Predicting total lung capacity from spirometry: a machine learning approach

Background and objective

Spirometry patterns can suggest that a patient has a restrictive ventilatory impairment; however, lung volume measurements such as total lung capacity (TLC) are required to confirm the diagnosis. The aim of the study was to train a supervised machine learning model that can accurately estimate TLC values from spirometry and subsequently identify which patients would most benefit from undergoing a complete pulmonary function test.

Methods

We trained three tree-based machine learning models on 51,761 spirometry data points with corresponding TLC measurements. We then compared model performance using an independent test set consisting of 1,402 patients. The best-performing model was used to retrospectively identify restrictive ventilatory impairment in the same test set. The algorithm was compared against different spirometry patterns commonly used to predict restriction.

Results

The prevalence of restrictive ventilatory impairment in the test set is 16.7% (234/1402). CatBoost was the best-performing machine learning model. It predicted TLC with a mean squared error (MSE) of 560.1 mL. The sensitivity, specificity, and F1-score of the optimal algorithm for predicting restrictive ventilatory impairment was 83, 92, and 75%, respectively.

Conclusion

A machine learning model trained on spirometry data can estimate TLC to a high degree of accuracy. This approach could be used to develop future smart home-based spirometry solutions, which could aid decision making and self-monitoring in patients with restrictive lung diseases.

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.

Correction to: Tumor fragmentation estimated by volume surface ratio of tumors measured on 18F-FDG PET/CT is an independent prognostic factor of diffuse large B-cell lymphoma

A unit error concerning the tumor volume surface ratio (TVSR) is present throughout the article. The unit reported is "cm" but is actually "mm".

Tumor fragmentation estimated by volume surface ratio of tumors measured on 18F-FDG PET/CT is an independent prognostic factor of diffuse large B-cell lymphoma

INTRODUCTION

Our aim was to study the prognostic value of two new ¹⁸F-FDG PET biomarkers in diffuse large B-cell lymphoma (DLBCL). We examined the total tumor surface (TTS), describing the tumor-host interface, and the tumor volume surface ratio (TVSR), corresponding to the ratio between the total metabolic tumor volume (TMTV) and TTS, describing the tumor fragmentation.

METHODS

We retrospectively included 215 patients with DLBCL. Patients underwent initial ¹⁸F-FDG PET/CT before R-CHOP (73%) or intensified R-CHOP (R-ACVBP) regimens (27%). The TMTV was measured using a fixed threshold value of 41% of SUVmax. To calculate TTS and TVSR, the surface was measured using an in-house software based on the marching cube algorithm. Spearman's rank correlation coefficient (ρ) was computed between TMTV, TTS, and TVSR, and ROC analysis was performed. Survival functions at 5 years were studied using a Kaplan-Meier method and uni/multivariate Cox analysis.

RESULTS

TVSR was poorly correlated with TMTV (ρ = 0.5) and TTS (ρ = 0.26), while TTS was highly correlated with TMTV (ρ = 0.94) and was, therefore, excluded from the analysis. TMTV had the highest area under the ROC curve (0.711) and the best sensitivity (0.797), while TVSR had the best specificity (0.745). The optimal cut-off values to predict 5-year OS were 222 cm³ for TMTV and 6.0 mm for TVSR. Patients with high TMTV and TVSR had significantly worse prognosis in Kaplan-Meier and Cox univariate analysis. In a multivariate Cox analysis combining the International Prognostic Index (IPI), the type of chemotherapy, TMTV, and TVSR, all parameters were independent and significant prognostic factors (HR [95%CI]: IPI 1.4 [1.1-1.8], type of chemotherapy 4.5 [2.0-10.5], TMTV 2.8 [1.4-5.5], TVSR 2.1 [1.3-3.4]). A synergistic effect between TMTV and TVSR was observed in a Kaplan-Meier analysis combining the two parameters.

CONCLUSIONS

TVSR measured on the initial ¹⁸F-FDG PET is an independent prognostic factor in DLBCL and has an additional prognostic value when combined with TMTV, IPI score and chemotherapy.

Combination of baseline FDG PET/CT total metabolic tumour volume and gene expression profile have a robust predictive value in patients with diffuse large B-cell lymphoma

PURPOSE

This study evaluated the predictive significance of total metabolic tumour volume (TMTV) measured on baseline FDG PET/CT and its value in addition to gene expression profiling using a new method of gene analysis (rapid reverse transcriptase multiplex ligation-dependent probe amplification assay, RT-MLPA) in patients with diffuse large B-cell lymphoma treated with R-CHOP or R-CHOP-like chemotherapies.

METHODS

The analysis included 114 patients. TMTV was measured using a 41% SUVmax threshold and tumours were classified into GCB or ABC subtypes according to the RT-MLPA assay.

RESULTS

The median follow-up was 40 months. the 5-year progression-free survival (PFS) was 54% and the 5-year overall survival (OS) was 62%. The optimal TMTV cut-off value was 261 cm³. In 59 patients with a high TMTV the 5-year PFS and OS were 37% and 39%, respectively, in comparison with 72% and 83%, respectively, in 55 patients with a low TMTV (p = 0.0002 for PFS, p < 0.0001 for OS). ABC status was significantly associated with a worse prognosis. TMTV combined with molecular data identified three groups with very different outcomes: (1) patients with a low TMTV whatever their phenotype (n = 55), (2) patients with a high TMTV and GCB phenotype (n = 33), and (3) patients with a high TMTV and ABC phenotype (n = 26). In the three groups, 5-year PFS rates were 72%, 51% and 17% (p < 0.0001), and 5-year OS rates were 83%, 55% and 17% (p < 0.0001), respectively. In multivariate analysis, TMTV, ABC/GCB phenotype and International Prognostic Index were independent predictive factors for both PFS and OS (p < 0.05 for both).

CONCLUSIONS

This integrated risk model could lead to more accurate selection of patients that would allow better individualization of therapy.

Predictive value of initial FDG-PET features for treatment response and survival in esophageal cancer patients treated with chemo-radiation therapy using a random forest classifier

Purpose

In oncology, texture features extracted from positron emission tomography with 18-fluorodeoxyglucose images (FDG-PET) are of increasing interest for predictive and prognostic studies, leading to several tens of features per tumor. To select the best features, the use of a random forest (RF) classifier was investigated.

Methods

Sixty-five patients with an esophageal cancer treated with a combined chemo-radiation therapy were retrospectively included. All patients underwent a pretreatment whole-body FDG-PET. The patients were followed for 3 years after the end of the treatment. The response assessment was performed 1 month after the end of the therapy. Patients were classified as complete responders and non-complete responders. Sixty-one features were extracted from medical records and PET images. First, Spearman’s analysis was performed to eliminate correlated features. Then, the best predictive and prognostic subsets of features were selected using a RF algorithm. These results were compared to those obtained by a Mann-Whitney U test (predictive study) and a univariate Kaplan-Meier analysis (prognostic study).

Results

Among the 61 initial features, 28 were not correlated. From these 28 features, the best subset of complementary features found using the RF classifier to predict response was composed of 2 features: metabolic tumor volume (MTV) and homogeneity from the co-occurrence matrix. The corresponding predictive value (AUC = 0.836 ± 0.105, Se = 82 ± 9%, Sp = 91 ± 12%) was higher than the best predictive results found using the Mann-Whitney test: busyness from the gray level difference matrix (P < 0.0001, AUC = 0.810, Se = 66%, Sp = 88%). The best prognostic subset found using RF was composed of 3 features: MTV and 2 clinical features (WHO status and nutritional risk index) (AUC = 0.822 ± 0.059, Se = 79 ± 9%, Sp = 95 ± 6%), while no feature was significantly prognostic according to the Kaplan-Meier analysis.

Conclusions

The RF classifier can improve predictive and prognostic values compared to the Mann-Whitney U test and the univariate Kaplan-Meier survival analysis when applied to several tens of features in a limited patient database.

A French cluster of Creutzfeldt-Jakob disease: a molecular analysis

We report the molecular and phenotypic analysis of a French cluster of three cases of Creutzfeldt-Jakob disease (CJD), two of them occurring in 1998 in the same village and the other in 1995 in a neighboring village. Analyses of the occurrence of these events in a close area with less than 3000 inhabitants over the 1992-1999 notification period confirmed that they are rare. This could be explained either by a common source of contamination or by the coincidental occurrence of either sporadic or genetic CJD. We applied genetic analysis and brain PrPres typing to explore these CJD cases. The three patients did not carry any mutation in their prion protein gene coding sequence. All were homozygous for methionine at the polymorphic codon 129. Brain tissue was available from two cases that died in 1998. The two patients showed different PrPres profiles on Western blot and distinct clinico-pathological features. These findings do not support the conclusion that in these three cases, CJD was acquired from a unique source of contamination and suggest that concurrent occurrence of sporadic CJD accounted for this CJD cluster.

Chronic inflammatory demyelinating polyneuropathy: immunopathological and ultrastructural study of peripheral nerve biopsy in 42 cases

The authors recently reexamined the peripheral nerve biopsies from 42 patients with chronic inflammatory demyelinating polyneuropathy (CIDP). There were 27 males and 15 females, aged from 9 to 84 years, and 13 had relapses. No patient had vasculitis, monoclonal gammopathy, tumor, diabetes mellitus, Lyme disease, familial neuropathy, HIV, or any other immune deficiency. In the endoneurium, perivascular inflammatory cell infiltrates were present in only one case, but scattered histiocytes marked by KP1 on paraffin-embedded fragments were present in every case and there were no T-lymphocytes. At ultrastructural examination macrophage-associated demyelination was observed in 17 cases, of which 6 had relapses separated by intervals of several months or years. Axonal lesions without associated primary demyelination were observed in 4 cases and 3 of these had relapses. Thirty-two patients had mixed lesions of demyelination and axonal involvement. This study confirms other recent data indicating that in all cases of CIDP, macrophages are present in the endoneurium. Macrophage-associated demyelination is the characteristic feature of demyelinating forms. On the other hand, isolated primary axonal forms, which have been known since 1989, are relatively frequent and prone to relapses.

[Cerebral embolism of cardiac origin]

Embolisms of cardiac origin represent approximately 15 p. cent of the causes of cerebral vascular accidents. This article considers the difficult diagnostic and therapeutic problems raised by cerebral embolisms. First: arguments permitting to suspect this mechanism in the absence of an obvious cardiac cause or in the presence of a high incidence heart disease but low embolic potential. The main etiologies are then reviewed emphasizing the evolution of their respective frequencies, then a program of additional investigative examinations is suggested. Finally the indication of anticoagulants is discussed according to neurological and cardiologic criteria.

Brain water and aging

Edematous reactions surrounding brain lesions are less extensive in old patients. There also is a general tendency of the aging brain to be vulnerable to osmotic stress, to yield space, and to collapse. In order to elucidate these clinical phenomena, brain sodium, potassium and water, brain osmolarity, and Na+-K+-ATPase activity were studied in old and young rats following three experimental aggressions: cold induced vasogenic edema, osmotically induced edema, and osmotically induced dehydration. This study supports the hypothesis that: (a) extracellular edema is slightly smaller in the aged brain, but cellular swelling is relatively greater and (b) that protective adaptation of brain volume to acute osmotic changes is less efficient and slower in the aged brain.

[Indications for the long-term electrocardiogram and echocardiogram after a cerebral ischemia complication]

Ninety patients admitted to a neurology unit for cerebral ischaemic accident without evidence of embolism from the heart were examined by ambulatory electrocardiographic monitoring (AEM) and by echocardiography assessable in 76 cases. On the basis of a standard cardiac evaluation (SCE) including physical examination, chest radiography and electrocardiography, the patients were divided into 3 groups: 42 with normal SCE (group I), 19 with isolated arterial hypertension (group II) and 36 with patent cardiac disease (group III). Significant abnormalities were detected by AEM in 10.5% of group I patients, 18.5% of group II patients and 33% of group III patients. A structural cardiopathy was discovered at echocardiography in 33%, 62% and 91% respectively of patients in these 3 groups. The greatest number of mitral valve prolapses (7/9 cases) was found in group I. The main echocardiographic abnormality detected in group II was dilatation of the left cardiac cavities: atrium more than 38 mm in 8 cases, ventricle more than 50 mm in 3 cases. Comparisons between the two explorations showed that arrhythmias were often associated with dilatation of the left cardiac cavities (39%) and much less frequently with mitral valve prolapse (11%) and myocardial hypertrophy (16%). Our results suggest that when examinations cannot be routinely performed in hospital patients with a cerebral ischaemic accident echocardiography should be reserved to patients with heart disease or hypertension, and AEM to those with heart disease or hypertension and with dilatation of the left cardiac cavities.

Eating seizures

An 18-year old man had a cluster of three seizures in a few hours and then remained seizure-free without medication; his mother has experienced seizures induced by movement. A 29-year-old man has had recurrent seizures for six years. In both cases, seizures were partial motor seizures induced by chewing. They are considered to be a particular variety of movement-induced seizures triggered by proprioceptive afferents of muscular origin. This explanation does not account for the great majority of the 63 published cases of seizures precipitated by eating. Eating seizures represent a heterogeneous group of seizures with discrete electroclinical signs and mechanisms. The term "eating seizures" should be preferred to the term "eating epilepsy."

Brain water and aging

Brain water content and Na/K-ATPase activity have been compared in two groups of rats aged 60 +/- 5 days (group I) and 630 +/- 10 days (group II). In group II control animals, brain water content (p less than 0.001) and Na/K-ATPase activity (p less than 0.02) were found to be significantly reduced. Following a cryogenic lesion of the brain, the increase in water content was larger in group I (not significant), whereas impairment of Na/K-ATPase activity was much more pronounced in group II (p less than 0.001).

Cavernous sinus syndrome due to lymphoma

In both the cases described, painful ophthalmoplegia was the first indication of infiltration of the cavernous sinus by a lymphosarcoma. The onset of symptoms and the course of the disease were different in the two cases. CT scan which has been the crucial investigation for detecting lymphomas in the cavernous sinus, was normal in the early stages. Symptomatic remission could be obtained with treatment, although the prognosis remained poor.