeden ◽

Laure Wynants ◽

...

Keyword(s):

Decision Making ◽

Clinical Decision Making ◽

Prediction Models ◽

Predictive Analytics ◽

External Validation ◽

Clinical Decision ◽

Machine Learning Algorithms ◽

Model Complexity ◽

Patient Counseling ◽

Flexible Machine

Abstract Background The assessment of calibration performance of risk prediction models based on regression or more flexible machine learning algorithms receives little attention. Main text Herein, we argue that this needs to change immediately because poorly calibrated algorithms can be misleading and potentially harmful for clinical decision-making. We summarize how to avoid poor calibration at algorithm development and how to assess calibration at algorithm validation, emphasizing balance between model complexity and the available sample size. At external validation, calibration curves require sufficiently large samples. Algorithm updating should be considered for appropriate support of clinical practice. Conclusion Efforts are required to avoid poor calibration when developing prediction models, to evaluate calibration when validating models, and to update models when indicated. The ultimate aim is to optimize the utility of predictive analytics for shared decision-making and patient counseling.

Download Full-text

Machine Learning based Autism Grading for Clinical Decision Making

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.d5315.118419 ◽

2019 ◽

Vol 8 (4) ◽

pp. 7443-7446

Keyword(s):

Machine Learning ◽

Decision Making ◽

Autism Spectrum Disorder ◽

Clinical Decision Making ◽

Prediction Models ◽

Clinical Decision ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Diagnostic Process ◽

Manhattan Distance

Autism spectrum disorder is a pervasive developmental disorder that affects the behavioral and communication function of the children. It shows poor performance in communication, social and cognitive abilities, which are generally characterized by developmental delays and abnormal activities in their regular work. Early intervention can reduce the autism spectrum disorders. Machine learning techniques are used to detect autistic features in childhood. The prediction models are implemented as classification problem in which model is constructed by using real-time autism dataset. The proposed work is use Backpropagation and learning vector quantization with different distance measures like Euclidean Distance, Manhattan Distance, and City Block Distance to predict whether a child has autism spectrum disorder and also defines the grade of the autism. So that it can be supported for the clinical decision making. It enables automated clinical autism spectrum disorder diagnostic process using machine learning models.

Download Full-text

The Influence of Personalised Sarcoma Care (PERSARC) Prediction Modelling on Clinical Decision Making in a Multidisciplinary Setting

Sarcoma ◽

10.1155/2021/8851354 ◽

2021 ◽

Vol 2021 ◽

pp. 1-6

Author(s):

H. S. Femke Hagenmaier ◽

Annelies G. K. van Beeck ◽

Rick L. Haas ◽

Veroniek M. van Praag ◽

Leti van Bodegom-Vos ◽

...

Keyword(s):

Decision Making ◽

Clinical Decision Making ◽

Treatment Decision ◽

Clinical Decision ◽

Patient Centered ◽

Treatment Protocols ◽

Treatment Decision Making ◽

Heterogenous Group ◽

Centered Care ◽

Made In

Background. With soft-tissue sarcoma of the extremity (ESTS) representing a heterogenous group of tumors, management decisions are often made in multidisciplinary team (MDT) meetings. To optimize outcome, nomograms are more commonly used to guide individualized treatment decision making. Purpose. To evaluate the influence of Personalised Sarcoma Care (PERSARC) on treatment decisions for patients with high-grade ESTS and the ability of the MDT to accurately predict overall survival (OS) and local recurrence (LR) rates. Methods. Two consecutive meetings were organised. During the first meeting, 36 cases were presented to the MDT. OS and LR rates without the use of PERSARC were estimated by consensus and preferred treatment was recorded for each case. During the second meeting, OS/LR rates calculated with PERSARC were presented to the MDT. Differences between estimated OS/LR rates and PERSARC OS/LR rates were calculated. Variations in preferred treatment protocols were noted. Results. The MDT underestimated OS when compared to PERSARC in 48.4% of cases. LR rates were overestimated in 41.9% of cases. With the use of PERSARC, the proposed treatment changed for 24 cases. Conclusion. PERSARC aids the MDT to optimize individualized predicted OS and LR rates, hereby guiding patient-centered care and shared decision making.

Download Full-text

The novel POSEIDON stratification of ‘Low prognosis patients in Assisted Reproductive Technology’ and its proposed marker of successful outcome

F1000Research ◽

10.12688/f1000research.10382.1 ◽

2016 ◽

Vol 5 ◽

pp. 2911 ◽

Cited By ~ 84

Author(s):

Peter Humaidan ◽

Carlo Alviggi ◽

Robert Fischer ◽

Sandro C. Esteves

Keyword(s):

Assisted Reproductive Technology ◽

Ovarian Reserve ◽

Prediction Models ◽

Live Birth Rate ◽

Ovarian Response ◽

Antral Follicle ◽

Antral Follicle Count ◽

Reproductive Technology ◽

Successful Outcome ◽

Specific Patient

In reproductive medicine little progress has been achieved regarding the clinical management of patients with a reduced ovarian reserve or poor ovarian response (POR) to stimulation with exogenous gonadotropins -a frustrating experience for clinicians as well as patients. Despite the efforts to optimize the definition of this subgroup of patients, the existing POR criteria unfortunately comprise a heterogeneous population and, importantly, do not offer any recommendations for clinical handling. Recently, the POSEIDON group (Patient-Oriented Strategies Encompassing IndividualizeD Oocyte Number) proposed a new stratification of assisted reproductive technology (ART) in patients with a reduced ovarian reserve or unexpected inappropriate ovarian response to exogenous gonadotropins. In brief, four subgroups have been suggested based on quantitative and qualitative parameters, namely, i. Age and the expected aneuploidy rate; ii. Ovarian biomarkers (i.e. antral follicle count [AFC] and anti-Müllerian hormone [AMH]), and iii. Ovarian response - provided a previous stimulation cycle was performed. The new classification introduces a more nuanced picture of the “low prognosis patient” in ART, using clinically relevant criteria to guide the physician to most optimally manage this group of patients. The POSEIDON group also introduced a new measure for successful ART treatment, namely, the ability to retrieve the number of oocytes needed for the specific patient to obtain at least one euploid embryo for transfer. This feature represents a pragmatic endpoint to clinicians and enables the development of prediction models aiming to reduce the time-to-pregnancy (TTP). Consequently, the POSEIDON stratification should not be applied for retrospective analyses having live birth rate (LBR) as endpoint. Such an approach would fail as the attribution of patients to each Poseidon group is related to specific requirements and could only be made prospectively. On the other hand, any prospective approach (i.e. RCT) should be performed separately in each specific group.

Download Full-text

Deep learning for cardiovascular medicine: a practical primer

European Heart Journal ◽

10.1093/eurheartj/ehz056 ◽

2019 ◽

Vol 40 (25) ◽

pp. 2058-2073 ◽

Cited By ~ 48

Author(s):

Chayakrit Krittanawong ◽

Kipp W Johnson ◽

Robert S Rosenson ◽

Zhen Wang ◽

Mehmet Aydar ◽

...

Keyword(s):

Decision Making ◽

Deep Learning ◽

Clinical Decision Making ◽

Image Interpretation ◽

Clinical Decision ◽

Computer Hardware ◽

Cardiovascular Medicine ◽

Treatment Pathways ◽

Challenges And Opportunities ◽

Near Term

AbstractDeep learning (DL) is a branch of machine learning (ML) showing increasing promise in medicine, to assist in data classification, novel disease phenotyping and complex decision making. Deep learning is a form of ML typically implemented via multi-layered neural networks. Deep learning has accelerated by recent advances in computer hardware and algorithms and is increasingly applied in e-commerce, finance, and voice and image recognition to learn and classify complex datasets. The current medical literature shows both strengths and limitations of DL. Strengths of DL include its ability to automate medical image interpretation, enhance clinical decision-making, identify novel phenotypes, and select better treatment pathways in complex diseases. Deep learning may be well-suited to cardiovascular medicine in which haemodynamic and electrophysiological indices are increasingly captured on a continuous basis by wearable devices as well as image segmentation in cardiac imaging. However, DL also has significant weaknesses including difficulties in interpreting its models (the ‘black-box’ criticism), its need for extensive adjudicated (‘labelled’) data in training, lack of standardization in design, lack of data-efficiency in training, limited applicability to clinical trials, and other factors. Thus, the optimal clinical application of DL requires careful formulation of solvable problems, selection of most appropriate DL algorithms and data, and balanced interpretation of results. This review synthesizes the current state of DL for cardiovascular clinicians and investigators, and provides technical context to appreciate the promise, pitfalls, near-term challenges, and opportunities for this exciting new area.

Download Full-text